Fact-checked by Grok 2 weeks ago

Picture archiving and communication system

A Picture archiving and communication system (PACS) is a medical imaging technology that digitally acquires, archives, transmits, and displays images from various modalities, enabling the transition from analog film-based workflows to efficient digital management in radiology and beyond.^[1] PACS originated in the early 1980s amid advancements in computing and networking, with the first international conference on the topic held in 1981 in Newport Beach, California, fostering early research in academic and government institutions.^[1] Commercial implementations emerged later in the decade, driven by the need for centralized image handling to improve diagnostic efficiency and reduce costs associated with physical film storage and distribution.^[1] Key components of a PACS include imaging modalities (such as CT scanners and MRI machines) for acquisition, high-capacity archival storage systems (e.g., using magneto-optical disks or cloud-based solutions), transmission networks (often fiber-optic for high-speed data transfer), and display workstations for viewing and interpretation.^[1]^[2] The system also incorporates patient registry and worklist management to streamline workflows, ensuring images are linked to relevant clinical data.^[2] Interoperability is facilitated by the Digital Imaging and Communications in Medicine (DICOM) standard, initially developed in the 1980s as ACR-NEMA versions 1.0 (1985) and 2.0 (1988), and formalized as DICOM 3.0 in 1993 to define formats for image storage and protocols for network communication.^[3] DICOM supports essential services like storage, query/retrieve, and modality worklist, allowing seamless integration across devices and institutions while embedding metadata such as patient information and acquisition parameters.^[3] In modern deployments, PACS integrates with radiology information systems (RIS) for prefetching prior exams and electronic health records (EHR) via standards like HL7 and IHE frameworks, though full EHR interoperability remains a challenge.^[1]^[2] Current architectures favor thin-client, cacheless designs with cloud storage to support remote access and collaboration among diverse healthcare teams, enhancing patient care while prioritizing data security as a Class II medical device under FDA regulation.^[1]^[2]

Fundamentals

Definition and Purpose

A Picture Archiving and Communication System (PACS) is a filmless medical imaging technology that enables the electronic acquisition, storage, transmission, and display of radiological images via digital networks and computer workstations.^[1] Developed to transition radiology from analog film-based processes to digital workflows, PACS replaces traditional hard-copy films with centralized digital repositories, allowing seamless integration into broader healthcare systems such as Radiology Information Systems (RIS) and Hospital Information Systems (HIS).^[1] The primary purposes of PACS include replacing physical film archives to eliminate manual handling and storage, enabling remote access to images for teleradiology, integrating medical images directly into electronic health records for comprehensive patient data management, and streamlining radiology workflows to enhance operational efficiency.^[4] These functions support four main uses: hard copy replacement by digitizing and archiving images to reduce reliance on physical media; remote radiology reading, which allows specialists to interpret studies from off-site locations; electronic integration, facilitating the incorporation of images into patient records across departments; and workflow management, optimizing the sequence of image acquisition, review, and reporting.^[1] Key benefits of PACS encompass reduced physical storage requirements, as digital archives eliminate the need for extensive film libraries and associated maintenance costs, and significantly faster image access—often within seconds via networks compared to hours or more for film development and manual retrieval in traditional systems.^[5] This expedited access contributes to improved patient outcomes by enabling timely diagnostics and reducing delays in clinical decision-making.^[1]

Core Components

A picture archiving and communication system (PACS) comprises four essential components that enable the capture, transmission, storage, and display of medical images: imaging modalities, secure networks, viewing workstations, and long-term archives.^[6] These elements work together to replace traditional film-based systems with digital workflows, ensuring efficient handling of high-volume radiological data.^[1] Imaging modalities, such as computed tomography (CT) scanners, magnetic resonance imaging (MRI) devices, and X-ray systems, serve as the primary sources of image data generation. These devices produce digital images that are formatted to comply with the Digital Imaging and Communications in Medicine (DICOM) standard, facilitating interoperability across systems. Acquisition gateways often interface with modalities to preprocess and convert data into DICOM-compliant files, including tasks like image resizing and orientation correction.^[6] Secure networks form the backbone for transmitting images between components, ensuring reliable and protected data flow within hospitals and to remote sites. These networks typically employ high-bandwidth connections, such as Gigabit Ethernet supporting speeds of 1 Gbps or higher, to handle large image files without delays. Security measures, including encryption and access controls, are integral to prevent unauthorized access during transmission.^[7]^[8] Viewing workstations enable radiologists to interpret and diagnose from images, featuring specialized software for manipulation, annotation, and comparison. High-resolution monitors, often 5-megapixel (5MP) grayscale displays, provide the necessary detail for accurate visualization, particularly for modalities like mammography. These workstations connect via networks and include local caching for quick access.^[9]^[6] Long-term archives store images and associated metadata for extended periods, supporting retrieval for clinical, legal, and research purposes. Storage solutions commonly use redundant array of independent disks (RAID) configurations to ensure data integrity and fault tolerance, with short-term retrieval in seconds and long-term retrieval typically within minutes, though deep archives may require up to 30 minutes. Emerging implementations incorporate cloud-based storage for scalability and off-site redundancy.^[6]^[10] Servers play a critical role in managing data flow: acquisition servers handle initial image capture and routing from modalities, while database servers index metadata such as patient details and study parameters for efficient organization and search. These servers ensure seamless integration among PACS components.^[6]^[11]

Data and Modalities

Types of Images

PACS primarily manages a range of radiology images, including X-rays, which provide two-dimensional projections of internal structures using ionizing radiation; computed tomography (CT) scans, generating cross-sectional images through X-ray rotation; magnetic resonance imaging (MRI), producing detailed soft-tissue contrast via magnetic fields and radio waves; ultrasound images, created by sound wave echoes for real-time visualization; and nuclear medicine images such as positron emission tomography (PET) and single-photon emission computed tomography (SPECT), which map physiological functions using radioactive tracers.^[12]^[13]^[14] Beyond traditional radiology, PACS has expanded to accommodate non-radiology images from various specialties, including echocardiograms in cardiology, which capture cardiac motion via ultrasound; endoscopic images and videos depicting internal organ surfaces; fundus photographs in ophthalmology for retinal assessment; digital pathology slides showing microscopic tissue details; and dermatology photographs documenting skin conditions.^[15]^[16] These extensions enable unified storage and access across clinical departments, often encapsulating non-image data like procedural reports in DICOM format alongside the visuals.^[15] Medical images in PACS exhibit diverse characteristics that influence their handling and display. Dimensionality ranges from 2D static projections, such as plain X-rays, to 3D volumetric datasets reconstructed from serial slices in CT and MRI, allowing multi-planar views.^[14] Most radiology images are grayscale to emphasize density and contrast differences, whereas color is prevalent in Doppler ultrasound for flow visualization and in endoscopy or dermatology for natural tissue representation.^[17] Resolutions vary significantly by modality and application; for instance, digital mammograms achieve high detail with pixel sizes around 50 microns to detect subtle microcalcifications.^[18] Emerging image types are further diversifying PACS capabilities, particularly digital pathology whole-slide images, which are gigapixel scans of entire glass slides enabling virtual microscopy and remote consultation.^[19] Additionally, AI-generated annotations—such as automated segmentations of lesions or overlaid diagnostic markers—are increasingly incorporated to augment human interpretation without replacing core imaging data.^[17] These innovations highlight the evolving data diversity in PACS, with storage requirements scaling from megabytes for 2D X-rays to terabytes for high-resolution whole-slide images.^[20]

Standards and Formats

The Digital Imaging and Communications in Medicine (DICOM) standard serves as the foundational protocol for Picture Archiving and Communication Systems (PACS), ensuring interoperability by defining the file structure, network communication protocols, and metadata conventions for medical imaging data.^[21] DICOM files, typically with a .dcm extension, organize data into datasets comprising attributes such as patient identifiers, study dates, and image pixel data, enabling seamless exchange between imaging devices, archives, and viewing workstations.^[22] The standard's network protocols facilitate services like storage and retrieval over TCP/IP, using abstract syntaxes to specify data types and transfer syntaxes for encoding, such as JPEG or uncompressed formats.^[23] Central to DICOM's functionality are Service-Object Pair (SOP) classes, which pair specific services (e.g., Store or Query/Retrieve) with information objects tailored to imaging modalities like computed tomography (CT) or magnetic resonance imaging (MRI), allowing modalities to transmit standardized image sets to PACS.^[22] The Modality Worklist (MWL) service integrates with hospital information systems to provide acquisition devices with pre-scheduled procedure details, including patient demographics and exam parameters, thereby minimizing data entry errors and enhancing workflow efficiency.^[22] Additionally, DICOM supports encapsulation of non-image data, such as PDFs for reports or JPEG files, within its objects via dedicated attributes, permitting PACS to handle diverse content types while maintaining a unified structure.^[22] Complementing DICOM, the Health Level Seven (HL7) standards govern messaging for administrative and clinical data exchange between PACS and other healthcare systems, such as radiology information systems (RIS) or electronic health records (EHRs), using formats like HL7 v2 for orders and results or FHIR for modern RESTful APIs. Integrating the Healthcare Enterprise (IHE) profiles build on these by outlining practical implementations; for instance, the Cross-Enterprise Document Sharing (XDS) profile enables secure sharing of DICOM studies across institutions via a federated repository. DICOMweb, a RESTful web services extension introduced in 2003, allows browser-based access to images and metadata without proprietary software, supporting modern cloud-based PACS deployments.^[24] Recent supplements also address artificial intelligence (AI) integration, such as new Segmentation Information Object Definitions (IODs) for encoding AI-derived annotations like tumor boundaries, ensuring PACS can store and query model outputs consistently.^[25] These advancements maintain backward compatibility while accommodating emerging technologies in medical imaging.^[26]

Architecture and Workflow

System Design

The system design of a Picture Archiving and Communication System (PACS) typically employs a component-based architecture to ensure efficient image handling across healthcare environments. This includes four primary elements: imaging modalities such as CT scanners and MRI machines that capture and transmit raw images via standardized protocols; a secure network for transmission; the PACS core, consisting of servers that route, process, and store images in a central archive for optimized access; and diagnostic workstations and web-based viewers that enable clinicians to retrieve and interpret images remotely.^[27]^[28]^[29] Network topology in PACS implementations often favors star configurations, where modalities and workstations connect centrally to core servers through switches, facilitating straightforward management and reduced latency, though mesh topologies may be adopted in larger facilities for enhanced redundancy between distributed nodes. To bolster security, Virtual Local Area Networks (VLANs) segment traffic, isolating sensitive imaging data from general hospital networks and minimizing breach risks. Bandwidth demands are substantial for high-resolution transfers, with gigabit Ethernet (1 Gbps) serving as a standard minimum to support seamless movement of large datasets like multi-slice CT studies without bottlenecks.^[28]^[30]^[31] Scalability is achieved through modular server designs that allow incremental addition of storage and processing capacity as imaging volumes grow, coupled with load balancing mechanisms to distribute queries across multiple nodes and prevent single points of failure. Fault-tolerant features, such as redundant power supplies, RAID configurations, and automated failover clustering, ensure 99.999% uptime, critical for uninterrupted clinical workflows in high-volume settings.^[32]^[33] Contemporary PACS designs increasingly incorporate web-based architectures, leveraging HTML5-compatible viewers that operate as zero-footprint clients—requiring no local software installation and enabling access via standard browsers on diverse devices, from desktops to mobile units. This shift enhances interoperability and remote diagnostics while maintaining compliance with security standards like HIPAA.^[34]^[31]

Operational Processes

The operational processes of a Picture Archiving and Communication System (PACS) encompass the dynamic handling of medical images from acquisition to clinical use, ensuring efficient workflow in radiology departments. The end-to-end workflow begins with image acquisition from imaging modalities such as computed tomography (CT), magnetic resonance imaging (MRI), or digital radiography, where digital images are generated and transmitted to the PACS using standardized protocols for immediate processing.^[1] Following acquisition, quality assurance (QA) review occurs, involving automated checks for image integrity, artifacts, or technical errors, often supplemented by technologist verification to confirm diagnostic usability before further routing.^[1] Images then undergo routing to the archive, where they are directed to central storage based on predefined rules, such as patient demographics or study type, facilitating long-term retention while minimizing delays.^[7] Once archived, images proceed to radiologist interpretation at workstations, where clinicians access studies for analysis using specialized viewing software that supports multi-monitor setups and advanced visualization tools. This stage integrates prefetching of prior studies, an automated process that retrieves relevant historical images from the archive upon order entry, allowing side-by-side comparisons to enhance diagnostic accuracy and reduce search time.^[1] Hanging protocols further streamline display by automatically arranging images in predefined layouts—such as tiled grids for multi-series exams or body-part-specific views—mimicking traditional film alternators while adapting to individual radiologist preferences.^[7] Annotation tools enable radiologists to add measurements, arrows, text overlays, or region-of-interest markings directly on images, with these enhancements saved and linked to reports for collaborative review.^[1] After interpretation, the finalized reports and images are prepared for distribution to clinicians, disseminated via secure network access to electronic health records or web-based portals, enabling point-of-care viewing in settings like intensive care units or operating rooms without physical media.^[1] Throughout the workflow, error handling addresses issues like patient data mismatches through automated reconciliation tools, which compare demographics from modality worklists against hospital information systems, flagging discrepancies for manual correction.^[35] These processes rely on integration with storage and retrieval mechanisms for seamless access, as detailed in related sections.^[7] Performance in PACS operations is evaluated through metrics such as throughput, typically targeting 100 studies per hour in high-volume environments to match radiologist reading speeds, and latency, with display times under 2 seconds essential for maintaining workflow efficiency and reducing diagnostic delays.^[36] Modern systems achieve these via optimized networking and caching, though bottlenecks in prefetching or routing can extend latencies to several minutes if not monitored.^[1]

Storage and Retrieval

Archival Mechanisms

Picture archiving and communication systems (PACS) employ a tiered storage hierarchy to ensure data persistence, balancing accessibility, cost, and capacity for medical imaging data. Online storage, typically implemented using high-performance disk arrays such as RAID 6 configurations, provides immediate access to recently acquired or frequently viewed images, with retrieval times in milliseconds and capacities reaching several terabytes in smaller facilities or petabyte-scale in large hospitals.^[37]^[38]^[39] Nearline storage serves as an intermediate layer for data that is less immediately needed, often utilizing optical jukeboxes or robotic tape libraries, allowing access within 30 to 60 seconds at transfer rates of a few megabytes per second, which supports efficient prefetching for clinical workflows while reducing costs compared to online tiers.^[40]^[38]^[41] Offline storage, the most cost-effective for long-term retention, relies on removable media like magnetic tape libraries, where data retrieval may take minutes to hours but enables archival of vast datasets, with modern systems supporting petabyte capacities suitable for multi-year image repositories in enterprise environments.^[40]^[39]^[42] In recent years, vendor-neutral archives (VNAs) have become prominent for long-term storage, decoupling data from proprietary PACS and enabling multi-system access. As of 2025, hybrid cloud storage solutions are widely adopted for scalable, compliant archival, supporting petabyte-scale data with remote accessibility.^[39]^[43] Backup strategies in PACS emphasize redundancy and recovery to mitigate data loss, incorporating full backups that capture entire datasets periodically, alongside incremental backups that record only changes since the prior backup to optimize storage and time efficiency.^[44]^[45] Disaster recovery protocols often include offsite replication to geographically distant sites, ensuring business continuity in the event of hardware failure or site-specific disasters, with recovery time objectives typically targeted under 24 hours for critical imaging data.^[46]^[47] The data lifecycle in PACS is governed by retention policies aligned with applicable regulations and state laws, which typically require maintaining medical imaging records for 5 to 10 years or longer; HIPAA requires retention of certain compliance documents for at least six years, though clinical needs may extend this.^[48]^[49] Lossless compression techniques, notably JPEG 2000 as standardized in DICOM, are applied during archiving to reduce file sizes by 50-70% without quality degradation, facilitating efficient storage of high-resolution modalities like CT and MRI.^[38] Purging of data occurs systematically after the retention period, involving secure deletion protocols to prevent unauthorized access while documenting compliance.^[50]

Querying and Retrieval Methods

The DICOM Query/Retrieve (Q/R) Service Class provides standardized mechanisms for locating and fetching medical imaging data stored in PACS archives, enabling efficient access based on key attributes such as patient ID, study date, accession number, and modality. This service operates at the application layer using DIMSE-C (DICOM Message Service Element for Composite objects) protocols over TCP/IP associations between service class users (SCUs, e.g., workstations) and providers (SCPs, e.g., PACS servers). It supports hierarchical information models like Patient Root, Study Root, and Patient/Study Only, which organize queries across levels from patient to image instance, ensuring referential integrity and scalability in clinical environments. Central to the Q/R service is the C-FIND operation, which allows an SCU to query an SCP for matching Composite SOP Instances using specified key attributes in a Query/Retrieve Information Model. The SCU sends a C-FIND request with identifiers marked as Universal Matching (for wildcards like '*'), Single Value Matching (exact matches, e.g., Patient ID='12345'), or Wildcard Matching, prompting the SCP to return zero or more C-FIND responses with Pending status for each match, followed by a final Success, Failure, or Refused status. For example, a query at the Study Root level might use Study Date (range matching) and Accession Number to retrieve all studies for a patient, supporting both relational and non-relational retrieval modes to optimize database interactions. Advanced Q/R SOP Classes, such as the Study Root Query/Retrieve Information Model, define required, optional, and unique keys (e.g., Study Instance UID as unique) to standardize queries across vendors. Retrieval is facilitated by the C-MOVE and C-GET operations, which transfer SOP Instances identified via prior C-FIND queries. In C-MOVE, the SCU instructs the SCP to initiate C-STORE sub-operations to a specified destination AE (e.g., another workstation or archive), returning Pending responses with remaining and completed sub-operation counts for progress tracking, and handling failures via status codes like 0122H (SOP Class Not Supported) or A7xx (Out of Resources). C-GET, conversely, performs transfers over the existing association without a secondary connection, making it suitable for direct workstation retrieval and avoiding association overhead, though it supports fewer SOP Classes in practice (less than 30% of evaluated PACS).^[51] Error handling in both includes detailed status codes (e.g., 0210H for Sub-operations Complete - No Failures) and optional UID lists of failed instances, ensuring robust operation in distributed PACS environments. For web-based access, the Web Access to DICOM Objects (WADO) standard, defined in DICOM PS3.18, enables URI-based retrieval of persistent DICOM objects from PACS using HTTP/HTTPS protocols, bridging traditional DICOM networks with web clients.^[52] WADO-URI supports simple GET requests with parameters like requestType (WADO/RS for retrieval), studyUID, seriesUID, and objectUID to fetch entire studies, series, or instances in native DICOM format or rendered outputs (e.g., JPEG images with window/level adjustments via viewport and quality parameters).^[53] WADO-WS extends this with RESTful web services, allowing multipart responses for metadata and bulk frames, and integrates querying via QIDO-RS (Query/Retrieve Information for DICOM Objects - RS) to search PACS repositories without full DICOM associations.^[54] These methods support anonymization and transfer syntax negotiation, facilitating secure, browser-based access in modern PACS workflows while maintaining interoperability.^[52] Performance considerations in Q/R methods emphasize handling large result sets through hierarchical queries and relational modes, which reduce database load by limiting responses to matched subsets rather than exhaustive scans. Evaluations of PACS implementations show high support (nearly 100%) for core models like Study Root but variability in advanced features, such as strong semantic matching (average support score of 16.81 out of possible maxima), impacting efficiency for complex queries involving thousands of instances.^[51] Optimized SCPs use indexed databases to manage these scales, ensuring reliable retrieval in high-volume clinical settings.^[51]

Integration and Interoperability

Healthcare System Interfaces

Picture archiving and communication systems (PACS) integrate with radiology information systems (RIS) to facilitate scheduling of imaging exams and distribution of radiology reports, enabling seamless workflow from order placement to result delivery.^[55] PACS connects to hospital information systems (HIS) for accessing patient demographics such as identifiers and admission details, ensuring accurate linking of images to patient records.^[56] Similarly, integration with electronic medical records (EMR) or electronic health records (EHR) provides clinical context, allowing radiologists to view relevant patient history alongside images for informed interpretation.^[55] These interfaces primarily rely on Health Level Seven (HL7) protocols for data exchange. HL7 version 2 and 3 support admission, discharge, and transfer (ADT) messages to update patient information across systems, while order management messages like ORM (order) and ORU (observation results) handle exam requests and report transmission between HIS, RIS, and PACS.^[57] Modern implementations increasingly adopt HL7 Fast Healthcare Interoperability Resources (FHIR), particularly the ImagingStudy resource, which standardizes access to imaging metadata and links to DICOM images via APIs, enhancing interoperability with RIS and EMR for structured data like study descriptions and accession numbers.^[58] Workflow integration through these interfaces supports end-to-end processes in clinical settings. Order management begins with HL7 transactions from HIS to RIS for scheduling, followed by routing to PACS for image acquisition and storage.^[55] Results distribution occurs via HL7 messages that push finalized reports from RIS back to HIS and EMR, ensuring multidisciplinary access.^[56] Context-aware prefetching uses patient data from EMR or HIS—triggered by ADT or query messages—to automatically retrieve prior imaging studies from PACS archives, reducing radiologist search time during interpretation.^[1] Despite these advancements, challenges persist in achieving robust integration. Terminology mapping, such as aligning local codes to standardized ontologies like SNOMED CT for anatomical sites and procedures, is essential for semantic interoperability but often requires manual curation due to inconsistencies across systems.^[59] Handling legacy systems poses additional hurdles, as older PACS and RIS may lack support for contemporary HL7 versions or FHIR, leading to custom interfaces that increase maintenance costs and error risks.^[60]

Vendor Neutral Solutions

A Vendor Neutral Archive (VNA) serves as a centralized, standards-based repository for medical imaging data, operating independently of proprietary Picture Archiving and Communication System (PACS) vendors to enable seamless ingestion and management of images from diverse sources.^[61] By decoupling storage from vendor-specific workflows, VNAs facilitate multi-vendor interoperability, allowing healthcare organizations to consolidate data without being locked into a single supplier's ecosystem.^[62] This approach addresses limitations in traditional PACS, where data silos hinder efficient access and sharing across departments or enterprises.^[63] Key benefits of VNAs include substantial cost savings through the elimination of redundant storage systems and streamlined data management, reducing operational expenses by up to 70% compared to disk-based alternatives in some implementations.^[63] They also simplify migrations between systems by preserving data integrity and avoiding proprietary formats, minimizing downtime and vendor dependency during transitions.^[61] Furthermore, VNAs enhance compliance and interoperability by adhering to Integrating the Healthcare Enterprise (IHE) profiles such as Cross-Enterprise Document Sharing (XDS) and Cross-Community Access (XCA), which support federated archiving and secure data exchange across multiple organizations.^[62]^[64] Implementation of a VNA typically leverages object storage architectures, such as Amazon S3-compatible systems, to provide scalable, cost-effective handling of large imaging datasets with high durability (up to 99.999999999% in enterprise configurations).^[63] Metadata normalization is a core process, involving the dynamic adjustment of DICOM tags and reconstruction of images to standardize varying vendor-specific data for uniform access and retrieval.^[62] Lifecycle management features automate data retention policies, including transitions to lower-cost archival tiers, deletion of expired records, and compliance with regulations like HIPAA through immutable storage options.^[63] Adoption of VNAs has surged since the 2010s, driven by increasing imaging volumes and the need for unified data management, with the global market projected to reach USD 3.26 billion in 2025, growing at a compound annual growth rate (CAGR) of 13.3% through 2033.^[65] In large hospitals, which account for over 60% of the market share due to their high-volume data needs, VNAs have become standard for enterprise-wide imaging consolidation by 2025.^[66]

Advanced Technologies

AI and Analytics Integration

Artificial intelligence (AI) has significantly enhanced picture archiving and communication systems (PACS) by automating diagnostic tasks, improving workflow efficiency, and enabling data-driven decision-making in radiology. Computer-aided detection (CAD) algorithms, integrated into PACS, assist radiologists in identifying lesions such as those in breast imaging by analyzing images for subtle abnormalities that might be overlooked, thereby increasing detection rates while reducing false negatives.^[67] These tools process DICOM images directly within the PACS environment, providing overlays or annotations to highlight potential pathologies.^[68] AI-driven workflow prioritization in PACS flags critical findings, such as pulmonary embolisms or fractures, allowing radiologists to triage urgent cases ahead of routine ones.^[69] For instance, systems like those from Aidoc integrate with PACS to generate real-time alerts, notifying clinicians of high-priority scans and integrating seamlessly into existing reading workflows without disrupting user interfaces.^[70] Predictive analytics further supports resource allocation by forecasting imaging demand based on historical PACS data, optimizing staff scheduling and equipment utilization to prevent bottlenecks during peak periods.^[71] Integration of AI into PACS relies on standardized methods to ensure compatibility and data flow. DICOM Structured Reporting (SR) enables AI outputs, such as measurement annotations or detection probabilities, to be embedded as structured objects within PACS, allowing for easy retrieval and visualization alongside original images.^[72] REST APIs facilitate model deployment by enabling secure, real-time communication between external AI engines and PACS servers, supporting scalable inference without requiring proprietary hardware.^[73] To address privacy concerns in multi-institutional settings, federated learning allows collaborative AI training on distributed PACS datasets without centralizing sensitive imaging data, preserving patient confidentiality under regulations like HIPAA.^[74] Notable examples include AI applications for triaging COVID-19 chest imaging post-2020, where algorithms analyzed CT scans to stratify patients into stable or severe categories, aiding rapid resource deployment in overwhelmed hospitals.^[75] Natural language processing (NLP) has also been integrated into radiology workflows for extracting and analyzing key findings from reports stored in PACS, improving consistency in documentation.^[76] As of 2025, advancements emphasize real-time AI processing via edge computing, where lightweight models run on local PACS hardware to deliver instant analyses, minimizing latency for point-of-care decisions.^[77] Regulatory progress includes numerous FDA-cleared algorithms, such as Aidoc's BriefCase-Triage for flagging critical findings, ensuring clinical validation and safe deployment in PACS workflows.^[78]^[79]

Cloud and Remote Capabilities

Cloud-based Picture Archiving and Communication Systems (PACS) have increasingly adopted Software as a Service (SaaS) models, hosted on platforms such as Microsoft Azure, to deliver on-demand access to medical imaging data without the need for extensive local infrastructure. These SaaS implementations allow healthcare providers to store, retrieve, and manage DICOM-compliant images through web-based interfaces, enhancing flexibility for distributed radiology workflows. Hybrid PACS architectures further support this evolution by integrating on-premises servers for handling sensitive patient data with cloud resources for overflow storage and processing, ensuring compliance with regulations like HIPAA while leveraging external scalability.^[80]^[81]^[82] Remote access capabilities in PACS are secured through Virtual Private Networks (VPNs) and zero-trust security models, which verify every access request regardless of user location, thereby mitigating risks in teleradiology scenarios. These systems enable radiologists to use mobile viewers or web clients for interpreting images from anywhere, supported by multifactor authentication (MFA) and Transport Layer Security (TLS) encryption to protect data in transit and at rest. Teleradiology benefits particularly from such features, allowing off-site specialists to collaborate on urgent cases like stroke imaging without compromising security.^[82]^[83]^[84] Key advantages of cloud-enabled PACS include elastic scaling, where resources auto-provision during high-demand periods such as imaging surges in emergency departments, optimizing performance without manual intervention. Global disaster recovery is bolstered by cloud providers' redundant data centers, enabling rapid failover and minimizing downtime from local failures. Moreover, these models reduce upfront capital costs by converting infrastructure expenses to subscription-based operational fees, making advanced imaging accessible to smaller facilities.^[85]^[80]^[80] By 2025, PACS trends emphasize edge-to-cloud pipelines, where initial image processing occurs at the network edge to reduce latency before full upload to central clouds, supporting efficient data flows in resource-constrained environments. The rollout of 5G networks facilitates real-time remote reading, enabling sub-10-minute interpretations for time-sensitive diagnostics like acute strokes via high-bandwidth, low-latency connections. Integration with telehealth platforms further allows PACS data to feed directly into virtual consultations, promoting multidisciplinary care and remote patient monitoring.^[86]^[86]^[86]

Implementation and Compliance

Acceptance Testing

Acceptance testing for Picture Archiving and Communication Systems (PACS) involves a structured validation process to confirm that the deployed system meets contractual specifications, ensures clinical reliability, and supports safe patient care before full operational use. This phase typically follows installation and initial configuration, encompassing both technical and clinical evaluations to verify functionality, interoperability, and performance across the entire imaging workflow. Rigorous testing is essential to mitigate risks associated with medical imaging systems, where failures could compromise diagnostic accuracy or data integrity. The testing phases begin with unit testing at the component level, where individual modules such as image storage servers or display workstations are examined in isolation to ensure they function correctly according to design specifications. This is followed by integration testing, which focuses on interfaces between PACS components and external systems like radiology information systems (RIS) or hospital information systems (HIS), verifying seamless data exchange via standards such as DICOM and HL7. System testing then evaluates end-to-end workflows, simulating complete imaging processes from acquisition to retrieval and display to confirm overall system coherence. Finally, user acceptance testing (UAT) engages clinical staff, including radiologists, to assess usability and diagnostic efficacy in real-world scenarios, ensuring the system aligns with operational needs. Key tests during acceptance include assessments of image fidelity to prevent loss or degradation during transfer and storage, where metrics such as resolution, contrast, and grayscale accuracy are measured against baseline DICOM datasets to maintain diagnostic quality. Performance under load is evaluated through benchmark scenarios, such as handling high volumes of concurrent image queries or retrievals, to ensure response times remain within acceptable thresholds for clinical efficiency. Failover simulations test system redundancy, including automatic switching to backup servers or databases, to validate recovery from hardware or network failures without interrupting access to critical patient images. Tools for these evaluations prominently feature DICOM conformance testing using open-source frameworks like the DICOM Validation Toolkit (DVTk), which emulates PACS behaviors such as storage and query/retrieve functions to diagnose communication issues and ensure standards compliance. Interoperability is further validated at events like IHE Connectathons, where PACS vendors test peer-to-peer integrations in supervised environments to confirm adherence to IHE profiles for cross-system data sharing. The historical Therac-25 incidents, involving software bugs in a radiation therapy system that led to patient overdoses due to inadequate verification, underscore the perils of insufficient testing in medical devices, highlighting the need for comprehensive software checks in PACS to avoid similar safety lapses. Documentation is a critical output, comprising detailed test plans outlining objectives, methodologies, and pass/fail criteria, alongside comprehensive results reports that log deficiencies, resolutions, and performance metrics. These records, often structured as Contract Data Requirements Lists (CDRLs) in large deployments, support regulatory submissions by demonstrating compliance with standards like those from the FDA or Joint Commission, facilitating approval for clinical deployment.

Regulatory Requirements

In the United States, Picture Archiving and Communication Systems (PACS) are classified by the Food and Drug Administration (FDA) as Class II medical devices, requiring premarket notification through the 510(k) clearance process to demonstrate substantial equivalence to a legally marketed predicate device.^[87] This classification stems from the moderate risk associated with PACS functions, such as image storage, processing, and display, which support radiological diagnostics without directly altering patient physiology.^[88] In 2021, the FDA updated the regulatory nomenclature from PACS to Medical Image Management and Processing Systems (MIMPS) to better encompass evolving software capabilities while maintaining the Class II status.^[89] Under the Health Insurance Portability and Accountability Act (HIPAA) Security Rule, PACS implementations must incorporate safeguards for electronic protected health information (ePHI), including encryption for data at rest and in transit to prevent unauthorized access or interception.^[90] Audit controls are also mandatory, requiring systems to record and examine user activity, such as access attempts and modifications to imaging data, with logs retained for at least six years to facilitate breach investigations and compliance audits.^[91] Internationally, the European Union's Medical Device Regulation (MDR) 2017/745 categorizes PACS software as a medical device under Rule 11 of Annex VIII, typically Class IIa or IIb depending on its diagnostic support role, necessitating conformity assessment by a notified body for CE marking.^[92] The General Data Protection Regulation (GDPR) complements MDR by imposing strict data protection obligations on PACS handling personal health data, including pseudonymization, data minimization, and explicit consent mechanisms to safeguard patient privacy in medical imaging workflows.^[93] For cybersecurity, frameworks like the National Institute of Standards and Technology (NIST) Cybersecurity Framework are recommended for healthcare, with NIST Special Publication 1800-24 providing tailored guidance for PACS to mitigate risks such as unauthorized access and data exfiltration.^[7] Key regulatory concerns for PACS include ensuring data integrity through tamper-proofing measures, such as digital signatures and blockchain-like hashing to detect alterations in archived images, aligning with both HIPAA and MDR requirements for non-repudiation.^[83] Accessibility standards under Section 508 of the Rehabilitation Act apply to federally funded healthcare software, mandating that PACS interfaces support assistive technologies like screen readers for users with disabilities, ensuring equitable access to diagnostic tools.^[94] For AI-integrated PACS, the FDA's post-2020 AI/ML Software as a Medical Device (SaMD) framework requires a Predetermined Change Control Plan to manage iterative model updates, focusing on transparency in algorithms that process or analyze imaging data.^[95] As of 2025, enhanced cybersecurity mandates have emerged in response to ransomware incidents targeting healthcare, including a proposed HIPAA Security Rule amendment to strengthen ePHI protections through mandatory multi-factor authentication and risk assessments for imaging systems.^[96] The bipartisan Healthcare Cybersecurity Act of 2025 further promotes real-time threat intelligence sharing between the Cybersecurity and Infrastructure Security Agency (CISA) and the Department of Health and Human Services (HHS) to bolster PACS resilience against evolving threats.^[97] Global harmonization efforts, led by the International Medical Device Regulators Forum (IMDRF), aim to align quality management systems—such as the FDA's impending Quality Management System Regulation (QMSR) effective February 2026 with ISO 13485—to streamline PACS approvals across jurisdictions while maintaining rigorous safety standards.^[98]

Historical Development

Origins and Early Adoption

The origins of the Picture Archiving and Communication System (PACS) trace back to early efforts in digital medical imaging in the 1970s. One of the first prototypes was developed in 1972 by Dr. Richard J. Steckel at the University of California, Los Angeles (UCLA), utilizing a high-resolution closed-circuit television system to transmit and view digitized X-ray images from film originals, enabling remote consultation without physical film transport.^[99]^[100] This system represented an initial step toward digital storage and display, though it was limited to basic transmission and did not encompass full archiving or network communication. The term "PACS" was coined in 1981 by cardiovascular radiologist Dr. André J. Duerinckx during discussions leading to the first international conference on the topic organized by the Society of Photo-Optical Instrumentation Engineers (SPIE) in Newport Beach, California.^[101] The principles of PACS were formally discussed at this 1981 SPIE conference, where 83 papers outlined concepts for filmless radiology, including digital capture, storage, and distribution of images.^[102] Early international efforts also emerged around this time, such as prototypes developed in Europe by institutions like the Technical University of Berlin. The first large-scale PACS installation occurred in 1982 at the University of Kansas Medical Center, led by researchers including Samuel J. Dwyer III and Archie W. Templeton, marking a shift from isolated prototypes to integrated systems handling computed tomography (CT) and other modalities.^[99]^[103] Early adoption in the 1980s was hindered by significant challenges, including exorbitant hardware costs—often exceeding millions of dollars for initial setups—insufficient network bandwidth for transmitting large image files, and the logistical difficulties of transitioning from traditional film-based workflows to digital formats.^[104]^[102] These issues limited PACS to pilot projects, such as the U.S. Army's PACS II initiative in Kansas City starting in 1983, which tested mini-PACS for military hospitals, and implementations at Georgetown University Hospital (1985) and Duke University Medical Center (1986).^[102]^[105] A pivotal milestone came in 1985 with the release of the first ACR-NEMA standard (version 1.0) by the American College of Radiology (ACR) and the National Electrical Manufacturers Association (NEMA), which defined basic protocols for image exchange and laid the groundwork for the DICOM standard, addressing interoperability gaps in these early systems.^[106]^[102] By the late 1980s, additional pilots at institutions like UCLA and the University of Pennsylvania demonstrated feasibility, though widespread adoption remained constrained until the 1990s.

Modern Evolution

During the 2000s, Picture Archiving and Communication Systems (PACS) experienced widespread adoption, fueled by commercial offerings from imaging modality and film vendors that extended beyond radiology departments to enterprise-wide implementations.^[1] This period marked a shift toward filmless hospitals, where cheaper powerful personal computers, gigabit networking, and DICOM-compliant displays eliminated the need for physical film printing, making studies available across entire healthcare facilities.^[1] Web-based thin-client architectures emerged, supporting query-on-demand access without local caching, which improved efficiency and reduced infrastructure costs.^[1] Concurrently, integration with Radiology Information Systems (RIS) via Health Level 7 (HL7) standards and DICOM brokers automated patient demographic entry, prefetched relevant prior images, and incorporated context-sensitive speech recognition for report generation by the mid-2000s, significantly streamlining radiology workflows.^[1] In the 2010s, PACS evolved with the rise of cloud migration, enabling scalable, cost-effective storage and deployment models that supported teleradiology and remote diagnostics, with the U.S. medical imaging cloud market valued at $56.5 million in 2010 and projected to expand rapidly thereafter.^[107] The emergence of Vendor Neutral Archives (VNAs) decoupled archival storage from proprietary PACS platforms, allowing multi-vendor interoperability and easier data migration, addressing limitations in traditional systems.^[108] Mobile access advanced through web-based zero-footprint viewers and dedicated applications, permitting radiologists and clinicians to review images on smartphones and tablets for on-the-go consultations.^[109] In the United States, the Health Information Technology for Economic and Clinical Health (HITECH) Act of 2009 provided billions in incentives for adopting certified electronic health record systems, which encompassed imaging technologies like PACS and accelerated transitions to digital, integrated environments.^[110] The 2020s have seen PACS incorporate artificial intelligence for enhanced image processing and analytics, alongside a telemedicine surge driven by the COVID-19 pandemic that relied on PACS for secure remote image distribution and virtual collaborations. Fast Healthcare Interoperability Resources (FHIR) standards have gained traction for seamless data exchange between PACS and broader electronic health records, promoting unified patient care. The global PACS and RIS market, valued at approximately $6.58 billion in 2024, is projected to grow at a compound annual growth rate (CAGR) of 7.2% through 2034, reflecting sustained demand for advanced imaging solutions.^[111]

References

[1]
Picture archiving and communication systems: past, present ... - NIH
Picture archiving and communication systems (PACS) that digitally acquire, archive, transmit, and display medical images ultimately enabled the transition
[2]
Securing Picture Archiving and Communication System - NCCoE
The overall Picture Archiving and Communication System (PACS) ecosystem consists of diverse technologies that include medical imaging devices, patient registry ...
[3]
Thirty Years of the DICOM Standard - PMC - NIH
Oct 6, 2023 · First developed for radiology and then cardiology departments, the DICOM standard has evolved over the years to support various other branches ...
[4]
What is PACS in Healthcare? - The HIPAA Journal
Aug 2, 2024 · A PACS in healthcare is a Picture Archiving and Communications System – a digital system used to store, retrieve, and transmit medical images.
[5]
Evaluation of Picture Archiving and Communication System (PACS)
One possible reason for the faster processes with PACS is that radiologists do not have to wait for the film to be printed to view images or write reports. They ...
[6]
Components and implementation of a picture archiving and ...
Dec 24, 2018 · PACS consists of four major components: image acquisition devices (imaging modalities), communication networks, PACS archive and server, and ...Missing: core | Show results with:core
[7]
[PDF] Securing Picture Archiving and Communication System (PACS)
PACS allows for the acceptance, transfer, display, storage, and digital processing of medical images. PACS centralizes functions surrounding medical imaging ...
[8]
A high speed integrated computer network for picture archiving and ...
A 200-Mbs fiber optic computer network was designed based on the presented PACS network requirements and the data traffic. The characteristics, protocols ...Missing: bandwidth | Show results with:bandwidth
[9]
Monitor displays in radiology: Part 2 - PMC - NIH
With ongoing refinements in technology, high-resolution monitors with resolutions as high as 9 MP and higher have started becoming available. In CRT monitors ...
[10]
[PDF] Key Elements of a PACS - AAPM
Many sole source PACS have a proprietary database server which provides a distributed database for each workstation and the archive(s). • The advantage of this ...
[11]
Towards a Theory of PACS Deployment - PubMed Central - NIH
After nearly 30 years of picture archiving and communication system (PACS) technology development and evolution, PACS has become an integrated component of ...
[12]
PACS System Key Components - Radsource
Dec 10, 2024 · By replacing film-based processes and conventional systems, PACS facilitates faster retrieval of medical images and ensures a more seamless ...
[13]
Medical Imaging: Modalities & Types of Equipment
Jul 5, 2023 · These various imaging modalities include X-rays, computed tomography (CT) scans, magnetic resonance imaging (MRI), ultrasound, and nuclear medicine, among ...Radiology & The Uses Of... · Common Imaging Modalities · Magnetic Resonance Imaging...Missing: PACS | Show results with:PACS
[14]
Medical Image File Formats - PMC - NIH
Dec 13, 2013 · A nuclear medicine image like a PET image will have information about the radiopharmaceutical injected and the weight of the patient. These data ...
[15]
Multispecialty Enterprise Imaging Workgroup Consensus on ...
Diagnostic and evidential static image, video clip, and sound multimedia are captured during routine clinical care in cardiology, dermatology, ophthalmology ...
[16]
Enhancing Cardiac Imaging: The Role of PACS in Echocardiography
Integrating this vital imaging technique with Picture Archiving and Communication Systems (PACS) is revolutionizing how cardiologists view, analyze, and store ...<|separator|>
[17]
Image annotation and curation in radiology: an overview for ... - NIH
Feb 6, 2024 · This review provides an overview of the methods and tools that can be used to ensure high-quality data for machine learning and artificial intelligence ...Missing: emerging | Show results with:emerging
[18]
Ultra-high resolution, multi-scale, context-aware approach for ...
Jul 8, 2022 · Digital Mammograms have a pixel size of around 50–100 microns. DMs tend to be very large images, ranging from 2300 × 1800 pixels (of dimension ...
[19]
Twenty Years of Digital Pathology: An Overview of the Road ...
Nov 21, 2018 · Today, whole-slide scanners are capable of automatically producing very high-resolution images that replicate glass slides (so-called virtual ...
[20]
Digital Pathology: Data-Intensive Frontier in Medical Imaging - PMC
As devices that generate whole slide images become more practical and affordable, practices will increasingly adopt this technology and eventually produce an ...
[21]
About DICOM: Overview
Digital Imaging and Communications in Medicine — is the international standard for medical images and related information.Related Standards and SDOs · Translation Policy · Governance
[22]
Key Concepts - DICOM
This is a historical requirement to maintain compatibility with older existing systems. It also mandates the presence of a media directory, the DICOMDIR file, ...
[23]
5 Data Structures and Encoding - DICOM Standard
A Data Set is that portion of a DICOM Message that conveys information about real world objects being managed over the network.<|control11|><|separator|>
[24]
DICOMweb™
DICOMweb is the DICOM Standard for web-based medical imaging. It is a set of RESTful services, enabling web developers to unlock the power of healthcare images.DICOMweb Cheatsheet · DICOMweb Resources · Search (QIDO-RS) · CapabilitiesMissing: 2024 2025<|control11|><|separator|>
[25]
DICOM News
This supplement to the DICOM Standard introduces new SR template content to address fetal anatomy survey assessments in ultrasound reports.Dicomweb Modality Procedure... · Ultrasound Fetal Anatomy... · Rdsr Informative Annex
[26]
Current Edition - DICOM
The DICOM Standard is managed by the Medical Imaging & Technology Alliance - a division of the National Electrical Manufacturers Association. DICOM® ...
[27]
PACS Fundamentals | Radiology Key
Feb 27, 2016 · In a PACS, the system architecture normally consists of acquisition devices, storage, display workstations, and an image management system.
[28]
None
### Summary of PACS Network Topology, Star or Mesh, Bandwidth
[29]
Top Ten Recommendations for Implementing PACS Security
Mar 1, 2005 · 1. Deploy external & internal firewalls · 2. Implement VLANS to limit access · 3. Make sure your virus scanner is installed and up to date · 4.
[30]
Performance Enhancement of a Web-Based Picture Archiving and ...
Using the proposed COTS server cluster as a Web-based PACS enhances the image download and upload efficiency and guarantees the continuous availability.Missing: cloud | Show results with:cloud
[31]
Fault-tolerant PACS server design | Request PDF - ResearchGate
Aug 9, 2025 · This paper describes a novel, portable, and scalable fault-tolerant PACS controller design that is affordable for most PACS implementations.
[32]
How load balancers optimize PACS performance in radiology
Jul 31, 2020 · Load balancing PACS servers ensure high availability and scalability ... Server failover improves fault-tolerance for mission-critical PACS ...Missing: modular | Show results with:modular
[33]
Design and Implementation of a Cloud PACS Architecture - MDPI
Nov 7, 2022 · The paper introduces a vendor-neutral cloud PACS architecture. It is divided into two main components: a cloud platform and an access device.
[34]
Investigation of misfiled cases in the PACS environment and a ...
Aug 5, 2025 · The aim of the study was to survey misfiled cases in a picture archiving and communication system environment at two hospitals and to ...
[35]
Predicting PACS loading and performance metrics using Monte ...
Aug 9, 2025 · This simulation provides estimates on what a radiological department can expect from a PACS in terms of throughput, utilization, and delay.
[36]
Storage media for computers in radiology - PMC - NIH
Online storage refers to data storage on magnetic discs and redundant array of inexpensive discs (RAID) systems. It provides access to the data in a few ...
[37]
Picture archiving and communication system | Radiology Reference ...
Jun 9, 2023 · Storage. Storage media for PACS can be divided into online, nearline, and offline storage. Online storage allows immediate access to data. It ...Missing: hierarchy libraries
[38]
Choose image archiving solutions before data volume grows too ...
... offline levels of file storage hierarchy are supported: Online with one copy on RAID and at least one copy on tape; Near-line with at least one copy on tape ...
[39]
Demystifying data storage: Archiving options for PACS
May 6, 2004 · Generally, a nearline system can access data within 60 seconds and is able to transfer data at a few MB/sec. Offline storage is removable tape ...Missing: libraries | Show results with:libraries
[40]
A Comprehensive Look at Data Archive Strategies - PACS Boot Camp
May 13, 2022 · Nearline storage is the storage outside the computer (mostly removable media) but provides quick access to the stored data when needed. Nearline ...Missing: libraries | Show results with:libraries
[41]
PACS System Radiology: Workflow, Benefits, and Challenges
Oct 12, 2025 · PACS has transformed radiology from film-heavy, time-consuming workflows into a fast, digital, and collaborative process. By centralizing image ...
[42]
How to Easily Backup PACS Images and Servers?
Aug 5, 2024 · 1. Proper Backup Frequency: · 2. Use Incremental Backup: · 3. Data Deduplication and Compression: · 4. Automate Backup: · 5. Review the backup ...
[43]
Secure Healthcare Imaging: Robust Backup & Disaster Recovery
Rating 5.0 (41) · Free · HealthIncremental backups capture only changes made since the last backup, conserving storage space and reducing backup time. Differential backups, on the other hand, ...
[44]
How to Implement PACS Disaster Recovery in Hospital?
Nov 13, 2024 · PACS disaster recovery mainly includes data backup PACS images and servers and the restore methods to reduce RTO.
[45]
Configuring Offsite Disaster Recovery: Benefits & Why It Matters
Jan 19, 2024 · Offsite backups can be configured in one of three ways: full backups, incremental backups, or differential backups. Full backups capture what ...Missing: PACS | Show results with:PACS
[46]
HIPAA Retention Requirements - 2025 Update
Apr 16, 2025 · The HIPAA retention requirements are that certain types of documents must be maintained for six years from the date of their creation or from the date on which ...Missing: PACS lifecycle compression JPEG 2000
[47]
Medical Records Retention Guide (Updated for 2025) - SecureScan
Apr 25, 2023 · In this guide, we'll break down medical records retention requirements, explain HIPAA's role in the process, and share a few tips that can help you manage ...
[48]
Optimizing Healthcare Systems Through Effective Data Purging
Data purging is necessary to eliminate data that surpasses the retention period defined in the persistence settings. This process is managed through a database ...Missing: 7-10 JPEG 2000
[49]
PAC Storage | PAC Storage | High-Performance Enterprise Data ...
Discover the power behind the PAC Storage PS 5000 Hybrid Storage Solution—engineered for organizations demanding high performance, scalability, and efficiency.
[50]
PAC Storage Showcases Ultra-High-Performance 5000 Series ...
Oct 14, 2025 · The PAC Storage 5000 All Flash NVMe system delivers extreme performance with throughput up to 50 GB/s read and 25 GB/s write, and up to 1.3 ...
[51]
NAB Show 2025: PAC Storage Unveils 5000 Series Data Storage ...
Mar 26, 2025 · NAB Show 2025: PAC Storage Unveils 5000 Series Data Storage Solutions. Includes Hybrid 90 HDD+ 4 NVMe (RW cache) system and ultra-fast All-Flash ...
[52]
Quantitative Evaluation of PACS Query/Retrieve Capabilities - PMC
We have developed an application to formally evaluate the query/retrieve capabilities of a PACS, in order to improve the interoperability of algorithms.
[53]
PS3.18 - DICOM - NEMA
PS3.18 specifies web services (using the HTTP family of protocols) for managing and distributing DICOM (Digital Imaging and Communications in Medicine) ...
[54]
https://dicom.nema.org/medical/dicom/current/output/html/part18.html#sect_10
[55]
https://pmc.ncbi.nlm.nih.gov/articles/PMC9864478/
[56]
A Review of Core Concepts of Imaging Informatics - PMC
Dec 22, 2022 · PACS is able to communicate with imaging modalities with DICOM and/or EMR with HL7 transactions [1]. From about 2001 to 2006, most healthcare ...
[57]
Creating a Medical Imaging Workflow Based on FHIR, DICOMweb ...
Feb 2, 2023 · As shown in Fig. 1, standardized data is created in the HIS, RIS (Radiological Information System), and PACS, and then shared across systems ...
[58]
ImagingStudy - FHIR v5.0.0
### Summary of FHIR ImagingStudy Resource for Integration
[59]
Large-Scale Integration of DICOM Metadata into HL7-FHIR for ... - NIH
Apr 15, 2025 · Large-Scale Integration of DICOM Metadata into HL7-FHIR for Medical Research ... PACS of the UHE into HL7-FHIR “ImagingStudy” resources.
[60]
Functional Requirements for Medical Data Integration into ... - NIH
The system must process data by mapping it to multiple terminology standards. Possible terminology standards are SNOMED-CTa, LOINCb, ICDc, ATCd, IDC-Oe, CPT ...
[61]
Interoperability of heterogeneous health information systems - NIH
Jan 24, 2023 · The lack of interoperability between health information systems reduces the quality of care provided to patients and wastes resources.
[62]
What is Vendor Neutral Archive (VNA) - Intelerad Medical Systems
Apr 20, 2023 · A Vendor Neutral Archive (VNA) is a medical imaging technology that provides a centralized storage solution for medical images and associated data.Missing: IHE XDS/ XCA
[63]
None
### Summary of Key Points on VNA
[64]
Vendor Neutral Archive: From Silos to Unified Data - Cloudian
A Vendor Neutral Archive (VNA) stores images generated by medical scanners and devices using a standard format.Missing: Amazon normalization lifecycle<|separator|>
[65]
XDS Main Page - IHE Wiki
Mar 18, 2019 · This site helps with the testing of XDS.a, XDS.b, XCA, and XDR profiles as well as ATNA as it supports these profiles.
[66]
Vendor Neutral Archive Market Size | Industry Report, 2033
VNAs were initially adopted to manage and unify radiology images from different PACS vendors, enabling interoperability, long-term storage, and streamlined ...Missing: XCA | Show results with:XCA
[67]
Vendor Neutral Archive Market | Global Market Analysis Report - 2035
Sep 22, 2025 · Hospitals are estimated to hold 61% of the market share in 2025. This dominance reflects the large-scale imaging data management requirements of ...
[68]
The utilization of artificial intelligence applications to improve breast ...
Computer-aided detection (CAD) has been designed and used in breast imaging to aid radiologists and automate the early discovery and diagnosis of breast lesions ...
[69]
Artificial intelligence, machine learning, computer-aided diagnosis ...
With the advent of artificial intelligence and “big data”, we are moving toward reducing those limitations, homogenizing and expanding the use of CAD tools in ...
[70]
Revolutionizing Radiology With Artificial Intelligence - PMC - NIH
Oct 29, 2024 · ... (PACS). By flagging critical or suspicious findings, AI can help radiologists prioritize urgent cases, enabling more timely diagnoses and ...
[71]
https://pmc.ncbi.nlm.nih.gov/articles/PMC11554795/
[72]
Clinical impact of AI in radiology department management - NIH
Sep 7, 2024 · [9, 13] This type of analysis allows for better allocation and use of resources, patient management, and operations especially in urgent care.
[73]
Integrating AI into radiology workflow: levels of research, production ...
We present a roadmap for integrating artificial intelligence (AI)-based image analysis algorithms into existing radiology workflows.
[74]
A Responsible Framework for Applying Artificial Intelligence on ...
We propose the PACS-AI platform as a tool for the responsible deployment of AI models in the hospital setting for clinical and research purposes. The PACS-AI ...
[75]
Federated Learning in Medical Imaging: Part I: Toward Multicentral ...
Federated learning (FL) is a version of distributed learning tailored for tasks in which data privacy is essential so that researchers can preserve privacy ...
[76]
AI-based analysis of CT images for rapid triage of COVID-19 patients
Apr 22, 2021 · In this study, we provided risk stratification based on CT-based radiomics features and clinical data for COVID-19 patients in terms of stable or severe ...Missing: post- | Show results with:post-
[77]
Deep Learning-Based Natural Language Processing in Radiology
Sep 4, 2021 · In radiology, natural language processing (NLP) allows the extraction of valuable information from radiology reports.
[78]
AI Integration in Radiology PACS: Smart Imaging
Jun 29, 2025 · The AI generates results in standard formats like: DICOM SEG (segmentation masks); DICOM SR (structured reports with measurements); GSPS ( ...
[79]
Artificial Intelligence and Machine Learning (AI/ML)-Enabled ... - FDA
The AI/ML-Enabled Medical Device List is a resource intended to identify AI/ML-enabled medical devices that are authorized for marketing in the United States.Artificial Intelligence · 510(k) Premarket Notification · Software as a Medical Device
[80]
[PDF] May 30, 2025 Aidoc Medical, Ltd. John Smith Partner Hogan Lovells ...
May 30, 2025 · BriefCase-Triage uses an artificial intelligence algorithm to analyze images and highlight cases with detected findings on a standalone desktop ...
[81]
[PDF] February 27, 2025 Gleamer SAS Antoine Tournier Chief ...
Feb 27, 2025 · Aorta-CAD has the following FDA-cleared. Indications for Use: Aorta-CAD is a computer-assisted detection (CADe) software device that analyzes ...
[82]
Unraveling the role of cloud computing in health care system and ...
This review explores the integration of cloud computing within these fields, highlighting its pivotal role in enhancing data management, security, and ...Missing: AWS | Show results with:AWS
[83]
https://pmc.ncbi.nlm.nih.gov/articles/PMC7728878/
[84]
[PDF] Securing Picture Archiving and Communication System (PACS)
This practice guide builds upon the network zoning concept described in NIST SP 1800-8, Securing Wireless Infusion Pumps in Healthcare Delivery Organizations.
[85]
Cybersecurity in PACS and Medical Imaging: an Overview - PMC
This article provides an overview on the literature published on the topic of cybersecurity for PACS (Picture Archiving and Communications Systems) and medical ...
[86]
https://dcmsys.com/project/teleradiology-and-telehealth-in-2025/
[87]
[PDF] Department of Veterans Affairs VA Directive 6008 Washington, DC ...
Jan 6, 2023 · (c) Rapid Elasticity: Computing capabilities are automatically provisioned and released in a manner that scales with customer demand. In ...
[88]
Teleradiology and Telehealth in 2025 - Dicom Systems
Integration with telemedicine platforms enables real-time consultations, facilitating multidisciplinary discussions and enhancing the quality of patient care.Evolution Of Teleradiology · Teleradiology Workflows · How Are Healthcare...
[89]
510(k) Clearances - FDA
May 29, 2024 · This allows FDA to determine whether the device is equivalent to a device already placed into one of the three classification categories. Thus, ...
[90]
Medical Device Classification Regulations To Conform to Medical ...
Apr 19, 2021 · The Picture Archiving and Communications Systems (PACS) device includes both software and hardware image storage and display functions and ...
[91]
510(k) Premarket Notification - FDA
Sep 10, 2021 · 510(k) Premarket Notification ; System, Image Processing, Radiological · K211257 · EFAI PACS Picture Archiving and Communication System · Ever ...
[92]
Summary of the HIPAA Security Rule | HHS.gov
Dec 30, 2024 · The Security Rule establishes a national set of security standards to protect certain health information that is maintained or transmitted in electronic form.
[93]
HIPAA Encryption Requirements - 2025 Update
Apr 9, 2025 · The HIPAA encryption requirements are included in the HIPAA Security Rule standards relating to access controls and transmission security.
[94]
[PDF] MDR and Regulation (EU) 2017/746 – IV
Medical Devices addresses the qualification of PACS.33 The transposition of this Directive. Guidance to the Regulations is currently underway and will be ...
[95]
The new EU General Data Protection Regulation - NIH
Apr 24, 2017 · The regulation aims at protecting the confidentiality of personal health data whilst preserving the benefits of digital image processing for ...
[96]
IT Accessibility Laws and Policies - Section508.gov
Under Section 508, agencies must give disabled employees and members of the public access to information comparable to the access available to others. The U.S. ...Section 508 requirements · Website Accessibility StatementMissing: PACS medical
[97]
[PDF] Artificial Intelligence/Machine Learning (AI/ML)-Based.:Jf/<X ... - FDA
The discussion paper proposed a framework for modifications to AI/ML-based SaMD that relies on the principle of a “Predetermined Change Control Plan.” As ...Missing: PACS | Show results with:PACS
[98]
HIPAA Security Rule To Strengthen the Cybersecurity of Electronic ...
Jan 6, 2025 · The proposed modifications would revise existing standards to better protect the confidentiality, integrity, and availability of electronic protected health ...
[99]
Bipartisan Healthcare Cybersecurity Act Introduced in House and ...
Jun 16, 2025 · This bipartisan bill takes direct, strategic action: empowering CISA and HHS to coordinate real-time threat sharing, expanding cybersecurity ...
[100]
QMSR: What You Need to Know about Global Harmonization ... - AAMI
Oct 9, 2025 · The amended Part 820 will take effect February 3, 2026, and will be called the Quality Management System Regulation or QMSR. QMSR incorporates ...Missing: PACS | Show results with:PACS
[101]
PACS and the Road to Reconstruction | Imaging Technology News
Jun 5, 2018 · One of the first was created in 1972 by Richard J. Steckel, M.D., and the large-scale introduction occurred 10 years later at the University of ...Missing: prototype Robert
[102]
Daily X-Ray Rounds in a Large Teaching Hospital Using High ...
Daily X-Ray Rounds in a Large Teaching Hospital Using High-Resolution Closed-Circuit Television. Author: Richard J. Steckel, M.D.Authors Info & Affiliations.
[103]
Introduction to two PACS '82 Panel Discussions edited by André J ...
The term was created by Dr Duerinckx prior to this first meeting in 1982 after many discussions with Sam Dwyer and others, and after rejecting many alternate ...
[104]
SPIE Medical Imaging 50th anniversary: history of the Picture ...
An update on the ACR-NEMA “Digital Imaging and Communications in Medicine” was given and data protection and security issues of PACS were discussed. The UCLA ...Missing: coined | Show results with:coined
[105]
Standards Watch | PACS Through the Years - Radiology Business
Jan 1, 2004 · The early versions of DICOM, called ACR-NEMA, only specified a dedicated point-to-point connection, leaving it up to the manufacturer to ...
[106]
The History of PACS - Radsource
Dec 5, 2024 · The PACS concept was introduced in the late 1970s and early 1980s as a design blueprint for capturing, storing, and distributing digital imaging ...Missing: 1981-1982 | Show results with:1981-1982
[107]
[PDF] PACS: Then and Now (… and Tomorrow !)
❖ Post-ACR-NEMA PACS and Modalities. – Several systems adopted ACR-NEMA ... ❖ Term coined by Tandem for ServerNet product. ❖ Treats storage devices as ...
[108]
1.3 History - DICOM Standard - NEMA
ACR-NEMA Standards Publication No. 300-1985, published in 1985 was designated version 1.0. The Standard was followed by two revisions: No. 1, dated October ...Missing: pilot | Show results with:pilot
[109]
Roadmap to cloud-based PACS - Applied Radiology
May 30, 2012 · The cloud computing market for medical imaging in the United States (U.S.), valued at an estimated $56.5 million in 2010, is expected to grow at ...
[110]
Vendor neutral archive in PACS - PMC - NIH
The new concept of vendor neutral archive (VNA) has emerged. A VNA simply decouples the PACS and workstations at the archival layer.
[111]
Web-Based PACS Enables Image Viewing on Mobile Devices | DAIC
It allows reading physicians to access multiple disparate image repositories from a single workstation utilizing a single automated, unified worklist.
[112]
Impact of the HITECH Act on physicians' adoption of electronic ... - NIH
Jul 30, 2015 · The Health Information Technology for Economic and Clinical Health (HITECH) Act has distributed billions of dollars to physicians as incentives for adopting ...Missing: PACS cloud emergence mobile
[113]
PACS and RIS Market Size, Share, Growth | CAGR of 7.2%
Apr 5, 2025 · Global PACS and RIS Market was valued at US$ 6579.46 Million in 2024 and is expected to grow at a CAGR of 7.2% from 2024 to 2034.
[114]
Post-quantum healthcare: A roadmap for cybersecurity resilience in ...
This paper navigates the intricate landscape of post-quantum cryptographic approaches and emerging threats specific to the healthcare sector.