DICOM Structured Reporting Research Articles

A novel reporting workflow for automated integration of artificial intelligence results into structured radiology reports

ObjectivesArtificial intelligence (AI) has tremendous potential to help radiologists in daily clinical routine. However, a seamless, standardized, and time-efficient way of integrating AI into the radiology workflow is often lacking. This constrains the full potential of this technology. To address this, we developed a new reporting pipeline that enables automated pre-population of structured reports with results provided by AI tools.MethodsFindings from a commercially available AI tool for chest X-ray pathology detection were sent to an IHE-MRRT-compliant structured reporting (SR) platform as DICOM SR elements and used to automatically pre-populate a chest X-ray SR template. Pre-populated AI results could be validated, altered, or deleted by radiologists accessing the SR template. We assessed the performance of this newly developed AI to SR pipeline by comparing reporting times and subjective report quality to reports created as free-text and conventional structured reports.ResultsChest X-ray reports with the new pipeline could be created in significantly less time than free-text reports and conventional structured reports (mean reporting times: 66.8 s vs. 85.6 s and 85.8 s, respectively; both p < 0.001). Reports created with the pipeline were rated significantly higher quality on a 5-point Likert scale than free-text reports (p < 0.001).ConclusionThe AI to SR pipeline offers a standardized, time-efficient way to integrate AI-generated findings into the reporting workflow as parts of structured reports and has the potential to improve clinical AI integration and further increase synergy between AI and SR in the future.Critical relevance statementWith the AI-to-structured reporting pipeline, chest X-ray reports can be created in a standardized, time-efficient, and high-quality manner. The pipeline has the potential to improve AI integration into daily clinical routine, which may facilitate utilization of the benefits of AI to the fullest.Key points• A pipeline was developed for automated transfer of AI results into structured reports.• Pipeline chest X-ray reporting is faster than free-text or conventional structured reports.• Report quality was also rated higher for reports created with the pipeline.• The pipeline offers efficient, standardized AI integration into the clinical workflow.Graphical

DICOM re‐encoding of volumetrically annotated Lung Imaging Database Consortium (LIDC) nodules

Purpose The dataset contains annotations for lung nodules collected by the Lung Imaging Data Consortium and Image Database Resource Initiative (LIDC) stored as standard DICOM objects. The annotations accompany a collection of computed tomography (CT) scans for over 1000 subjects annotated by multiple expert readers, and correspond to “nodules ≥ 3 mm”, defined as any lesion considered to be a nodule with greatest in-plane dimension in the range 3–30 mm regardless of presumed histology. The present dataset aims to simplify reuse of the data with the readily available tools, and is targeted towards researchers interested in the analysis of lung CT images. Acquisition and validation methods Open source tools were utilized to parse the project-specific XML representation of LIDC-IDRI annotations and save the result as standard DICOM objects. Validation procedures focused on establishing compliance of the resulting objects with the standard, consistency of the data between the DICOM and project-specific representation, and evaluating interoperability with the existing tools. Data format and usage notes The dataset utilizes DICOM Segmentation objects for storing annotations of the lung nodules, and DICOM Structured Reporting objects for communicating qualitative evaluations (nine attributes) and quantitative measurements (three attributes) associated with the nodules. The total of 875 subjects contain 6859 nodule annotations. Clustering of the neighboring annotations resulted in 2651 distinct nodules. The data are available in TCIA at https://doi.org/10.7937/TCIA.2018.h7umfurq. Potential applications The standardized dataset maintains the content of the original contribution of the LIDC-IDRI consortium, and should be helpful in developing automated tools for characterization of lung lesions and image phenotyping. In addition to those properties, the representation of the present dataset makes it more FAIR (Findable, Accessible, Interoperable, Reusable) for the research community, and enables its integration with other standardized data collections.

DICOM re-encoding of volumetrically annotated Lung Imaging Database Consortium (LIDC) nodules.

PurposeThe dataset contains annotations for lung nodules collected by the Lung Imaging Data Consortium and Image Database Resource Initiative (LIDC) stored as standard DICOM objects. The annotations accompany a collection of computed tomography (CT) scans for over 1000 subjects annotated by multiple expert readers, and correspond to “nodules ≥ 3 mm”, defined as any lesion considered to be a nodule with greatest in‐plane dimension in the range 3–30 mm regardless of presumed histology. The present dataset aims to simplify reuse of the data with the readily available tools, and is targeted towards researchers interested in the analysis of lung CT images.Acquisition and validation methodsOpen source tools were utilized to parse the project‐specific XML representation of LIDC‐IDRI annotations and save the result as standard DICOM objects. Validation procedures focused on establishing compliance of the resulting objects with the standard, consistency of the data between the DICOM and project‐specific representation, and evaluating interoperability with the existing tools.Data format and usage notesThe dataset utilizes DICOM Segmentation objects for storing annotations of the lung nodules, and DICOM Structured Reporting objects for communicating qualitative evaluations (nine attributes) and quantitative measurements (three attributes) associated with the nodules. The total of 875 subjects contain 6859 nodule annotations. Clustering of the neighboring annotations resulted in 2651 distinct nodules. The data are available in TCIA at https://doi.org/10.7937/TCIA.2018.h7umfurq.Potential applicationsThe standardized dataset maintains the content of the original contribution of the LIDC‐IDRI consortium, and should be helpful in developing automated tools for characterization of lung lesions and image phenotyping. In addition to those properties, the representation of the present dataset makes it more FAIR (Findable, Accessible, Interoperable, Reusable) for the research community, and enables its integration with other standardized data collections.

Relevance of eHealth standards for big data interoperability in radiology and beyond.

The aim of this paper is to report on the implementation of radiology and related information technology standards to feed big data repositories and so to be able to create a solid substrate on which to operate with analysis software. Digital Imaging and Communications in Medicine (DICOM) and Health Level 7 (HL7) are the major standards for radiology and medical information technology. They define formats and protocols to transmit medical images, signals, and patient data inside and outside hospital facilities. These standards can be implemented but big data expectations are stimulating a new approach, simplifying data collection and interoperability, seeking reduction of time to full implementation inside health organizations. Virtual Medical Record, DICOM Structured Reporting and HL7 Fast Healthcare Interoperability Resources (FHIR) are changing the way medical data are shared among organization and they will be the keys to big data interoperability. Until we do not find simple and comprehensive methods to store and disseminate detailed information on the patient's health we will not be able to get optimum results from the analysis of those data.

Cloud-Based CT Dose Monitoring using the DICOM-Structured Report: Fully Automated Analysis in Regard to National Diagnostic Reference Levels

To implement automated CT dose data monitoring using the DICOM-Structured Report (DICOM-SR) in order to monitor dose-related CT data in regard to national diagnostic reference levels (DRLs). We used a novel in-house co-developed software tool based on the DICOM-SR to automatically monitor dose-related data from CT examinations. The DICOM-SR for each CT examination performed between 09/2011 and 03/2015 was automatically anonymized and sent from the CT scanners to a cloud server. Data was automatically analyzed in accordance with body region, patient age and corresponding DRL for volumetric computed tomography dose index (CTDIvol) and dose length product (DLP). Data of 36,523 examinations (131,527 scan series) performed on three different CT scanners and one PET/CT were analyzed. The overall mean CTDIvol and DLP were 51.3% and 52.8% of the national DRLs, respectively. CTDIvol and DLP reached 43.8% and 43.1% for abdominal CT (n=10,590), 66.6% and 69.6% for cranial CT (n=16,098) and 37.8% and 44.0% for chest CT (n=10,387) of the compared national DRLs, respectively. Overall, the CTDIvol exceeded national DRLs in 1.9% of the examinations, while the DLP exceeded national DRLs in 2.9% of the examinations. Between different CT protocols of the same body region, radiation exposure varied up to 50% of the DRLs. The implemented cloud-based CT dose monitoring based on the DICOM-SR enables automated benchmarking in regard to national DRLs. Overall the local dose exposure from CT reached approximately 50% of these DRLs indicating that DRL actualization as well as protocol-specific DRLs are desirable. The cloud-based approach enables multi-center dose monitoring and offers great potential to further optimize radiation exposure in radiological departments. • The newly developed software based on the DICOM-Structured Report enables large-scale cloud-based CT dose monitoring • The implemented software solution enables automated benchmarking in regard to national DRLs • The local radiation exposure from CT reached approximately 50 % of the national DRLs • The cloud-based approach offers great potential for multi-center dose analysis.

Optimizing Radiation Use During Fluoroscopic Procedures: A Quality and Safety Improvement Project

The ionizing radiation used during fluoroscopically guided medical interventions carries risk. The teams performing these procedures seek to minimize those risks while preserving each procedure's benefits. This report describes a data-driven optimization strategy. Manual and automated data capture systems were used to collect a series of different metrics, including fluoroscopy time, kerma area product, and reference point air kerma, from both adult and pediatric interventional radiologic procedures. Tools from statistical process control were used to identify opportunities for improvement and assess which changes led to improvement. Initial efforts focused on creating a system capable of reliably capturing fluoroscopy time from all interventional radiologic procedures. Ongoing data analysis and feedback to frontline teams led to the development of a manual workflow that reliably captured fluoroscopy time. Data capture was later supplemented by automatic capture of electronic records. This process exploited the standardized format (DICOM Structured Reporting) that newer fluoroscopy units use to record the radiation metrics. Data analysis found marked differences between the imaging protocols used for adults and children. Revision of the adult protocols led to a stable twofold reduction in average exposure per adult procedure. Analysis of balancing measures found no impact on workflow. A systematic approach to improving radiation use during procedures led to a substantial and sustained reduction in risk with no reduction in benefits. Data were readily captured by both manual and automated processes. Concepts from cognitive psychology and information theory provided a theoretical basis for both data analysis and improvement opportunities.

Implementing DICOM Structured Reporting in a Large-Scale Telemedicine Network

Large-scale asynchronous telemedicine networks can offer a unique opportunity for the acquisition of detailed epidemiological information if the data are acquired and handled in an appropriate way. In this work, an approach is presented for the integration of medical reports in the Digital Imaging and Communications in Medicine (DICOM) Structured Reporting standard in telemedicine networks using structured vocabularies. The use of these structured vocabularies is extended beyond radiology, and a case study in telecardiology is presented. The approach was applied in the context of a real-world statewide public telemedicine network; nowadays on average 470 written electrocardiographic structured reports daily are being performed. Cardiologists provided more than 220,000 written structured reports, and these reports are stored into a central database. This study was performed during a 12-month period, and it was possible to examine possible associations between a list of co-morbidities and cardiac risk factors with a diagnosis that indicates the presence of cardiac ischemia, cardiac injury, or possible necrosis by using DICOM Structured Reporting. Our application is responsible for coordinating the process of issuance of reports through various technologies and devices. The system works as a library in an HTTP server, which accesses information from studies in DICOM format from the database and from structured vocabularies. Results indicate that traceability of morbidity, diagnoses, and patient clinical information can be achieved, resulting in an efficient data mining-friendly framework. A multidevice application for Web-based and smartphone-based platforms showed that it is a viable solution for applying the DICOM Structured Reporting standard in telemedicine networks.

TU-B-110-02: ACR Dose Index Registry for Comparing CT Dose Indices

Exposure to ionizing radiation due to the growing use of imaging procedures in the United States has been a recent concern of radiologists,medical physicists, other healthcare providers, and the public in general. Despite significant improvements in CT acquisition and dose reduction technologies, the ability to compare and monitor doses delivered from CT scans across facilities remains problematic. The dose index registry pilot project collected and compared dose indices across ten facilities nationwide from three different CTscanner manufacturers. Each of the facilities in the pilot had at least one scanner with the ability to put CTDose information into a DICOM SR (Structured Report) format. Custom software was used to anonymize the DICOM SR file and transmit the dose information to the American College of Radiology (ACR) Dose Index Registry (DIR). Over a period one and a half months, 6979 exams were collected. Study descriptions of exam type varied both within and across the 10 facilities; therefore, a mapping was made to a standard Radlex Playbook term. Five exam types were mapped: CT Head With IV Contrast; CT Head Without IV Contrast; CT Chest With IV Contrast; CT Chest Without IV Contrast; and CT Head Perfusion. A total of 1944 exams were mapped to one of these five categories. Significant differences (p<.05) in CTDIvol by facility were noted for all exam types except CT Head Perfusion for which data for only 20 exams from 2 sites was contributed. This DIR pilot project demonstrated that a fully automated process of collecting, transmitting, storing and reporting dose information is possible, in spite of challenges related to scanner configuration, software installation, and study description standardization. Once this model is employed on a national level, it will provide unmatched data regarding radiation dose indices that will allow facilities to compare their results to national benchmarks and reference levels. A national Dose Index Registry using standard methods of data collection and transmission has been successfully piloted and is now available. The registry has the ability to monitor changes in dose indices due to technological advances and practice modifications and to establish benchmarks and national practice patterns.

Applicability of DICOM structured reporting for the standardized exchange of implantation plans

Today's operating room is equipped with different devices supporting the surgeon. Due to the lack of common interfaces between devices, an integrated support of the surgical workflow is missing. In the field of implantation, a smooth exchange of preoperatively planned data between devices is of great interest. Additionally, the availability of standardized preoperative data would facilitate the documentation, especially with regard to Electronic Health Records. To analyze whether DICOM Structured Reporting can be the basis for a standardized digital human- and machine-readable implantation plan, we derived all requirements for such a document. Therefore, we examined the conventional implantation plan and future applications of the digital plan. In this paper, we propose to use the mechanisms introduced by DICOM Structured Reporting as storage and communication infrastructure for implantation plans in the surgical domain. DICOM Structured Reporting complies with all requirements of our analysis. Additionally, we introduce a first draft of a standardized implantation plan structure. A standardized digital implantation plan based on the DICOM Structured Report has the potential to overcome current integration problems in the OR and to facilitate new applications.

Integration of computer-aided diagnosis/detection (CAD) results in a PACS environment using CAD–PACS toolkit and DICOM SR

Picture Archiving and Communication System (PACS) is a mature technology in health care delivery for daily clinical imaging service and data management. Computer-aided detection and diagnosis (CAD) utilizes computer methods to obtain quantitative measurements from medical images and clinical information to assist clinicians to assess a patient's clinical state more objectively. CAD needs image input and related information from PACS to improve its accuracy; and PACS benefits from CAD results online and available at the PACS workstation as a second reader to assist physicians in the decision making process. Currently, these two technologies remain as two separate independent systems with only minimal system integration. This paper describes a universal method to integrate CAD results with PACS in its daily clinical environment. The method is based on Health Level 7 (HL7) and Digital imaging and communications in medicine (DICOM) standards, and Integrating the Healthcare Enterprise (IHE) workflow profiles. In addition, the integration method is Health Insurance Portability and Accountability Act (HIPAA) compliant. The paper presents (1) the clinical value and advantages of integrating CAD results in a PACS environment, (2) DICOM Structured Reporting formats and some important IHE workflow profiles utilized in the system integration, (3) the methodology using the CAD-PACS integration toolkit, and (4) clinical examples with step-by-step workflows of this integration.

Evidence and diagnostic reporting in the IHE context

Capturing clinical observations and findings during the diagnostic imaging process is increasingly becoming a critical step in diagnostic reporting. Standards developers—notably HL7 and DICOM—are making significant progress toward standards that enable exchanging clinical observations and findings among the various information systems of the healthcare enterprise. DICOM—like the HL7 Clinical Document Architecture (CDA)—uses templates and constrained, coded vocabulary (SNOMED, LOINC, etc.). Such a representation facilitates automated software recognition of findings and observations, intrapatient comparison, correlation to norms and outcomes research. The scope of DICOM structured reporting (SR) includes many findings that products routinely create in digital form (measurements, computed estimates, etc.). In IHE, two integration profiles are defined for clinical data capture and diagnostic reporting: evidence document, and simple image and numeric report. This paper describes these two DICOM SR based integration profiles in the diagnostic reporting process.

DICOM structured reporting: Part 1. Overview and characteristics.

Supplement 23 to Digital Imaging and Communications in Medicine (DICOM) is an introduction to the structured reporting (SR) classes, which are used for transmission and storage of clinical documents. The SR classes fully support both conventional free-text reports and structured information, thus enhancing the precision, clarity, and value of clinical documentation. In addition, the SR standard provides the capability to link text and other data to particular images or waveforms and to store the coordinates of findings. In other words, SR documents not only describe the specific features contained in images or waveforms but can also refer to any number of images or waveforms. Accordingly, SR bridges the traditional gap between imaging systems and information systems. Furthermore, SR plays an essential role in Integrating the Healthcare Enterprise by providing healthcare practitioners with an effective tool that encompasses a variety of clinical contexts. Harmonization of DICOM SR and the Health Level Seven clinical document architecture standard is under way.

DICOM structured reporting: Part 2. Problems and challenges in implementation for PACS workstations.

Structured reporting (SR) was recently added to the Digital Imaging and Communications in Medicine (DICOM) standard to provide an efficient mechanism for the generation, distribution, and management of clinical reports. The main advantage of SR is the ability to link clinical documents with the referenced images for simultaneous retrieval and display. A generic SR toolkit that covers the different clinical reports used in today's healthcare enterprises was developed for picture archiving and communication system (PACS) workstations. The modules of the SR toolkit collaborate to automatically construct the DICOM SR files from the free-text input presented in hypertext markup language (HTML) by using the associated SR trees. The DICOM toolkit is reused for SR encoding and DICOM services. A setup module was required for creating both the standard and private SR templates used in different healthcare specialties. The SR manager transparently converts between the different SR document presentations, that is, DICOM SR files and HTML documents, to provide the end users with an easy-to-use toolkit. To evaluate and demonstrate the effectiveness of the SR toolkit in a pragmatic setting, the toolkit was integrated into PACS workstations.

A strategy for a wireless patient record and image data

The use of mobile computers improves health care delivery by allowing the medical staff to access important patient information during visits to the patient bedside or in emergency situations. This paper presents a software technology in which the medical and nursing staff will be equipped with handheld computers connected via radio to a central server that provides access to the patients' data and actively informs about pending task distributions. The server works as a database for DICOM compliant information, ranging from patient's computerized tomography (CT), ultrasonography (US) and magnetic resonance (MR) images to medical findings, observations and prescriptions stored in DICOM Structured Report standard. The server prototype developed makes the search and recovery of these DICOM archives possible through a local wireless network and a personal digital assistant (PDA)-compatible graphical user interface (GUI).

XML Schema Representation of DICOM Structured Reporting.

The Digital Imaging and Communications in Medicine (DICOM) Structured Reporting (SR) standard improves the expressiveness, precision, and comparability of documentation about diagnostic images and waveforms. It supports the interchange of clinical reports in which critical features shown by images and waveforms can be denoted unambiguously by the observer, indexed, and retrieved selectively by subsequent reviewers. It is essential to provide access to clinical reports across the health care enterprise by using technologies that facilitate information exchange and processing by computers as well as provide support for robust and semantically rich standards, such as DICOM. This is supported by the current trend in the healthcare industry towards the use of Extensible Markup Language (XML) technologies for storage and exchange of medical information. The objective of the work reported here is to develop XML Schema for representing DICOM SR as XML documents. We briefly describe the document type definition (DTD) for XML and its limitations, followed by XML Schema (the intended replacement for DTD) and its features. A framework for generating XML Schema for representing DICOM SR in XML is presented next. None applicable. A schema instance based on an SR example in the DICOM specification was created and validated against the schema. The schema is being used extensively in producing reports on Philips Medical Systems ultrasound equipment. With the framework described it is feasible to generate XML Schema using the existing DICOM SR specification. It can also be applied to generate XML Schemas for other DICOM information objects.

DICOM Structured Reporting—a prototype implementation

About 1 year ago, Digital Imaging and Communications in Medicine (DICOM) Structured Reporting (SR) has been released as an official extension of the DICOM standard. Structured Reporting introduces a new concept for structuring and encoding medical reports in a standardised manner. Since this approach is quite different from any other extension that has been added to the DICOM standard in the past, it is not surprising that there is no “real” application available up to now. However, we have developed a DICOM SR editor and viewer, and demonstrated this prototype at RSNA infoRAD 2000 and ECR 2001 together with two of DICOM's new security extensions: secure network transmission and digital signatures.

Integrating Digital Imaging and Communications in Medicine (DICOM)-structured reporting into the hospital environment.

The Digital Imaging and Communications in Medicine (DICOM) Standards Committee has balloted and accepted a new class of objects dealing with the generation, distribution, and management of reports. The structured reporting (SR) objects bridge the traditional separation between imaging and information systems. The DICOM SR objects offer a higher level of integration of the medical enterprise, providing practitioners with an effective tool to cover all aspects of the medical process from admission to discharge. This report presents the technical challenges posed by integrating the concepts introduced by SR with a complete hospital information system (HIS).

DICOM Structured Reporting 構造化報告書

DICOM Structured Reporting 構造化報告書

The SNOMED DICOM Microglossary: Controlled Terminology Resource for Data Interchange in Biomedical Imaging

This paper describes an authoritative, non-proprietary information resource that provides an efficient mechanism for embedding specialized clinical knowledge into the design of healthcare telecommunications systems. The resource marries two types of data interchange standards, a message/electronic-document standard and a terminology standard. In technical terms, it is part protocol and part database. Industry, academia, professional specialty societies, and the federal government participated in its development. The development of multi-specialty content has broadly engaged biomedical domain experts to an unprecedented degree in voluntary, non-proprietary message/document-standards development. The resource is the SNOMED DICOM Microglossary (SDM), a message-terminology (or document-content) mapping resource. The message/electronic-document standard is DICOM (Digital Imaging and Communications in Medicine). The terminology standard is SNOMED, (Systematized Nomenclature of Human and Veterinary Medicine). The SDM specifies the mapping of multi-specialty imaging terminology from SNOMED to DICOM data elements. DICOM provides semantic constraints and a framework for discourse that are lacking in SNOMED. Thus the message standard and the computer-based terminology both depend upon and complete each other. The combination is synergistic. By substitution of different templates of specialty terminology from the SDM, a generic message template, such as the DICOM Visible Light (Color Diagnostic) Image or the DICOM Structured Reporting specification can be reconfigured for diverse applications. Professional societies, with technical assistance from the College of American Pathologists, contribute and maintain their portions of the terminology, and can use SDM templates and term lists in clinical practice guidelines for the structure and content of computer-based patient records.

Clinical importance of the DICOM structured reporting standard.

The purpose of the DICOM Structured Reporting (SR) specification is to improve the documentation of diagnostic images and waveforms. The specification supports the interchange of expressive compound reports in which the critical features shown by images and waveforms can be denoted unambiguously by the observer, indexed, and retrieved selectively by subsequent reviewers. Findings may be expressed by the observer as: 1) text, codes, numeric measurements: 2) computer-generated coordinates of specific regions of interest within images or waveforms; or 3) reference to comparison images, sound, waveforms, curves, and previous report information. The observational and historical findings recorded by the observer may include any evidence referenced as part of an interpretation procedure. Thus, DICOM SR supports not only the reporting of diagnostic observations, but the capability to document fully the evidence that evoked the observations. This capability provides significant new opportunities for large-scale collection of structured data for clinical research, training, and outcomes assessment as a routine by-product of diagnostic image and waveform interpretation and facilitates the pooling of structured data for multi-center clinical trials and evaluations.