A curated selection of DSI research papers covering a broad range of topics on the use of artificial intelligence in Radiology.
A curated selection of DSI research papers covering a broad range of topics on the use of artificial intelligence in Radiology.
March 12, 2024 — Proceedings From the 2022 ACR-RSNA Workshop on Safety, Effectiveness, Reliability, and Transparency in AI
Despite the surge in artificial intelligence (AI) development for health care applications, particularly for medical imaging applications, there has been limited adoption of such AI tools into clinical practice. During a 1-day workshop in November 2022, co-organized by the ACR and the RSNA, participants outlined experiences and problems with implementing AI in clinical practice, defined the needs of various stakeholders in the AI ecosystem, and elicited potential solutions and strategies related to the safety, effectiveness, reliability, and transparency of AI algorithms. Continue reading
January 22, 2024 — Developing, Purchasing, Implementing and Monitoring AI Tools in Radiology: Practical Considerations. A Multi-Society Statement From the ACR, CAR, ESR, RANZCR & RSNA
The integration of AI in radiology holds the potential to revolutionize healthcare practices by advancing diagnosis, quantification, and management of multiple medical conditions. Nevertheless, the ever-growing availability of AI tools in radiology highlights an increasing need to critically evaluate claims for its utility and to differentiate safe product offerings from potentially harmful, or fundamentally unhelpful ones. Continue reading
October 16, 2023 — Projected Growth in FDA-Approved Artificial Intelligence Products Given Venture Capital Funding (jacr.org)
Medical imaging accounts for 85% of digital health’s venture capital funding. As funding grows, it is expected that artificial intelligence (AI) products will increase commensurately. The study’s objective is to project the number of new AI products given the statistical association between historical funding and FDA-approved AI products. Continue reading
In this white paper, the ACR Pediatric AI Workgroup of the Commission on Informatics educates the radiology community about the health equity issue of the lack of pediatric artificial intelligence (AI), improves the understanding of relevant pediatric AI issues, and offers solutions to address the inadequacies in pediatric AI development. Continue reading
July 22, 2023 — Keeping Patient Data Secure in the Age of Radiology Artificial Intelligence: Cybersecurity Considerations and Future Directions - ScienceDirect
Implementation of AI comes along with cybersecurity risks and challenges that practices should be aware of and mitigate for a successful and secure deployment. In this article, these cybersecurity issues are examined through the lens of the “CIA” triad framework—confidentiality, integrity, and availability. Continue reading
July 17, 2023 — The Role of Organized Radiology in Advancing Imaging Artificial Intelligence - Journal of the American College of Radiology (jacr.org)
This article discusses ACR and SIIM’s ongoing collaboration to lead and educate their members on artificial intelligence. Continue reading
This is a response to a letter to the editor regarding the study “Real-World Performance of Large Vessel Occlusion Artificial Intelligence–Based Computer-Aided Triage and Notification Algorithms—What the Stroke Team Needs to Know.” Continue reading
The purpose of this study was to evaluate the real-world performance of two FDA-approved artificial intelligence (AI)-based computer-aided triage and notification (CADt) detection devices and compare them with the manufacturer-reported performance testing in the instructions for use. Continue reading
April 30, 2023 — Specialty Society Support for Multicenter Research in Artificial Intelligence - PubMed (nih.gov)
The American College of Radiology (ACR) has a long history of supporting multicenter trials in diagnostic radiology and radiation oncology. These trials typically involve standardized protocol development, site management, the development of study data dictionaries and data collection and cleaning, independent interpretation of imaging findings and centralized support to collate, analyze and publish the results. Continue reading
November 11, 2022 — ACR's Connect and AI-LAB technical framework - PubMed (nih.gov)
The AI-LAB application within ACR Connect allows users to investigate AI models using their own local data while maintaining data security. The software enables non-technical users to participate in the evaluation and training of AI models as part of a larger, collaborative network. Continue reading
September 29, 2022 — Artificial intelligence in oncologic imaging - ScienceDirect
Radiology is integral to cancer care. Compared to molecular assays, imaging has its advantages. Imaging as a noninvasive tool can assess the entirety of tumor unbiased by sampling error and is routinely acquired at multiple time points in oncological practice. Continue reading
August 2, 2022 — Implementation of Clinical Artificial Intelligence in Radiology: Who Decides and How? | Radiology (rsna.org)
Successful clinical implementation of artificial intelligence is facilitated by establishing robust organizational structures to ensure appropriate oversight of algorithm implementation, maintenance, and monitoring. Continue reading
The Society of Interventional Radiology Foundation called upon 13 key opinion leaders in the field of IR to develop research priorities for clinical applications of AI in IR. The objectives of the assembled research consensus panel were to assess the availability and understand the applicability of AI for IR, estimate current needs and clinical use cases, and assemble a list of research priorities for the development of AI in IR. Continue reading
January 5, 2022 — Advancing Research on Medical Image Perception by Strengthening Multidisciplinary Collaboration - PubMed (nih.gov)
At a time when medical imaging is being transformed by digital technologies and artificial intelligence, understanding the basic perceptual and cognitive processes underlying medical image interpretation is vital for increasing diagnosticians' accuracy and performance, improving patient outcomes, and reducing diagnostician burnout. Continue reading
December 27, 2021 — FDA-regulated AI Algorithms: Trends, Strengths, and Gaps of Validation Studies - ScienceDirect
Insufficient public information on validation datasets in several FDA-regulated AI/ML algorithms makes it difficult to justify clinical applications since their generalizability and presence of bias cannot be inferred. Continue reading
October 2, 2021 — Data Sharing of Imaging in an Evolving Health Care World: Report of the ACR Data Sharing Workgroup, Part 2: Annotation, Curation, and Contracting - ScienceDirect
Embarking on a data sharing partnership engenders a host of ethical, practical, technical, legal, and commercial challenges that require a thoughtful, considered approach. In 2019 the ACR convened a Data Sharing Workgroup to develop philosophies around best practices in the sharing of health information. This is Part 2 of a Report on the workgroup's efforts in exploring these issues. Continue reading
In 2019 the ACR convened a Data Sharing Workgroup to develop philosophies around best practices in the sharing of health information. The workgroup identified five broad domains of activity important to collaboration using patient data: privacy, informed consent, standardization of data elements, vendor contracts, and data valuation. This is Part 1 of a Report on the workgroup's efforts in exploring these issues. Continue reading
October 1, 2021 — Real-World Surveillance of FDA-Cleared Artificial Intelligence Models: Rationale and Logistics - Journal of the American College of Radiology (jacr.org)
Recent studies have documented concerns over the robustness, explainability, and generalizability of artificial intelligence (AI) models both in research settings and in clinical use of FDA-cleared models. A systematic review of 254 AI publications in coronavirus disease 2019 pneumonia reported outcome biases in all models; no AI model (0 of 62 best models) was suitable for clinical use. Continue reading
September 30, 2021 — Evaluation and Real-World Performance Monitoring of Artificial Intelligence Models in Clinical Practice: Try It, Buy It, Check It - ScienceDirect
In this article, researchers discuss why regulatory clearance alone may not be enough to ensure AI will be safe and effective in all radiological practices and review strategies available resources for evaluating before clinical use and monitoring performance of AI models to ensure efficacy and patient safety. Continue reading
April 20, 2021 — ACR Data Science Institute Artificial Intelligence Survey - ScienceDirect
The ACR Data Science Institute conducted its first annual survey of ACR members to understand how radiologists are using artificial intelligence (AI) in clinical practice and to provide a baseline for monitoring trends in AI use over time. Continue reading
March 12, 2021 — IHE Radiology White Paper: AI Interoperability in Imaging, Revision 1.0 – Public Comment
This white paper describes an organizing framework and roadmap for creating profiles to support the creation, lifecycle, and use of AI datasets and AI models. Continue reading
June 24, 2020 — Multi-Institutional Assessment and Crowdsourcing Evaluation of Deep Learning for Automated Classification of Breast Density - ScienceDirect
Researchers developed deep learning algorithms to automatically assess BI-RADS breast density. They demonstrated the possible parameters that can influence the performance of the model and how crowdsourcing can be used for evaluation. This study was performed in tandem with the development of the ACR AI-LAB, a platform for democratizing artificial intelligence. Continue reading
December 14, 2019 — Artificial intelligence in radiology: the ecosystem essential to improving patient care - ScienceDirect
AI has the potential to be a transformative technology that will significantly impact patient care. Particularly, AI has a promising role in radiology, in which computers are indispensable and new technological advances are often sought out and adopted early in clinical practice. Researchers present an overview of the basic definitions of common terms, the development of an AI ecosystem in imaging and its value in mitigating the challenges of implementation in clinical practice. Continue reading
November 29, 2019 — Integrating Artificial Intelligence Into Radiologic Practice: A Look to the Future - Journal of the American College of Radiology (jacr.org)
DSI leadership responds to M.A. Mazurowski’s “Artificial Intelligence May Cause a Significant Disruption to the Radiology Workforce." Continue reading
October 1, 2019 — Ethics of Artificial Intelligence in Radiology: Summary of the Joint European and North American Multisociety Statement | Radiology (rsna.org)
This is a condensed summary of an international multisociety statement on ethics of artificial intelligence (AI) in radiology produced by the ACR, European Society of Radiology, RSNA, Society for Imaging Informatics in Medicine, European Society of Medical Imaging Informatics, Canadian Association of Radiologists, and American Association of Physicists in Medicine. Continue reading
For physicians, academic data science nomenclature can seem not only cryptic but at times downright confusing. Additionally, because artificial intelligence (AI)—an important subset of data science—will likely have a significant impact on the future practice of medicine, physicians, understandably, want the terminology used to describe the field to the public to convey easily understood messages. Continue reading
July 15, 2019 — Bending the Artificial Intelligence Curve for Radiology: Informatics Tools From ACR and RSNA - ScienceDirect
Artificial intelligence (AI) will reshape radiology over the coming years. The radiology community has a strong history of embracing new technology for positive change, and AI is no exception. Continue reading
June 24, 2019 — Quality and Data Science - Journal of the American College of Radiology (jacr.org)
Applications of data science technologies including machine learning and artificial intelligence (AI) for the radiologic sciences are rapidly proliferating. Although image analysis has captured much of our attention, AI and advanced data analytics tools to improve quality, workflow, and patient experience are gaining importance, proposes four areas for performance improvement in medicine: improving the overall health of the population, improving the individual experience of care, improving the work life of health care providers, and reducing per capita costs. Continue reading
Important artificial intelligence (AI) tools for diagnostic imaging include algorithms for disease detection and classification, image optimization, radiation reduction, and workflow enhancement. Although advances in foundational research are occurring rapidly, translation to routine clinical practice has been slower. Continue reading
May 16, 2019 — Democratizing AI - ScienceDirect
Whether it is adjusting parameters for MR pulse sequences, specifying parameters to optimize radiation exposure on CT scanners, or programming complex treatment planning protocols in radiation oncology, radiology professionals use sophisticated computer software platforms in our practices daily to take better care of our patients. Yet because most of us are not data scientists or software engineers, up until now, most of us feel at least a little intimidated by artificial intelligence (AI) and how we will be able to use it. Continue reading
April 1, 2019 — The Role of the ACR Data Science Institute in Advancing Health Equity in Radiology - ScienceDirect
The ACR Data Science Institute has developed structured AI use cases with data elements that allow the development of standardized data sets for AI testing and training across multiple institutions to promote the availability of diverse data for algorithm development. Continue reading
October 30, 2018 — The Role of the FDA in Ensuring the Safety and Efficacy of Artificial Intelligence Software and Devices - Journal of the American College of Radiology (jacr.org)
The FDA is considering ways to further streamline the review process, including the Software Precertification Program, the Medical Device Development Tools, and the use of real-word data from clinical practice to monitor the safety and effectiveness of medical devices in clinical practice. Continue reading
October 26, 2018 — How Structured Use Cases Can Drive the Adoption of Artificial Intelligence Tools in Clinical Practice - Journal of the American College of Radiology (jacr.org)
An artificial intelligence (AI) “use case” is more than just an idea for what an AI algorithm should do. Creation of structured AI use cases is an important opportunity for radiologists to play a leading role in assisting developers in creating algorithms that will be useful, effective, and safe in clinical practice and can enhance the value radiology professionals provide to their patients and health systems. Continue reading
The ACR Data Science Institute (DSI) has developed a foundational framework for AI to improve clinical care and ensure these algorithms can be safely deployed and monitored in clinical practices on a large scale. Continue reading
March 9, 2018 — 2017 Presidential Address: Staying Ahead of the Curve - ScienceDirect
From economics and payment policy to imaging appropriateness, the ACR has led the way in keeping our specialty ahead of the curve. However, being ahead of the curve is a fragile place, and constant diligence is needed to remain there. Continue reading
February 28, 2018 — Artificial Intelligence in Health Care: Brave New World or Golden Opportunity? - Journal of the American College of Radiology (jacr.org)
Researchers discuss the science of AI in terms that are relevant to practicing radiology professionals and attempt to demystify the advances in data science, including how AI techniques that are seemingly a “black box” can be portrayed in a way that makes algorithm development more transparent to radiologists. Continue reading
Radiology specialty societies can advance AI in ways that allow radiology professionals to increase the value we provide to our patients and enhance our role in our health systems. Specialty societies can focus educational efforts for radiologists and all stakeholders on how radiologists can integrate AI into clinical practice. Continue reading