Laura Heacock, MD, after testing Google’s new Gemini generative AI algorithm.

What has radiology learned so far as it transitions to wider use of cloud-based medical image management? In this Imaging Wire Show, we talked to Ran Rumianek of Change Healthcare about how now is the right time to begin moving imaging data to the cloud.

Imaging Wire Sponsors

Bayer  •  Blackford  •  CARPL.ai  •  Change Healthcare  •  Clearpath  •  Enlitic  •  GE HealthCare  •  Gleamer  •  Intelerad  •  Medality  •  Merge by Merative  •  Nuance  •  PocketHealth  •  Riverain Technologies  •  Siemens Healthineers  •  SpinTech MRI  •  Subtle Medical  •  United Imaging  •  Us2.ai  •  Visage Imaging

Artificial Intelligence

AI’s Impact on Breast Screening

One of the most exciting radiology use cases for AI is in breast screening. At last week’s RSNA 2023 show, a paper highlighted the technology’s potential for helping breast imagers focus on cases more likely to have cancer.

Looking for cancers on screening mammography has been compared to finding a needle in a haystack, and as such it’s considered to be one of the areas where AI can best help. 

• One of the earliest use cases was in identifying suspicious breast lesions during radiologist interpretation (remember computer-aided detection?), but more recently researchers have focused on using AI as a triage tool, by identifying cases most likely to be normal that could be removed from the radiologist’s urgent worklist. Studies have found that 30-40% of breast screening cases could be read by AI alone or triaged to a low-suspicion list.

But what impact would AI-based breast screening triage have on radiologist metrics such as recall rate? 

• To answer this question, researchers from NYU Langone Health prospectively tested their homegrown AI algorithm for analyzing DBT screening cases.

The algorithm was trained to identify extremely low-risk cases that could be triaged from the worklist while more complex cases where the AI was uncertain were sent to radiologists, who knew in advance the cases they were reading were more complicated. In 11.7k screening mammograms, researchers examined recall rates over two periods, one before AI triage and one after, finding: 

• The overall recall rate went from 13% before the triage period to 15% after 
• Recall rates for complex cases went from 17% to 20%
• Recall rates for extremely low-risk studies went from 6% to 5%
• There were no statistically significant differences in any of the comparisons
• No change in median self-reported perceived difficulty of reading from the triage lists compared to non-triage list, regardless of years of experience

In future work, the NYU Langone researchers will continue their study to look at AI’s impact on cancer detection rate, biopsy rate, positive predictive value, and other metrics.

The Takeaway

The NYU Langone study puts a US spin on research like MASAI from Sweden, in which AI was able to reduce radiologists’ breast screening workload by 44%. Given the differences in screening protocols between the US and Europe, it’s important to assess how AI affects workload between the regions.

Further work is needed in this ongoing study, but early results indicate that AI can triage complex cases without having an undue impact on recall rate or self-perceived difficulty in interpreting exams – a surrogate measure for burnout.

The Difference Is in the Details

Riverain Technologies has developed the capability to create synthetic nodules automatically and place them in relevant anatomical contexts. Hear Chief Science Officer Jason Knapp explain the company’s unique position in this video.

The Power of the Platform at RSNA 2023

How can radiologists get easy access to AI solutions? Watch this video interview at RSNA 2023 with CARPL.ai CEO Vidur Mahajan and Chief Architect Rohit Takhar to learn how the power of the platform is making AI for radiology a reality.

The Wire

• AI Finds Interval Breast Cancers: In another set of breast screening talks from the same RSNA session, researchers found that ScreenPoint’s Transpara 1.7.1 AI helped identify interval cancers missed on screening rounds – among 185k screening mammograms, 44% of true interval cancers were flagged by AI. Another study found that women diagnosed with advanced cancers had longer median intervals between DBT screening rounds versus non-advanced (890 vs. 781 days). 

• New Google Generative AI: Google yesterday upped the ante in the battle over generative AI, launching Gemini, a new AI model designed to take on OpenAI’s GPT line of algorithms. Gemini is a multimodal AI model that can accept inputs from text to images, and Google plans to bundle it into multiple products, from Android smartphones to search engines. It didn’t take radiologists long to test the algorithm against radiology cases. The verdict? Radiologist jobs are secure … for now. 

• AI Classifies Normal Chest X-Rays: A series of RSNA 2023 papers presented on November 30 showed that AI can separate normal chest X-rays from abnormal studies. In one study from four sites in the US and India, the DeepTek algorithm separated 37-63% of normal X-rays. In another study, the CXR-Lung-Risk tool predicted COPD on routine chest X-rays at Mass General Brigham, while in Zambia AI was used to detect tuberculosis on screening radiographs with good sensitivity and specificity (87% and 70%). Finally, South Korean researchers found the Lunit Insight CXR AI removed 22% of frontal chest X-rays from those that required reporting.

• Siemens Signs 10-Year Partnership: Siemens Healthineers has signed a 10-year deal to provide medical imaging and lab equipment to OU Health Partners in Oklahoma. Siemens will provide advanced imaging technology such as the 7T Magnetom Terra MRI scanner and Naeotom Alpha photon-counting CT system, as well as mobile imaging systems and syngo Virtual Cockpit software to deliver care in rural and underserved communities. The agreement also includes the creation of the OU Health Sciences Imaging Institute to spearhead research and drive breakthroughs in medical technology. 

• Deepc Lands Hyland, Partners with Qure: German AI platform developer deepc has signed a collaboration with Hyland Software to integrate its deepcOS AI platform into Hyland’s medical imaging suite, giving Hyland customers access to vendor-neutral AI capabilities. In other news, deepc signed a deal with Qure.ai that integrates Qure’s AI algorithms for chest X-ray, chest CT, and musculoskeletal X-ray into deepcOS. Finally, deepc announced its support for MONAI, the UK open-source AI framework. Deepc entered the UK market earlier this year via a relationship with BT.

• Qure Secures UK Partnerships: In other news from Qure.ai, the company has signed two partnerships for its AI technology in the UK. First, Qure will be deploying its qXR solution for chest X-ray reporting at NHS Greater Glasgow and Clyde as part of a partnership with the health system, the University of Glasgow, and the Scottish government. Separately, Qure was named an industry partner in the UK College of Radiographers Industry Partnership Scheme. The deals come as the UK makes major investments in deploying AI within the NHS.

• Volpara Highlights RSNA Studies: Volpara highlighted several studies presented at RSNA 2023 with its software. Stamatia Destounis, MD, of Elizabeth Wende Breast Center reported that using Volpara Risk Pathways and the company’s density assessment software for risk assessment led to better outcomes. One study from Kettering Health showed that using Volpara Analytics to help train technologists produced a 4% increase in mammography image quality, while a second Kettering paper found high RT satisfaction levels with the software. 

• Enlitic Signs New ENDEX Customers: Enlitic has signed on new customers for its ENDEX data standardization toolset. Wake Radiology UNC REX Healthcare is deploying ENDEX to improve its reporting workflows and increase the capacity of its over 50 radiologists, who report on more than 250k scans a year. In a second deal, Southeast Alaska Regional Health Consortium (SEARHC) is deploying ENDEX to help its radiologists manage large volumes of patient studies. 

• Intelerad Scores $50M Michigan Install: Intelerad Medical Systems has scored a multiyear $50M contract to install its technology at one of Michigan’s largest health systems. The system operates 22 hospitals and 300 outpatient and post-acute facilities, and Intelerad will be providing its IntelePACS, Clario SmartWorklist, cloud-enabled VNA, and image-exchange solutions. 

• FDA Clears 4DMedical CT Software: The FDA has cleared 4DMedical’s CT LVAS software for creating lung ventilation studies using CT images. 4DMedical’s technology produces reports that include color-coded images of regional airflow and lung ventilation to help radiologists diagnose lung diseases. The company already had clearance for XV LVAS for use with fluoroscopy systems, which recently received a Medicare payment rate of $299. The CT LVAS clearance will make the technology available more widely. 

• Canon Signs R&D Deal with Cleveland Clinic: Canon has signed a high-level R&D partnership with Cleveland Clinic on medical imaging research, announcing the project at a packed RSNA 2023 news conference that included videotaped messages from US and Japanese ambassadors. The partners will build an imaging research center adjacent to Cleveland Clinic’s main campus, with initial research focusing on cardiology, neurology, and musculoskeletal medicine. The relationship is the next stage in Canon’s project to build a major R&D hub in the Cleveland area, an initiative the company announced at RSNA 2022.

• Agamon & Mayo Follow-Up: Follow-up care management solutions company Agamon Health entered into a know-how agreement with Mayo Clinic aimed at developing workflows that close follow-up gaps in cardiovascular care. Agamon Health got its start developing solutions that identify incidental radiology findings and ensure clinical follow-ups, and the new Mayo collaboration will focus on ensuring adherence to guideline-recommended cardiology follow-ups – apparently starting with aortic stenosis.

• Portable Brain Scanner Debuts: Australian medical device developer EMVision displayed the second generation of its portable brain scanner for diagnosing stroke at RSNA 2023. EMVision’s first-generation device mounts an electromagnetic scanner on a trolley that can be wheeled to patients; the second-gen scanner is an ultra-lightweight portable headset that can be taken aboard ambulances and helicopters to help first responders diagnose stroke victims before they reach the hospital. The second-gen device is in prototype development, with plans to start clinical testing soon.

Solutions to Transform Medical Image Delivery

Medical providers and health systems are looking to ditch the disc and modernize their patients’ journey. Learn how Clearpath helps them reduce the cost of retrieving and fulfilling patient requests for imaging and medical records.

Lessons of Cloud Image Management

What has radiology learned so far as it transitions to wider use of cloud-based medical image management? In this Imaging Wire Show, we talked to Ran Rumianek of Change Healthcare about how now is the right time to begin moving imaging data to the cloud.

United Imaging’s RSNA 2023 Highlights

What were the highlights in United Imaging’s booth at RSNA 2023? Watch this video interview with CEO Jeffrey Bundy, PhD, at the conference to learn about the company’s 510(k)-pending 5T MRI scanner, mobile digital radiography system, and more.

The Resource Wire

• Key Takeaways in Image Exchange from RSNA 2023: What trends in image exchange surfaced at RSNA 2023, and what were some of the lessons learned? Check out this article from PocketHealth Co-Founder & CEO Rishi Nayyar for actionable insights.

• AI Applications in Neuroradiology: What are the most common AI applications in neuroradiology? This downloadable e-book from Bayer and Calantic Digital Solutions reviews the most common AI applications for brain imaging and the evidence behind them.  

• Improving Image Acquisition: Watch this video interview from RSNA 2023 with Subtle Medical Founder Greg Zaharchuk, MD, PhD, to learn about the company’s AI-based technology for improving image acquisition, including SubtleMR, SubtlePET, and other applications. 

• The Journey to Cloud-Based PACS: Radiology is looking closely at cloud-based PACS as an alternative to on-premises digital image management. Learn about providers who have made the switch with Visage Imaging in this white paper from Signify Research. 

• The Big Picture at Intelerad at RSNA 2023: What was in the big picture at Intelerad Medical Systems at RSNA 2023? Check out this video interview with President Morris Panner about the company’s accomplishments in 2023 and its plans for 2024, including a big focus on image exchange.

• A Technologists’ Guide to Cardiac CT Protocols: Interested in learning more on cardiac CT protocols? Hear from Luis Landeras, MD, and technologist Michael Mason from the University of Chicago as they share common challenges, clinical cases, and customized CT protocols they utilize with cardiac patients on their GE HealthCare Revolution Apex CT scanner.

• Solutions to Solve Radiology’s Workflow Challenges: Radiology faces numerous challenges to more efficient workflow, from the siloed nature of healthcare enterprises to mundane tasks that are ripe for automation. In this Imaging Wire Show, we talked to Dr. Matthew Lungren and Calum Cunningham of Nuance Communications.

• Faster MRI Scans with No Compromise: What if you could speed up your MRI scans with no compromise on image quality? Watch this video from RSNA 2023 to hear from SpinTech MRI CEO Karen Holzberger and Senior Clinical Sales Executive John Ciliberto about how their STAGE software is making this vision a reality.

• True TOF Technology Sets the Standard in PET/CT: True time-of-flight (TOF) PET/CT based on lutetium oxyorthosilicate (LSO) detectors offers numerous clinical advantages, such as better definition of small lesions and improved uniformity. Learn the other advantages in this article from Siemens Healthineers. 

• An Update from Merge by Merative at RSNA 2023: At RSNA 2023, we caught up with Merge by Merative’s Julie Pekarek, head of product and strategy, for an update on the company’s cloud solutions, their new digital pathology and 3D printing announcements, and how they’re tackling challenges around workflow and burnout.

• Medical Imaging Data for Improved Research: The need for high-quality medical imaging data is crucial to drive advancements in diagnostics and treatment. Learn how Enlitic’s ENDEX for data standardization and ENCOG for data anonymization solutions enable researchers to access superior data while optimizing their resources. 

• Major Milestones in Platform AI: It’s been a busy year for AI platform developer Blackford. We reviewed the company’s major milestones in this video interview from RSNA 2023, in which we talked to Blackford executives David Hilderbrand and Anthony Cammack. 

• Radiology’s Changing Training Needs: Radiology is getting more sub-specialized — but is that contributing to the growing workforce shortage? And how can radiologists get the training they need to match changing requirements? We talked about these trends with Daniel Arnold, founder and CEO of Medality, in The Imaging Wire Show.

• A Milestone Study for Cardiac Strain Analysis: Us2.ai’s deep learning algorithm was able to interpret echo AI left ventricular strain images with similar accuracy as conventional measurements. Read all about this milestone study and its implications for patient management in EHJ-Digital Health. 

• Making a Difference in Scoliosis Detection: Did you know scoliosis affects about 2-3% of the population? That’s millions of lives, and Gleamer is on a mission to make a difference with its BoneMetrics solution for automatically detecting and quantifying spinal measurements. Get a demo today.