Matthew Lungren, MD, Nuance Communications, at RSNA 2023.

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 Dominates at RSNA 2023

Take a deep breath. You survived another RSNA conference.

While a few hardy souls are still enjoying educational sessions in the cozy confines of McCormick Place, the final day of the exhibit floor yesterday marks the end of RSNA 2023 for most attendees. And what a show it was. 

Predictions were that AI would dominate the scientific sessions at RSNA 2023, a forecast that largely panned out. A November 28 session was a case in point, in which a series of top-quality papers were presented on one of the most promising use cases of AI, for breast screening:

• A homegrown AI algorithm that analyzed screening breast ultrasound exams in addition to FFDM and DBT mammograms boosted sensitivity for detecting cancer in 12.5k patients, with better sensitivity for women with dense breasts (71% vs. 60%) and non-dense breasts (79% vs. 63%)
• AI did a good job of detecting breast arterial calcification (BAC) when used prospectively to analyze screening mammograms in 16k women across 15 sites.  It found 15% of women had BAC, a possible marker for atherosclerotic disease
• Swedish researchers used their VAI-B validation platform to compare three AI algorithms (Therapixel, Lunit, and Vara) in 34k women, finding that using AI with a single radiologist boosted sensitivity 10-30% compared to double reading, with a slight loss in specificity (2-7%). VAI-B could be used to validate AI implementation and guide purchasing decisions
• Why does AI miss some breast cancers? South Korean researchers addressed this question by analyzing 1.1k patients with invasive cancers in which AI had a miss rate of 14%. Luminal cancers were missed most often
• Adding AI analysis of prior images to current studies with FFDM and DBT boosted sensitivity for cancer detection in 30k patients, with sensitivity the highest for two years of priors compared to no priors (74% vs. 70%)

The Takeaway

This week’s research points to an exciting near-term future in which AI will help make mammography screening more accurate while helping breast radiologists perform their jobs more efficiently. Landmark studies toward this end were published in 2023 – this week’s RSNA conference shows that we can expect the momentum to continue in 2024. 

Exploring the Full Potential of Photon-Counting CT

The potential of photon-counting CT is creating continued excitement in radiology. New detector technology along with AI and imaging reconstruction techniques will push the frontiers of CT and promise game-changing innovations. Read how GE HealthCare is exploring the full potential of photon-counting CT.

A Tactical Approach to Leadership Success

Learn new strategies for achieving leadership success in this on-demand recording of a RadEqual webinar sponsored by Intelerad and the American Association for Women in Radiology, and featuring Geraldine McGinty, MD, and Melissa Davis, MD.

The Wire

• RSNA Papers on Breast Cancer: Several papers in a November 27 session at RSNA 2023 examined the relationship between breast density and cancer. Researchers reviewed 202k digital screening mammograms to find women with dense breasts had higher odds ratios for interval cancer and overall cancer diagnosis (OR=2.83 and 1.38). Separately, using molecular breast imaging with DBT produced a 2.5X increase in cancer detection in 3k patients. Meanwhile, analyzing normal mammograms with iCAD’s ProFound AI generated risk scores that predicted which women had higher risk of future breast cancer. And an AI model for predicting breast cancer within five years of a normal mammogram worked well at multiple centers in 52k patients (AUCs=0.75-0.80).

• MRI Documents Dangers of Soccer Heading: Diffusion-tensor MRI (DT-MRI) scans detected changes in brain microstructure similar to what’s seen with mild traumatic brain injury (TBI). In a paper presented at RSNA 2023, researchers performed DT-MRI scans on 353 amateur soccer players, in particular focusing on the interface between the brain’s gray and white matter. They found the normally sharp interface was blurred, in direct proportion to the player’s exposure to repetitive head impacts. 

• Black Patients See Delayed Alzheimer’s Diagnosis: Black patients were diagnosed with Alzheimer’s disease an average of almost five years later than white and Hispanic patients – even though they are at higher risk of the disease. In a study presented at RSNA 2023, researchers looked at patients who got CT or MRI scans for cognitive impairment, finding that Blacks who were later diagnosed with Alzheimer’s had an average age of 73 years, compared to 68 for whites and 67 for Hispanics. Blacks also had lower rates of MRI for cognitive impairment (51% vs. 60% for whites and 67% for Hispanics. 

• X-Ray AI Slashes Fracture Turnaround: An algorithm that analyzed X-rays for signs of fracture and prioritized the ones that appeared positive slashed report turnaround time in a study presented November 28 at RSNA 2023. Researchers from SimonMed Imaging used AI to analyze 28k X-rays and compared it to 23k before AI at 200 centers, finding that report turnaround time for positive fracture cases fell by 39 hours thanks to AI’s reprioritization (9 vs. 48 hours). 

• HOPPR Debuts Foundation Model: AI developer HOPPR has launched Grace, a multimodal foundation model for development of AI applications. Foundation models are designed to make it easier to aggregate data needed to train AI algorithms, and HOPPR developed Grace as a B2B model for AI and PACS developers to create image-to-image and text-to-image learning across all imaging modalities. Grace is being offered as a beta version initially, with commercial release in Q1 of 2024. The company also signed AWS to power the platform. HOPPR recently hired imaging veteran Khan Siddiqui, MD, as CEO. 

• Studies Support Contrast Mammo: A series of November 27 talks at RSNA 2023 supported broader use of contrast-enhanced mammography (CEM). CEM proved to be a good supplementary screening tool in a study of 1.3k women with extremely dense breast tissue (sensitivity=88%), while a study of 601 women eligible for breast MRI found CEM and DBT were able to detect twice as many cancers as DBT alone (12 vs. 6). And in 461 high-risk patients, CEM had a cancer detection rate of 21.7 per 1,000, comparable to breast MRI. 

• Barco Adds DeepLook Breast Density Tool: Display manufacturer Barco has signed a deal with DeepLook Medical to integrate that company’s DL Precise algorithm for breast cancer detection into Barco’s Intuitive Workflow software. Barco customers will be able to segment and measure breast lesions or even add color to segmentations using Barco’s SteadyColor feature. DL Precise will be offered under a licensing model that can be installed on workstations using Barco’s QAWeb Enterprise platform. 

• Us2.ai’s Echo Strain Accuracy: A new study in European Heart Journal – Digital Health showed that Us2.ai’s AI echo algorithm can interpret echocardiographic strain images with similar accuracy as conventional measurements, highlighting how AI can democratize cardiac strain exams. Us2.ai successfully analyzed the majority of exams across three global cohorts (89%, 96%, 98%), while achieving good agreement with manual measurements, and accurately detecting patients with HF (AUCs: 0.89 for total HF, 0.98 for HFrEF) and with regional wall-motion abnormalities (AUC: 0.80).

• Quantivly Adds to Operations Software: At RSNA 2023, Quantivly displayed enhancements to its software for improving radiology operations, which enables users to create a “digital twin” to simulate a facility’s operating environment. New features include a smart recommendation engine to detect operational inefficiencies and recommend fixes, as well as a natural language interface to make ChatGPT-like queries to the digital twin.

• Fujifilm Products Include 0.4T MRI Scanner: A new 0.4T permanent magnet MRI scanner called Aperto Lucent Plus is spearheading Fujifilm’s product launches at RSNA 2023. The scanner sports a single-pillar design with 320° open view for better patient comfort. In CT, Fujifilm has introduced FCT iStream, designed to be a compact, affordable option for customers, while in DR the company is launching the Essentia FS floor-mounted system and Essentia SA compact straight-arm unit, while D-EVO Suite OTCx is an overhead tube-crane X-ray the company launched in July.

• FDA Clears Pixyl Brain Software: The FDA has cleared the Pixyl.Neuro application from French software developer Pixyl. The software analyzes brain MRI scans to detect neurological disorders and speed up radiologist reading time by quantifying brain region volumes and comparing them to normal data to identify early signs of atrophy. Pixyl.Neuro is already in use in 12 countries; Pixyl already has a distribution deal with Brainomix in certain European markets.

• Densitas Launches Mammo QA Software: Densitas is launching new mammography quality assurance software called intelliMaven at RSNA 2023. The AI-powered application works with the company’s intelliMammo software and helps breast imaging facilities meet MQSA EQUIP requirements for QA by simplifying data interpretation and analysis and automating analytics, enabling them to operate more efficiently. Separately, Densitas announced a technology integration agreement with Agfa HealthCare that unites intelliMammo with Agfa’s enterprise imaging offerings.

Innovations in the Medical Image Acquisition Chain

What are some of the major innovations happening now in the medical image acquisition chain? In the latest edition of The Imaging Wire Show, we talked to Josh Gurewitz and Ajit Shankaranarayanan of Subtle Medical about new developments in image acquisition and enhancement.

A Comprehensive AI Copilot

Gleamer is dedicated to pioneering the future of medical imaging by building a comprehensive AI copilot that will pave the way for precision medicine. Learn more about the company and its solutions.

AI in Radiology and the Considerations for Regulation

AI in healthcare has grown quickly, as have discussions about AI regulation. Listen to this on-demand webinar from Bayer and Calantic Digital Solutions to hear expert perspectives on the current and future state of AI governance in healthcare and radiology.

The Resource Wire

• AMRIC’s Multimodality Approach to Medical Imaging: AMRIC is a new premium imaging clinic on Manhattan’s Upper East Side. Learn about their multimodality approach to medical imaging and why they turned to United Imaging for cutting-edge CT, MRI, and molecular imaging technology. 

• A Better Way to Deploy AI: CARPL.ai’s end-to-end modular platform for AI deployment is changing how University Hospitals in Cleveland uses AI to enhance patient care. Hear from UH clinicians and administrators as they share their experiences.

• Achieve the Benefits of AI with Choice and Control: AI for imaging is here. More and more applications are clearing regulatory hurdles and proving to be mature enough to support clinical use cases. Learn how to achieve the benefits of AI on your own terms in this guide from Merge by Merative. 

• Calculate Your Cost Savings: Instantly calculate your savings from data standardization with the Curie|ENDEX solution using Enlitic’s ROI Calculator. ENDEX conforms messy metadata to a standard convention, making it searchable and making hanging protocols more reliable.

• How to Revamp Patient Engagement: What’s the best way to eliminate patient frustration and get them engaged with healthcare again? Find out how technology can revamp the patient engagement experience in this article produced in collaboration with Nuance in Becker’s Hospital Review.

• The Benefits of Breast Imaging AI: Breast imaging AI can help providers reduce their workload and improve patient care. Blackford Analysis offers a wide selection of breast imaging AI apps on its Blackford Platform – find out how they could benefit your organization. 

• A Major US Health System Optimizes Image Exchange: A major US healthcare organization streamlined their image exchange, saving them $100,000 while improving their patient experience and eliminating administrative work. Find out how in this case study from PocketHealth.

• 3 Good Reasons to Add Mammography: There are three good reasons to add mammography services at your imaging site as providers expect higher demand for breast imaging services. Get the facts about mammography on this resource page from Siemens Healthineers. 

• Improving Patient Outcomes in Lung Cancer: Early detection is key to improving treatment pathways and patient outcomes in lung cancer. Learn more facts about lung cancer screening on this resource page from Riverain Technologies. 

• The Benefits of an AI Accelerator: What is an AI accelerator, and how can it impact your practice? Learn about the Visage AI Accelerator program and its impact on research and clinical practice in this video from Visage Imaging. 

• The Intersection of Health Technology and Business: How are the worlds of health technology and business intersecting? In this episode of The Radiology Report, Intelerad Medical Systems President Morris Panner sits down with Medality CEO Daniel Arnold to explore his career and discuss the evolution of the industry.

• The Benefits of AI-Automated Echo: Us2.ai just published what might be the most comprehensive paper we’ve seen on AI echo, detailing the benefits of AI-automated echocardiography, the global need for more scalable and flexible CVD assessments, and how its technology is fit for the future. 

• Gain Clarity at Speed in MRI: Acquire images faster per MRI machine per day with STAGE from SpinTech MRI. STAGE reduces the time for MRI brain protocols by 30% for your most common exams. 

• Automated Solutions for Patient and Provider Sharing: What’s the latest news from Clearpath? Find out how its fully automated patient and provider solutions for sharing medical records and images are making waves in healthcare.

• Unleash the Power of the Cloud: Change Healthcare’s cloud-native, zero-footprint Stratus Imaging PACS is live in clinical use. See how Stratus Imaging PACS is helping radiology practices improve productivity and patient care, while eliminating the cost and resource constraints of on-premise systems.