Journalist Maggie Levantovskaya, writing on burnout in a thread on X.

Imaging Wire Sponsors

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

Artificial Intelligence

Can AI Direct Breast MRI?

A deep learning algorithm trained to analyze mammography images did a better job than traditional risk models in predicting breast cancer risk. The study shows the AI model could direct the use of supplemental screening breast MRI for women who need it most. 

Breast MRI has emerged (along with ultrasound) as one of the most effective imaging modalities to supplement conventional X-ray-based mammography. Breast MRI performs well regardless of breast tissue density, and can even be used for screening younger high-risk women for whom radiation is a concern. 

But there are also disadvantages to breast MRI. It’s expensive and time-consuming, and clinicians aren’t always sure which women should get it. As a result, breast MRI is used too often in women at average risk and not often enough in those at high risk. 

In the current study in Radiology, researchers from MGH compared the Mirai deep learning algorithm to conventional risk-prediction models. Mirai was developed at MIT to predict five-year breast cancer risk, and the first papers on the model emerged in 2019; previous studies have already demonstrated the algorithm’s prowess for risk prediction. 

Mirai was used to analyze mammograms and develop risk scores for 2.2k women who also received 4.2k screening breast MRI exams from 2017-2020 at four facilities. Researchers then compared the performance of the algorithm to traditional risk tools like Tyrer-Cuzick and NCI’s Breast Cancer Risk Assessment (BCRAT), finding that … 

• In women Mirai identified as high risk, the cancer detection rate per 1k on breast MRI was far higher compared to those classified as high risk by Tyrer-Cuzick and BCRAT (20.6 vs. 6.0 & 6.8)
• Mirai had a higher PPV for predicting abnormal findings on breast MRI screening (14.6% vs. 5.0% & 5.5%)
• Mirai scored higher in PPV of biopsies recommended (32.4% vs. 12.7% & 11.1%) and PPV for biopsies performed (36.4% vs. 13.5% & 12.5%)

The Takeaway
Breast imaging has become one of the AI use cases with the most potential, based on recent studies like PERFORMS and MASAI, and the new study shows Mirai could be useful in directing women to breast MRI screening. Like the previous studies, the current research is pointing to a near-term future in which AI and deep learning can make breast screening more accurate and cost-effective than it’s ever been before. 

Building a Mobile Lung Cancer CT Screening Program

The number of patients eligible for low-dose CT lung cancer screening has expanded, and so has the need to reach at-risk patients closer to where they live. That’s why Siemens Healthineers’ Mobile Lung Screening Solution combines the quality, ease of use, and flexibility needed to create a program that meets the real-life needs of your community.

A Comprehensive CVIS for Cardiology Imaging

Healthcare providers need to access and manage patient cardiovascular data from anywhere at any time. Learn how the Merge Cardio cardiovascular imaging system (CVIS) from Merge by Merative makes it possible.

The Wire

• Screening Foes Attack USPSTF: After years of holding up the USPSTF as the authority on cancer screening, screening foes are now criticizing the group for its decision in May to lower the starting age for mammography screening to age 40. In an opinion article in NEJM, the critics question whether the USPSTF’s statistical modeling justifies the change in guidelines, and question whether screening has had anything to do with the steady decline in breast cancer mortality in women under 50 over the past 30 years.

• Radiology Misses Burnout List: Finally, some good news on burnout in radiology … sort of. The field was not one of six medical specialties in a list compiled by AMA as having the highest rates of burnout based on a survey of 13k providers from 70 health systems in 30 states. The specialties and their burnout rates included emergency medicine (62%), hospital medicine (59%), family medicine (58%), pediatrics (55%), obstetrics and gynecology (54%), and internal medicine (52%). On the other hand, another recent study pegged radiology’s burnout rate at 54%.

• CT Perfusion Savings: A new study in European Radiology suggests CT perfusion (CTP) scans of patients with suspected acute ischemic stroke can be cost-effective by directing those with large vessel occlusion to endovascular therapy. Dutch researchers performed CTP scans on 701 patients who also got non-contrast CT and CTA; adding CTP reduced costs (-€2,671 per patient) and had a net positive monetary benefit (-€8,436). Given 2.4k patients annually get endovascular therapy in the Netherlands, the annual savings would be €9.1M. 

• Deep Learning for Brain CT: Annalise.ai’s Enterprise CTB deep learning algorithm helped radiologists read non-contrast brain CT exams in a study in European Radiology. A group of 32 radiologists used Enterprise CTB to review 2.8k scans for 144 possible clinical findings. Radiologist AUC performance improved for 91 of the findings, with accuracy improving 32% overall and AUC rising as much as 0.19 for some indications. Use of the model even reduced reading time by a mean of 27 seconds or 11%.

• AI-Based App Cuts Stroke Mortality: The Viz.AI LVO AI software for identifying large vessel occlusion (LVO) on CT scans and coordinating subsequent stroke care via mobile app had a dramatic effect on patient management in a new study in JAMA Neurology. Texas researchers used Viz.AI LVO in 243 patients at four stroke centers from January 2021 to February 2022; during the period in which the app was used, researchers saw lower patient mortality rates (13% vs. 31%) and a 12% reduction in door-to-groin time (88 vs. 100 minutes). 

• Is Ultrasound Poised to Rebound? A new market analysis by Signify Research predicts that the global ultrasound market will finish 2023 strong as it works through supply chain and macroeconomic issues that held it back in 2022. Signify sees government initiatives driving growth in Western Europe, while the US market slowed in early 2023 on delayed orders; the FDA’s new breast density rules may drive future growth. Purchasing in China is returning after a lengthy COVID-19 lockdown, but the slowing Chinese economy could affect long-term growth.

• GE Lands $44M AI Ultrasound Grant: GE HealthCare has been awarded a $44M grant from the Bill & Melinda Gates Foundation to develop AI technology for ultrasound. The grant is targeted at creating user-friendly AI-assisted tools for use in low- and middle-income countries that will help healthcare professionals without specialized training in ultrasound perform scans, with a focus on maternal and fetal care as well as in pediatric lung health. Leading the research will be Caption Health, the ultrasound AI company that GE acquired earlier in 2023. 

• Specialists Order Low-Value Imaging: Specialists tend to order a higher share of low-value medical care than primary care physicians (PCPs) – especially for medical imaging. In JAMA Network Open, researchers analyzed claims for 10.9M Medicare beneficiaries from 2016-2018, finding that specialists’ share of spending versus PCPs was higher than their share of service volume overall (57% vs. 29%) and for 28 of 40 services. Specialists’ share of spending was particularly high for emergency head CT for dizziness (76%), head CT for hearing loss (73%), and CAC scoring for known CAD (73%). 

• AI for Chest X-Ray Agrees with Rads: Qure’s qXR AI algorithm for chest X-rays showed high agreement with radiologist interpretations of COVID-19 pneumonia patients. In Journal of Advances in Radiology and Medical Imaging, researchers from UAE and the US found that in 535 radiographs of 100 patients from March to June 2020, qXR V2.1’s analysis showed high agreement with radiologists across different patient characteristics, with sensitivity of 0.88. The findings confirm qXR’s ability to predict disease status, especially where access to radiologists is limited.

• SNMMI Gives V/Q Green Light: With the COVID-19 public health emergency over, SNMMI said that it’s now safe for nuclear medicine practices to perform lung ventilation/perfusion (V/Q) scans. SNMMI in March 2020 raised concerns that aerosols released from V/Q scans could pose an infection risk to patients and healthcare personnel, and many facilities stopped conducting them. The group updated the guidance several times and now advises that V/Q scans are safe to perform assuming local and institutional guidelines and procedures are followed.

• Clearpath Adds Automation: Clearpath Technologies has added automation technology to PatientConnect and ProviderConnect, its solutions enabling healthcare providers to share medical records and images with patients. The applications were developed to eliminate CDs for exchanging medical data, and enable patients to request records and images from any provider using the web or iOS and Android apps. The solutions can integrate with a facility’s EHR, PACS, or other information system, and can automatically forward images to patients and providers within minutes of report completion. Clearpath made its corporate debut at SIIM 2023. 

• AI Firm HOPPR Taps Siddiqui: AI startup HOPPR has bolstered its executive lineup by hiring radiologist and imaging informatics pioneer Khan Siddiqui, MD, as CEO. Siddiqui previously served in executive roles at Hyperfine, Higi, and Microsoft; at HOPPR he will direct the company’s efforts to create “GPT-4 for medical imaging” by developing a foundational platform that enables developers to build AI models for medical imaging. The company plans to discuss use cases for its technology at RSNA 2023. 

• Just Say Ohm: We don’t totally understand all of the details in this paper, but it sure sounds cool. Researchers from Australia performed ultra-high-field 7T functional MRI scans on 10 people while they meditated to gain insights into their brain activity. The researchers wrote in Brain Research Bulletin that 7T fMRI showed that meditation deactivated the brain’s default-mode network, which could reduce mind-wandering and spontaneous thought during meditation. Research subjects also showed higher levels of mind-body awareness for up to two weeks after the scans. 

Why Data Standardization for Medical Imaging?

Data standardization has emerged as a key issue for both clinical and research aspects of medical imaging. Learn about its pivotal role in healthcare in this Enlitic webinar on October 25 featuring radiologist Cheryl Petersilge, MD, founder and CEO of Vidagos. 

Leveraging Pediatric Imaging AI

Check out this Blackford Analysis white paper detailing how children’s hospital imaging teams can leverage AI to improve modality throughput and imaging device availability.

How Imaging Partners of OC Eliminated CDs

Imaging Partners of Orange County was using CD-ROMs to share with patients many of the over 70,000 imaging exams they perform annually. Find out how PocketHealth helped them eliminate CDs and provide a better patient experience.

The Resource Wire

• A new platform from Clearpath now enables healthcare providers to delight their patients by sharing images and medical records digitally. Find out how it integrates simply into your practice. 

• See how AI and the cloud combine to alleviate IT challenges and amplify radiologist performance in this Tempus Radiology white paper.

• Join the conversation in this webinar recording and hear from PACS administrator Griff R. Van Dusen of Memorial Health System how Nuance PowerScribe One’s next-generation reporting experience helps streamline workflow and improve report quality so radiologists can get more done in less time. 

• Clinical burnout is widespread in healthcare. What can be done to combat burnout in imaging? Listen to Sonia Gupta, MD, of Change Healthcare as she addresses the concerns and offers possible solutions that you can use right now.

• Riverain Technologies’ ClearRead technology is the first FDA-cleared Clear Visual Intelligence (CVI) system that improves both detection and reading time for lung abnormalities. Learn more in this article. 

• New technology from Us2.ai called Us2.connect allows you to add echo AI automation to any echo device. Any echo machine can now have 100% automated reporting with disease detection and editable measurements – all generated in realtime as you scan.

• Teleradiology can be a force multiplier in radiology. Join Daniel Corbett and Daniel Arnold on September 27 for a webinar exploring the pros, cons, and essential factors for private practice leaders considering teleradiology integration, hosted by Medality.

• Knowing an individual’s mammographic breast density is key to understanding their risk for cancer. A new article from Visage Imaging explains how an AI-based solution can improve breast density assessment. 

• GE HealthCare has developed Effortless Workflow to streamline the entire CT process with technologies like AI and deep learning and provide a seamless scanning experience. Learn more in this November 9 webinar.

• Join us on September 25 for the final installment in a series of #RadEqual webinars hosted by Intelerad on overcoming the mid-career stall. Hear from Jennifer Harvey, MD, and Maureen Kohli, MD, as they discuss strategies to guide your career and find your circle of influence. 

• As a radiologist, have you ever wanted a second opinion? Now picture receiving a unified assessment from 140+ expert radiologists – that’s what you get from the Annalise.ai Enterprise AI solution. Discover how Annalise.ai can serve as your second reader.

• What’s the latest on the ongoing collaboration between Bayer and Blackford Analysis? Get an update from Bayer’s Thanos Karras and Blackford’s Ben Panter in this video interview from SIIM 2023. 

• Because of United Imaging’s Software Upgrades for Life program, every time United Imaging launches a new solution it can automatically be installed in every compatible system at no cost.

• When it began implementing its AimSG nationwide AI program, Singapore’s Synapxe health technology agency relied on the CARPL.ai platform to make everything work. Learn more in this article. 

• Synthetic imaging is poised to reshape medical imaging with dramatically faster image acquisition. Learn how Subtle Medical’s SubtleSYNTH software will revolutionize the MRI experience in this September 21 webinar.