Kathleen Costello, who was diagnosed with breast cancer in 2017 via supplemental breast ultrasound after years of negative mammograms.

The past year has seen major advances in the use of artificial intelligence (AI) for breast screening. But how is AI affecting the real-world practice of mammography? In this episode of The Imaging Wire Show, we talked to Onalisa Winblad, MD, of the University of Kansas Health System to hear her thoughts about AI for breast screening.

Imaging Wire Sponsors

Bayer  •  Blackford  •  CARPL.ai  •  Clearpath  •  DeepHealth  •  Enlitic  •  Gleamer  •  Intelerad  •  Medality  •  Merge by Merative  •  Nuance  •  PocketHealth  •  Riverain Technologies  •  Siemens Healthineers  •  SpinTech MRI  •  TeraRecon  •  United Imaging  •  Us2.ai  •  Visage Imaging

Breast Imaging

USPSTF’s Mammography Letdown?

Last year’s relief that the USPSTF would lower its recommended starting age for breast screening to 40 gave way to frustration this week that the group did not go farther in its final decision on mammography recommendations. 

In a series of papers in JAMA journals this week, the USPSTF tackled a range of breast screening issues, from the age at which screening should start to whether modalities like ultrasound and MRI should be used to supplement conventional mammography.

• The group telegraphed its position in May 2023, stating that it intended to reverse its controversial 2009 decision to raise the breast screening starting age from 40 to 50.

That was the good news. The bad news is that breast screening advocates mostly got shut out on a variety of other issues, with the USPSTF … 

• Advising that breast screening be conducted biennially (every two years), rather than annually as most women’s imaging advocates would prefer
• Declining to raise the recommended upper limit for screening from 74 to 79
• Declining to recommend supplemental screening with MRI or ultrasound for women with dense breast tissue, even as women express frustration with the lack of reimbursement for these exams

On the positive side, the USPSTF finally weighed in on DBT, stating that the 3D mammography technology is equivalent to digital mammography for breast screening. 

• But in another disappointment, the group said it couldn’t find any studies stating that DBT was better than 2D digital mammography. 

Given the fierce battles that have been fought over screening guidelines in the last 15 years, what made the USPSTF change its mind on mammography’s starting age? 

• One big factor is the 2% annual rise in breast cancer incidence in women in their 40s from 2015 to 2019; the higher mortality rates among Black women was another issue (see story below in The Wire).

The Takeaway

The USPSTF’s move to lower its recommended starting age for screening mammography is a welcome – if overdue – change for women, who for 15 years have borne the brunt of the group’s conservative approach to guideline formation. The question remains, is the USPSTF making the same mistake all over again when it comes to supplemental imaging and annual screening? And how long will women have to wait this time until it sees the light?

Unboxing AI Validation

Join CARPL.ai this month for “Unboxing AI,” a series of webinars on important topics in AI and radiology. The series starts on May 3 with a discussion of AI validation featuring Dr. Vasanth Venugopal.

Delighting Patients with Medical Image Sharing

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.

The Wire

• Do New Guidelines Go Far Enough? The USPSTF’s about-face is welcome news to breast imagers, but do the new guidelines go far enough? In JAMA Oncology, breast radiologist Wendie Berg, MD, PhD, takes issue with the group’s preference for biennial screening, and for keeping the upper screening limit at 74 rather than 79. Modeling studies have shown a higher mortality reduction with annual screening 40-79 compared to biennial screening 40-74 (42% vs. 28%). The USPSTF could also have done more to recommend supplemental screening in women with dense breast tissue.  

• New Guidelines and Health Equity: Another editorial, this one in JAMA, views the new guidelines as part of the USPSTF’s pursuit of health equity. Black women are 40% more likely to die of breast cancer, and cancer rates are rising among younger African American women. The USPSTF used modeling studies to determine that lowering the starting age to 40 would avert 1.8 additional deaths per 1k Black women screened every two years, meaning that Black women would receive more benefit from earlier screening than the general population. 

• Occupational Stress in Technologists: A new survey of occupational stress in radiologic technologists finds that the burden of work demands and lack of positive workplace relationships are among the biggest sources of stress for RTs on a list of six potential stress hazards. Researchers surveyed 864 RTs in a study in Journal of Radiation Research and Applied Sciences, finding lack of management support to be another problematic issue. The study was conducted in Saudi Arabia, but the results could just as well be extrapolated to the US. 

• FDA Clears United’s 5T MRI: Talk about good timing. Just as ISMRM 2024 is about to begin, United Imaging has received FDA clearance for its uMR Jupiter 5T MRI scanner. United revealed the system at ECR 2023, and the company sees 5T as a promising segment for whole-body imaging at a field strength more powerful than 3T but without the operating challenges of 7T. United Imaging said it has resolved historical challenges to ultra-high-field MRI related to image uniformity and radiofrequency safety. 

• Hologic to Buy UK Breast Surgery Firm: Hologic plans to further expand the treatment side of its breast care business with a $310M deal to acquire Endomagnetics, a UK developer of breast surgical technology. Endomag develops breast surgery localization and lymphatic tracing technology, including the Magseed magnetic tissue localization marker, Magtrace lymphatic tracing injectable, and Sentimag platform for localization and lymphatic tracing. Endomag generated $35M in 2023 revenue, and the company will be added to Hologic’s Breast Health portfolio. 

• CEM+DBT=Better Cancer Detection: In interim results from the TOCEM study in Radiology, researchers found that adding contrast-enhanced mammography to DBT improved cancer detection in women with a personal history of breast cancer. A radiologist interpreted scans of 1.3k women, finding more cancers per 1k women with CEM+DBT versus DBT alone (23 vs. 16). The difference narrowed in years 2 and 3 (7.6 vs. 3.8). Recall rates rose, but authors concluded that CEM+DBT could be a good supplemental screening tool. 

• Walmart Shutters Health Operation: Retail giant Walmart said this week it is closing its Walmart Health business, which provides healthcare services at 51 stores in the US, as well as virtual health services. Walmart cited “challenging reimbursement” and “escalating operating costs” as among the reasons for the shutdown – factors that might sound familiar to any healthcare provider. Walmart has been collaborating with RadNet to offer AI-enhanced MammographyNow breast screening at three sites; RadNet sources told The Imaging Wire the company does not expect any changes in the collaboration.

• Us2.ai’s Contrast Echo AI Correlations: JACC published what might be the first study evaluating the performance of AI-automated contrast echocardiography exams, finding that Us2.ai’s echo AI solution produced LV measurements with “good to excellent agreement” with human experts. Among 171 patients’ contrast echo exams, Us2.ai successfully measured 168 (98.2%) of the exams, while AI-calculated biplane LVEDV, LVESV, and LVEF demonstrated high correlations with human readers (ICC: 0.92, 0.95, 0.82).

• Falling Through Lung Screening’s Cracks: Why do people eligible for low-dose CT lung cancer screening never get scanned, even after they start the process? Stanford researchers examined this in Clinical Lung Cancer, based on a study of 380 people who had orders for LDCT screening in 2022. Those meeting USPSTF criteria had higher completion rates compared to those with occupational exposure or family lung cancer history (98% vs. 82%). Lower completion rates were also found in unmarried people (45% vs. 58%) as well as current smokers (42% vs. 49%).

• PocketHealth Launches Free Access: PocketHealth has launched a new service that gives patients in the US and Canada no-cost access to their medical imaging records. PocketHealth Basic lets patients access their imaging records and download diagnostic-quality images, while also supporting instant sharing with healthcare providers. Patients can add on additional features in PocketHealth’s paid plans, including Report Reader, MyCare Navigator, and Follow-Up Navigator. PocketHealth raised $33M in March. 

• Guidelines Reduce Pediatric CT: In a study of 28k children with either abdominal or head trauma, adhering to PECARN guidelines when working up patients could reduce unnecessary use of CT – and radiation exposure. In a study in The Lancet Child & Adolescent Health, US researchers said PECARN’s intra-abdominal injury rule had 100% accuracy for predicting if a child did not need a CT scan, while the traumatic brain injury rule was also 100% accurate in predicting unnecessary CT. Sensitivity levels were equally high. 

• AI Alliance Targets Chest X-Rays: AI developers Lunit and Radiobotics have signed a technology integration deal designed to expand the number of clinical findings that can be detected on chest X-rays. Lunit will distribute Radiobotics’ RBfracture AI solution for fracture detection on X-ray, which when used with Lunit’s own INSIGHT CXR application will give clinicians a full spectrum of AI-assisted screening tools from lung abnormalities to bone fractures. The deal will initially focus on the Europe, Middle East, and Africa region.

• UK to Build 11.7T MRI Scanner: A project to build an ultra-high-field 11.7T MRI scanner for human imaging at the University of Nottingham in the UK is moving ahead. University officials said they had selected Tesla Engineering to build the magnet and gradient coils, while Philips will provide additional hardware. The scanner will be used for clinical and neuroscience-focused research at the university’s Sir Peter Mansfield Imaging Centre, and will be equal in strength to the Iseult 11.7T scanner that’s gone into operation in France.

Get to Know DeepHealth

What’s the latest from DeepHealth? In this episode of the Imaging Wire Show, we talked to COO and CTO Sham Sokka about the company’s recent launch and their take on the value AI provides to radiology, especially for screening.

Visit United Imaging at ISMRM 2024

If you’re attending ISMRM 2024 in Singapore, be sure to visit United Imaging in booth A18 to explore their latest advances in MRI technology including a lunch symposium on Thursday May 9 on ultra-high-field MRI at 5T.

Starting a CT Lung Cancer Screening Program

There’s no doubt CT lung cancer screening reduces lung cancer mortality. In this Imaging Wire Show, we discuss how to set up a lung screening program and the technologies available to help with Chip Gilkeson, MD, of University Hospitals Cleveland Medical Center and Steve Worrell of Riverain Technologies.

The Resource Wire

• Clarity and Confidence in Mammography: Join this Medality webinar at 12 pm ET on Thursday May 2 to learn from Gretchen Green, MD, on how to maximize performance and minimize malpractice risk in mammography. Co-sponsored by the American Association for Women in Radiology. 

• What Does Improved MRI Efficiency Mean? There’s a growing need for practical, cost-effective solutions to improve efficiency in MRI and other modalities. Read this article from Karen Holzberger of SpinTech MRI and James Backstrom, MD, to learn how the company’s STAGE software can help. 

• Benchmarking AI – Building an AI Ecosystem: What are the best ways to deploy and optimize AI for radiology? Learn how by attending this May 8 webinar on the value of AI in healthcare, hosted by Bayer and featuring Lauren Nicola, MD, and James Blackwood. 

• AI Improves Radiologist Sensitivity for Fractures: Gleamer’s AI algorithm for detecting hand and wrist fractures on X-rays improved radiologist sensitivity in a recent clinical study – without affecting their specificity or positive predictive value. Find out how it worked on this page. 

• Nuance’s PIN Helps Identifies Emphysema: Emphysema is often underdiagnosed, and this can make treatment more difficult. FirstHealth of the Carolinas was able to improve its diagnosis of emphysema and enhance its CT lung screening service with AI algorithms available through Nuance Precision Imaging Network (PIN).

• Solutions to Support Breast Density Reporting: The FDA has ruled that healthcare providers must inform patients of their breast density status. Learn how Intelerad’s solutions can help mammography facilities comply with this new rule well ahead of this year’s deadline. 

• Prioritizing Efficiency in Healthcare IT: Health IT teams are bombarded with projects and initiatives aimed at improving patient care, and prioritizing projects can be a challenge. In this white paper from Enlitic, learn more about how to efficiently manage and prioritize the introduction of new technologies.

• Breast Density Classification – From Conception to Routine Use: Knowing an individual’s mammographic breast density is key to understanding their risk for cancer. This article from Visage Imaging explains how an AI-based solution can improve breast density assessment. 

• Fully Automated AI LV Assessment: Read how a new study showed that Us2.ai’s echo AI solution had good to excellent agreement between AI and experts’ assessments of LV volumes and ejection fraction in contrast echocardiograms.

• Enterprise Imaging on Your Terms: Meet your radiology, cardiology and all other imaging needs – on your own terms – with imaging solutions from Merge by Merative. Learn more about their award-winning solutions and request a demo today. 

• 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. 

• Are You Getting the Most Out of Your Image Exchange Solution? On this page from PocketHealth, ask yourself these 5 questions to find out whether your enterprise image exchange solution is maximizing patient satisfaction, efficiency and driving revenue.  

• 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. 

• Turning Medical Imaging into Great Medicine: Imaging precision is at the core of positive patient outcomes. Learn how the Intuition 4.7 advanced visualization solution from TeraRecon is powering better patient care across the spectrum.