Dear AuntMinnie.com Member,
Advocates for beginning annual breast cancer screening in women at the age of 40 now have even more evidence to support their position.
After assessing four different screening scenarios using the Cancer Intervention and Surveillance Modeling Network (CISNET) 2023 median estimates of breast cancer screening outcomes, researchers found that commencing annual screening at that age and continuing to at least age 79 yielded the highest reduction in mortality with minimal risks. Our report, which includes a video interview with lead author Debra Monticciolo, MD, from Dartmouth, was our most highly viewed article this week. You can get all of the details by clicking here.
Our second-most highly viewed story covered research that could potentially pave the way for better care of depressed patients. Functional and structural brain MRI measures showed significant alterations in patients among most lifetime depression patient groups.
Speaking of the brain, a recent case report highlighted the potential for brain PET AI technology. The researchers reported that their deep-learning model had spotted a previously undetected glioblastoma. They believe this incidental finding demonstrates the promise of AI-based decision support for patient management.
AI was also the theme for two other popular stories this week. Deep learning-accelerated brain MRI was found to improve detection of acute ischemic lesions, according to a German team. Meanwhile, another group concluded that a deep learning-based approach could improve clinical strategies for managing ultrasound BI-RADS 4A lesions.
Sustainability is becoming an increasingly important topic in radiology. In a new video interview, John Scheel, MD, PhD, of Vanderbilt University, discussed how radiology can play a key role in the health of the planet.
See the full list below of our most popular stories of the week:
- Annual breast cancer screening starting at age 40 saves lives
- MRI reveals functional brain alterations associated with depression
- AI spots unidentified brain tumor on PET imaging
- Deep-learning accelerated brain MRI improves stroke lesion detection
- Deep learning distinguishes benign from malignant BI-RADS 4A lesions
- Radiology can play a key role in planetary health
- Cancer incidence during pandemic was lower than expected
- Women in healthcare experience higher burnout than male peers
- Researcher outlines radiation oncology workforce challenges
- Mortgage discrimination tied to breast cancer outcomes
- Surgeons urged to screen for osteoporosis in THA patients
- PCCT improves assessment of coronary artery disease
- Hyperfine to bring Swoop system to All-Star weekend
- False claims case highlights risky payment arrangements

![A normal mammogram confirmed by three-year radiologic follow-up illustrates reader-marked regions of interest (ROIs) during (A) unaided (round 1) and (B) artificial intelligence (AI)–assisted (round 2) reading. Each colored dot represents an ROI for recall by a human reader. Readers could mark more than one ROI per case, represented by multiple dots of the same color. During AI-assisted reading, the AI system displayed three visible prompts: two with suspicion of malignancy scores of 35% (left mediolateral oblique [L MLO] and craniocaudal [L CC]) and one with a suspicion of malignancy score of 10% (right craniocaudal [R CC]), shown as polygonal overlays. Without AI, six of 10 readers (60%) marked a false-positive ROI. With AI assistance, this fell to two of 10 (20%). R MLO = right mediolateral oblique.](https://img.auntminnie.com/mindful/smg/workspaces/default/uploads/2026/07/2026-07-14-radiology-mammogram-ai-auto-bias.H0bYO8QlWs.jpg?auto=format%2Ccompress&fit=crop&h=100&q=70&w=100)






![A normal mammogram confirmed by three-year radiologic follow-up illustrates reader-marked regions of interest (ROIs) during (A) unaided (round 1) and (B) artificial intelligence (AI)–assisted (round 2) reading. Each colored dot represents an ROI for recall by a human reader. Readers could mark more than one ROI per case, represented by multiple dots of the same color. During AI-assisted reading, the AI system displayed three visible prompts: two with suspicion of malignancy scores of 35% (left mediolateral oblique [L MLO] and craniocaudal [L CC]) and one with a suspicion of malignancy score of 10% (right craniocaudal [R CC]), shown as polygonal overlays. Without AI, six of 10 readers (60%) marked a false-positive ROI. With AI assistance, this fell to two of 10 (20%). R MLO = right mediolateral oblique.](https://img.auntminnie.com/mindful/smg/workspaces/default/uploads/2026/07/2026-07-14-radiology-mammogram-ai-auto-bias.H0bYO8QlWs.jpg?auto=format%2Ccompress&fit=crop&h=112&q=70&w=112)









