AI predicts late breast cancer recurrence risk
A new multimodal AI model helps solve the agonizing clinical dilemma of whether breast cancer survivors should endure five extra years of hormone therapy.
July 18, 2026
Follow us
latest articles
Discover the newest research about AI innovations in 🖼️ Computer Vision.
Eye scans predict brain aging using AI
A new deep learning model bypasses expensive brain scans by reading signs of dementia and stroke directly from the back of the eye.
July 9, 2026
AI reads rapid tests using synthetic images
Training diagnostic AI no longer requires massive, expensive libraries of real patient photos.
July 8, 2026
AI improves heart calcium scoring on basic scans
A new machine learning method extracts high-quality heart disease risk data from low-dose scans that doctors usually ignore for calcium scoring.
July 6, 2026
AI tracks sleep disorder severity using video
A new study shows video foundation models can grade violent sleep movements, but their tendency to overestimate severity reveals the limits of clinical AI.
July 6, 2026
AI detects kidney disease using heart ultrasound videos
A new deep learning model spots chronic kidney disease using routine heart ultrasounds, bypassing the need for immediate blood work.
July 4, 2026
Text-image pairing improves brain tumor MRI classification
Adding radiology text to visual AI models stops them from failing when hyperparameters change.
July 3, 2026
AI analyzes entire endoscopy cases for gastric cancer
A new foundation model bypasses cherry-picked images to evaluate gastric cancer risk using every photo taken during an endoscopy.
July 3, 2026
AI spots heart ablation targets during normal rhythm
A new deep learning model can locate dangerous heart arrhythmia targets without needing to trigger the life-threatening rhythm first.
June 29, 2026
Impact on Cost and Expert Time of Data-Efficient Deep Learning for Medical Image Segmentation
A new human-in-the-loop training method proves that AI can slash the grueling hours radiologists spend labeling medical images without sacrificing clinical accuracy.
June 28, 2026