A research scientist with French artificial intelligence firm Therapixel has been named the winner of the Digital Mammography DREAM Challenge, an effort to use artificial intelligence to improve the accuracy of breast cancer detection and reduce patient recalls.
After four rounds of the competition, Yaroslav Nikulin won the top prize of $50,000 in the validation phase of the challenge. Nikulin wrote an algorithm that reduced the rate of false positives by 5% compared with the existing state of the art, according to the company.
The next phase of the challenge will begin in mid-June, with teams working together to improve the accuracy of breast cancer detection algorithms.
Therapixel is a spin-off from research institute Inria of France.
![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.auntminnieeurope.com/mindful/smg/workspaces/default/uploads/2026/07/2026-07-14-radiology-mammogram-ai-auto-bias.H0bYO8QlWs.jpg?auto=format%2Ccompress&dpr=2&fit=crop&h=167&q=70&w=250)
