
Artificial intelligence (AI) software developer Koios Medical is highlighting the results of a study that used its DS Breast 2.0 as a second opinion for analyzing and assessing lesions found during breast ultrasound examinations.
During an 18-month software evaluation period, radiologists at a private practice used Koios' software to assist in lesion classifications and risk assessments of about 6,000 diagnostic breast ultrasound exams. Radiologists would activate Koios DS and review the software findings with clinical details to formulate the best management plan.
The diagnostic performance of the physicians was compared with the 18-month period prior to the introduction of the AI-enabled software. It was determined that physicians recommended biopsy for suspicious lesions at a similar rate of 17% and performed 14% more biopsies, increasing the cancer detection rate while simultaneously experiencing a significant reduction in benign biopsies, according to a press release from Koios.
The aggregate nature of the findings when the company began gradually adopting the software during the evaluation period also was noteworthy. Trailing six-month results indicated a reduction in benign biopsies exceeding 20% across the group. Positive predictive value improved by about 20%, Koios stated.











![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)






