Follow-up diagnostic imaging and biopsy procedures performed on patients with suspicious findings on screening mammography amounted to an annual cost of nearly $8 billion, according to an article being highlighted by optoacoustic imaging firm Seno Medical Instruments and published March 26 in ClinicoEconomics and Outcomes Research.
Seno Chief Medical Officer Dr. Thomas Stavros and researchers from IBM Watson Health reviewed the medical claims for female breast imaging and diagnostic procedures submitted to MarketScan Commercial and Medicare Databases between 2011 and 2015.
Among more than 870,000 patients who underwent screening mammography, 49.4% had a second diagnostic procedure, 20.1% had a third procedure, and 10% had a fourth procedure. The various follow-up exams these patients underwent included diagnostic mammography (53.3% of patients), breast ultrasound (42.4%), and biopsy (10.3%).
On average, the annual total cost was $3.05 billion for diagnostic mammograms (at an average cost of $349 per exam), $920 million for breast ultrasound (average cost of $132), and $3.07 billion for biopsy (average cost of $1,938).
Based on reports from the U.S. National Cancer Institute (NCI) estimating a false-positive breast biopsy rate of approximately 71%, as much as $2.18 billion in biopsy procedures could potentially have been avoided, according to Seno.













![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)





