Optical breast imaging technology developer DOBI Medical International of Mahwah, NJ, will display its Dynamic Optical Breast Imaging (DOBI) ComfortScan system, a noninvasive adjunct device to mammography that instead of x-rays uses near-infrared light and gentle external pressure to detect the growth of new blood vessels (angiogenesis) in suspicious areas of the breast.
ComfortScan's high-intensity, light-emitting diodes send light through breast tissue, recording one image per second with a CCD camera for 45 seconds. If the light hits an angiogenic area, it is absorbed differently, and appears on the ComfortScan image in contrast to healthy tissue.
In June, DOBI increased its clinical trial sites for ComfortScan from 10 to 20. It also entered into a relationship with Bio-Imaging Technologies, a company that provides medical image management services for clinical trials. Bio-Imaging will manage clinical data in DOBI's final study module for ComfortScan.
In October, DOBI signed a research agreement with the Thayer School of Engineering at Dartmouth College in Hanover, NH, under which Dartmouth researchers will explore the best configuration to use ComfortScan for identifying tumor angiogenesis in the breast. DOBI expects to submit the final module for its premarket approval (PMA) application to the FDA in December.
By Kate Madden Yee
AuntMinnie.com contributing writer
November 7, 2005
Copyright © 2005 AuntMinnie.com
![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&dpr=2&fit=crop&h=167&q=70&w=250)
