German research organization Fraunhofer Institute for Digital Medicine (MEVIS) is presenting several artificial intelligence (AI) algorithms at the International Society for Optics and Photonics (SPIE) Medical Imaging conference this week in San Diego, California, U.S.
MEVIS researcher Hans Meine, PhD, will share how a deep-learning algorithm can achieve better image segmentation performance than traditional segmentation software. In addition, MEVIS researcher Jennifer Nitsch will describe how an algorithm for segmenting brain ultrasound images can support neurosurgeons during procedures; these ultrasound images could be used to adjust a patient's preoperative MRI scan to reflect new situations, according to the institute.
Another MEVIS researcher, Alessa Hering, will demonstrate a self-learning algorithm for image registration of lung tumors. Designed to support comparison of lung tumors over time by automatically aligning new and older images, the algorithm takes only 0.2 sec to perform -- a 40-fold faster performance over the 8 sec required by previous image registration software, Fraunhofer MEVIS said.
![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)
