Artificial intelligence (AI) software developer Optellum said it will showcase a prototype of its deep learning-based lung nodule risk stratification software at this week's World Congress of Thoracic Imaging (WCTI) in Boston.
The AI software is designed to help radiologists and pulmonologists in managing patients with nodules detected incidentally or at lung cancer screening. It assesses chest CT studies and other patient metadata to provide an objective quantitative score related to the malignancy of a nodule, according to the U.K.-based company. In collaboration with partners at the University of Oxford, the software was trained and tested on curated databases that included thousands of patients with nodules and ground-truth outcomes, Optellum said.
The technology won the 2015 LungX automatic nodule classification challenge sponsored by the U.S. National Cancer Institute, according to the company. Optellum is currently preparing a multicenter, prospective study to validate the performance of the software.
![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)
