A consortium consisting of artificial intelligence (AI) software developer Optellum and hospitals in the U.K., Netherlands, and Germany will present prototype software for diagnosing lung nodules at this week's International Association for the Study of Lung Cancer World Conference on Lung Cancer in Yokohama, Japan.
Developed by the consortium EIT Health LUCINDA (Early Lung Cancer Diagnosis with Artificial Intelligence and Big Data), the deep learning-based software was designed to improve management and reduce unnecessary follow-up procedures in patients with small, indiscriminate lung nodules on CT scans. After processing a chest CT scan, the software outputs an objective risk score of nodule malignancy based on a database of thousands of examples with known ground-truth diagnoses, according to Optellum. Clinicians can then stratify patients with lung nodules earlier -- potentially on the basis of only one or two CT studies, the company said.
The consortium has received funding from EIT Health, the European Union's initiative aimed at helping to bring healthcare innovation to market. In addition to Optellum, consortium members include: Oxford University Hospital and the University of Oxford in the U.K.; the University Medical Center Groningen in the Netherlands; and Heidelberg University Hospital & ThoraxKlinik Heidelberg in Germany.
![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)
