Researchers have developed EXACT, a novel foundation model designed for analyzing 3D chest CT scans. This model learns spatially resolved representations from paired CT scans and radiology reports, enabling it to not only diagnose diseases but also to localize abnormalities with interpretable visual evidence. EXACT was pre-trained on over 25,000 CT-report pairs, utilizing anatomy-aware weak supervision to learn organ segmentation and anomaly localization without manual voxel-level annotations. In evaluations, EXACT demonstrated significant improvements across various CT tasks, outperforming existing 3D medical foundation models. AI
Summary written by gemini-2.5-flash-lite from 2 sources. How we write summaries →
IMPACT Establishes a new paradigm for trustworthy volumetric medical AI by providing explainable voxel-level representations.
RANK_REASON The cluster describes a new research paper detailing a novel AI model for medical imaging analysis.