HemExp: Clinically-Guided Latent Diffusion for Modeling Hematoma Expansion
Researchers have developed HemExp, a novel latent diffusion model designed to predict hematoma expansion after spontaneous intracerebral hemorrhage. This model generates patient-specific follow-up non-contrast CT images and hemorrhage segmentations, conditioned on baseline imaging and clinical data. By simulating realistic clinical scenarios and estimating distributions of plausible follow-up hematoma volumes, HemExp aims to support uncertainty-aware decision-making in neurosurgical care. AI
IMPACT This model could improve clinical decision-making for patients with brain hemorrhages by providing more detailed and uncertainty-aware predictions.