AI RESEARCH
Nodule-Aligned Latent Space Learning with LLM-Driven Multimodal Diffusion for Lung Nodule Progression Prediction
arXiv CS.CV
•
ArXi:2603.15932v1 Announce Type: new Early diagnosis of lung cancer is challenging due to biological uncertainty and the limited understanding of the biological mechanisms driving nodule progression. To address this, we propose Nodule-Aligned Multimodal (Latent) Diffusion (NAMD), a novel framework that predicts lung nodule progression by generating 1-year follow-up nodule computed tomography images with baseline scans and the patient's and nodule's Electronic Health Record (EHR). NAMD