ProtoSurv: prototype-guided adaptation of computed tomography foundation model for lung-cancer prognosis prediction
Abstract Prognosis prediction is important for precision treatment in lung cancer. Chest computed tomography (CT) and deep learning are feasible approaches for learning imaging-based prognostic representations. However, prognostic labels are difficult to obtain because survival endpoints require long-term follow-up; th...
Chengcai Liu, Shitian Li, Haolin Sang et al.
· Visual Computing for Industr... · 0 citations