ZePT: Zero-Shot Pan-Tumor Segmentation via Query-Disentangling and Self-Prompting

arXiv:2312.04964v2 Announce Type: replace
Abstract: The long-tailed distribution problem in medical image analysis reflects a high prevalence of common conditions and a low prevalence of rare ones, which poses a significant challenge in developing a unified model capable of identifying rare or novel tumor categories not encountered during training. In this paper, we propose a new zero-shot pan-tumor segmentation framework (ZePT) based on query-disentangling and self-prompting to segment unseen tumor categories beyond the training set. ZePT disentangles the object queries …

abstract analysis arxiv challenge cs.cv distribution image low medical novel paper prompting query segmentation training type unified model via zero-shot