Prototype-Guided Zero-Shot Medical Image Segmentation with Large Vision-Language Models

Building on advances in promptable segmentation models, this work introduces a framework that integrates Large Vision-Language Model (LVLM) bounding box priors with prototype-based region of interest (ROI) selection to improve zero-shot medical image segmentation. Unlike prior methods such as SaLIP,...

Бүрэн тодорхойлолт

Номзүйн дэлгэрэнгүй

Үндсэн зохиолчид:	Huong Pham, Samuel Cheng
Формат:	Artigo
Хэл сонгох:	Inglês
Хэвлэсэн:	MDPI AG 2025-10-01
Цуврал:	Applied Sciences
Нөхцлүүд:	bounding box estimation large vision-language model medical image segmentation prototype similarity Segment Anything Model zero-shot learning
Онлайн хандалт:	https://www.mdpi.com/2076-3417/15/21/11441
Шошгууд:	Шошго нэмэх Шошго байхгүй, Энэхүү баримтыг шошголох эхний хүн болох!