Scholarlink

In this paper, we present a practical approach to improve anatomical shape accuracy in whole-body medical segmentation. Our analysis shows that a shape-focused toolkit can enhance segmentation performance by over 8%—without the need for model re-training or fine-tuning. In comparison, modifications to model architecture typically lead to marginal gains of less than 3%. Motivated by this observation, we introduce ShapeKit, a flexible and easy-to-integrate toolkit designed to refine anatomical shapes. We evaluate our method on two large-scale, multi-institutional CT scan datasets with expert-verified annotations. This work highlights the underappreciated value of shape-based tools and calls attention to their potential impact within the medical segmentation community. ShapeKit is available at https://github.com/BodyMaps/ShapeKit .

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

ShapeKit

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Junqi Liu,
  • Dongli He,
  • Wenxuan Li,
  • Ningyu Wang,
  • Alan L. Yuille,
  • Zongwei Zhou

摘要

In this paper, we present a practical approach to improve anatomical shape accuracy in whole-body medical segmentation. Our analysis shows that a shape-focused toolkit can enhance segmentation performance by over 8%—without the need for model re-training or fine-tuning. In comparison, modifications to model architecture typically lead to marginal gains of less than 3%. Motivated by this observation, we introduce ShapeKit, a flexible and easy-to-integrate toolkit designed to refine anatomical shapes. We evaluate our method on two large-scale, multi-institutional CT scan datasets with expert-verified annotations. This work highlights the underappreciated value of shape-based tools and calls attention to their potential impact within the medical segmentation community. ShapeKit is available at https://github.com/BodyMaps/ShapeKit .