ShapeKit
This work addresses the need for better shape accuracy in medical segmentation, offering a practical tool for the medical imaging community, though it is incremental as it builds on existing segmentation methods.
The paper tackles the problem of anatomical shape accuracy in whole-body medical segmentation by introducing ShapeKit, a shape-focused toolkit that improves segmentation performance by over 8% without requiring model re-training or fine-tuning.
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. This work highlights the underappreciated value of shape-based tools and calls attention to their potential impact within the medical segmentation community.