Learning with Explicit Shape Priors for Medical Image Segmentation
Abstract: Medical image segmentation is a fundamental
task for medical image analysis and surgical planning. In
recent years, UNet-based networks have prevailed in the
field of medical image segmentation. However, convolu-
tional neural networks (CNNs) suffer from limited receptive
fields, which fail to model the long-range dependency of
organs or tumors. Besides, these models are heavily de-
pendent on the training of the final segmentation head.
And existing methods can not well address aforemen-
tioned limitations simultaneously. Hence, in our work, we
proposed a novel shape prior module (SPM), which can
explicitly introduce shape priors to promote the segmenta-
tion performance of UNet-based models. The explicit shape
priors consist of global and local shape priors. The for-
mer with coarse shape representations provides networks
with capabilities to model global contexts. The latter with
finer shape information serves as additional guidance to
relieve the heavy dependence on the learnable prototype
in the segmentation head. To evaluate the effectiveness of
SPM, we conduct experiments on three challenging public
datasets. And our proposed model achieves state-of-the-art
performance. Furthermore, SPM can serve as a plug-and-
play structure into classic CNNs and Transformer-based
backbones, facilitating the segmentation task on different
datasets. Source codes are available at https://github.
com/AlexYouXin/Explicit-Shape-Priors.
Loading