Patcher: Patch Transformers with Mixture of Experts for Precise Medical Image Segmentation

Yanglan Ou (1), Ye Yuan (2), Xiaolei Huang (1), Stephen T.C. Wong (3), John Volpi (4), James Z. Wang (1), Kelvin Wong (3)

(1) The Pennsylvania State University, University Park, Pennsylvania, USA
(2) Carnegie Mellon University, Pittsburgh, Pennsylvania, USA
(3) TT and WF Chao Center for BRAIN & Houston Methodist Cancer Center, Houston Methodist Hospital, Houston, Texas, USA
(4) Eddy Scurlock Comprehensive Stroke Center, Department of Neurology, Houston Methodist Hospital, Houston, Texas, USA
Abstract:

We present a new encoder-decoder Vision Transformer architecture, Patcher, for medical image segmentation. Unlike standard Vision Transformers, it employs Patcher blocks that segment an image into large patches, each of which is further divided into small patches. Transformers are applied to the small patches within a large patch, which constrains the receptive field of each pixel. We intentionally make the large patches overlap to enhance intra-patch communication. The encoder employs a cascade of Patcher blocks with increasing receptive fields to extract features from local to global levels. This design allows Patcher to benefit from both the coarse-to-fine feature extraction common in CNNs and the superior spatial relationship modeling of Transformers. We also propose a new mixture-of-experts (MoE) based decoder, which treats the feature maps from the encoder as experts and selects a suitable set of expert features to predict the label for each pixel. The use of MoE enables better specializations of the expert features and reduces interference between them during inference. Extensive experiments demonstrate that Patcher outperforms state-of-the-art Transformer- and CNN-based approaches significantly on stroke lesion segmentation and polyp segmentation. Code for Patcher is released to facilitate related research.


Full Paper
(PDF, 10MB)

Source Codes
(GitHub)

More information


Citation: Yanglan Ou, Ye Yuan, Xiaolei Huang, Stephen T.C. Wong, John Volpi, James Z. Wang and Kelvin Wong, ``Patcher: Patch Transformers with Mixture of Experts for Precise Medical Image Segmentation,'' Proceedings of the International Conference on Medical Image Computing and Computer Assisted Interventions, Lecture Notes in Computer Science, vol. ??, ?? et al. (eds.), pp. ???-???b, Singapore, September 2022.

© 2022 MICCAI. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the MICCAI.

Last Modified: September 14, 2022
© 2022