Frequency-Mixed Single-Source Domain Generalization for Medical Image Segmentation

Li, Heng1,3; Li, Haojin1,2; Zhao, Wei3,4; Fu, Huazhu5; Su, Xiuyun3,4; Hu, Yan2; Liu, Jiang1,2,3,6

10.1007/978-3-031-43987-2_13

2023

26th International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI)

0302-9743

1611-3349

978-3-031-43986-5

MEDICAL IMAGE COMPUTING AND COMPUTER ASSISTED INTERVENTION, MICCAI 2023, PT VI

14225

OCT 08-12, 2023

null,Vancouver,CANADA

GEWERBESTRASSE 11, CHAM, CH-6330, SWITZERLAND

SPRINGER INTERNATIONAL PUBLISHING AG

The annotation scarcity of medical image segmentation poses challenges in collecting sufficient training data for deep learning models. Specifically, models trained on limited data may not generalize well to other unseen data domains, resulting in a domain shift issue. Consequently, domain generalization (DG) is developed to boost the performance of segmentation models on unseen domains. However, the DG setup requires multiple source domains, which impedes the efficient deployment of segmentation algorithms in clinical scenarios. To address this challenge and improve the segmentation model's generalizability, we propose a novel approach called the Frequency-mixed Single-source Domain Generalization method (FreeSDG). By analyzing the frequency's effect on domain discrepancy, FreeSDG leverages a mixed frequency spectrum to augment the single-source domain. Additionally, self-supervision is constructed in the domain augmentation to learn robust context-aware representations for the segmentation task. Experimental results on five datasets of three modalities demonstrate the effectiveness of the proposed algorithm. FreeSDG outperforms state-of-the-art methods and significantly improves the segmentation model's generalizability. Therefore, FreeSDG provides a promising solution for enhancing the generalization of medical image segmentation models, especially when annotated data is scarce. The code is available at https://github.com/liamheng/Non-IID_Medical_Image_Segmentation.

Medical image segmentation single-source domain generalization domain augmentation frequency spectrum

第一 ; 通讯

英语

EI ; CPCI-S

Guangdong Basic and Applied Basic Research Foundation[2020A1515110286]

Computer Science ; Radiology, Nuclear Medicine & Medical Imaging

Computer Science, Artificial Intelligence ; Computer Science, Theory & Methods ; Radiology, Nuclear Medicine & Medical Imaging

WOS:001109635100013

Web of Science

1.Research Institute of Trustworthy Autonomous Systems, Southern University of Science and Technology, Shenzhen, China
2.Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen, China
3.Medical Intelligence and Innovation Academy, Southern University of Science and Technology, Shenzhen, China
4.Southern University of Science and Technology Hospital, Shenzhen, China
5.Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore, Singapore
6.Guangdong Provincial Key Laboratory of Brain-inspired Intelligent Computation, Southern University of Science and Technology, Shenzhen, China

Li, Heng,Li, Haojin,Zhao, Wei,et al. Frequency-Mixed Single-Source Domain Generalization for Medical Image Segmentation[C]. GEWERBESTRASSE 11, CHAM, CH-6330, SWITZERLAND:SPRINGER INTERNATIONAL PUBLISHING AG,2023.