Task-Relevant Feature Replenishment for Cross-Centre Polyp Segmentation

Shen，Yutian1; Lu，Ye1; Jia，Xiao2; Bai，Fan1; Meng，Max Q.H.1,3

10.1007/978-3-031-16440-8_57

2022

25th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI)

0302-9743

1611-3349

978-3-031-16439-2

LECT NOTES ARTIF INT

13434 LNCS

599-608

SEP 18-22, 2022

null,Singapore,SINGAPORE

GEWERBESTRASSE 11, CHAM, CH-6330, SWITZERLAND

SPRINGER INTERNATIONAL PUBLISHING AG

Colonoscopy images from different centres usually exhibit appearance variations, making the models trained on one domain unable to generalize well to another. To tackle this issue, we propose a novel Task-relevant Feature Replenishment based Network (TRFR-Net) for cross-centre polyp segmentation via retrieving task-relevant knowledge for sufficient discrimination capability with style variations alleviated. Specifically, we first design a domain-invariant feature decomposition (DIFD) module placed after each encoding block to extract domain-shared information for segmentation. Then we develop a task-relevant feature replenishment (TRFR) module to distill informative context from the residual features of each DIFD module and dynamically aggregate these task-relevant parts, providing extra information for generalized segmentation learning. To further bridge the domain gap leveraging structural similarity, we devise a Polyp-aware Adversarial Learning (PPAL) module to align prediction feature distribution, where more emphasis is imposed on the polyp-related alignment. Experimental results on three public datasets demonstrate the effectiveness of our proposed algorithm. The code is available at: https://github.com/CathyS1996/TRFRNet.

Colonoscopy Domain adaptation Polyp segmentation

其他

英语

CPCI-S

National Key R&D Program of China[2019YFB1312400] ; Hong Kong RGC CRF[C4063-18G] ; Hong Kong RGC GRF[14211420]

Computer Science ; Radiology, Nuclear Medicine & Medical Imaging

Computer Science, Interdisciplinary Applications ; Radiology, Nuclear Medicine & Medical Imaging

WOS:000867306400057

2-s2.0-85139076762

Scopus

1.Department of Electronic Engineering,The Chinese University of Hong Kong,Sha Tin,Hong Kong
2.Department of Radiation Oncology,Stanford University,Stanford,United States
3.Department of Electronic and Electrical Engineering,The Southern University of Science and Technology,Shenzhen,China

Shen，Yutian,Lu，Ye,Jia，Xiao,et al. Task-Relevant Feature Replenishment for Cross-Centre Polyp Segmentation[C]. GEWERBESTRASSE 11, CHAM, CH-6330, SWITZERLAND:SPRINGER INTERNATIONAL PUBLISHING AG,2022:599-608.