Elongated Physiological Structure Segmentation via Spatial and Scale Uncertainty-Aware Network

Zhang, Yinglin1,2; Xi, Ruiling2; Fu, Huazhu4; Towey, Dave1; Bai, RuiBin1; Higashita, Risa2,3; Liu, Jiang1,2,3

10.1007/978-3-031-43901-8_31

2023

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

0302-9743

1611-3349

978-3-031-43900-1

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

14223

OCT 08-12, 2023

null,Vancouver,CANADA

GEWERBESTRASSE 11, CHAM, CH-6330, SWITZERLAND

SPRINGER INTERNATIONAL PUBLISHING AG

Robust and accurate segmentation for elongated physiological structures is challenging, especially in the ambiguous region, such as the corneal endothelium microscope image with uneven illumination or the fundus image with disease interference. In this paper, we present a spatial and scale uncertainty-aware network (SSU-Net) that fully uses both spatial and scale uncertainty to highlight ambiguous regions and integrate hierarchical structure contexts. First, we estimate epistemic and aleatoric spatial uncertainty maps using Monte Carlo dropout to approximate Bayesian networks. Based on these spatial uncertainty maps, we propose the gated soft uncertainty-aware (GSUA) module to guide the model to focus on ambiguous regions. Second, we extract the uncertainty under different scales and propose the multiscale uncertainty-aware (MSUA) fusion module to integrate structure contexts from hierarchical predictions, strengthening the final prediction. Finally, we visualize the uncertainty map of final prediction, providing interpretability for segmentation results. Experiment results show that the SSU-Net performs best on cornea endothelial cell and retinal vessel segmentation tasks. Moreover, compared with counterpart uncertainty-based methods, SSU-Net is more accurate and robust.

Uncertainty Medical Image Segmentation Elongated Physiological Structure Deep Learning

通讯

英语

EI ; CPCI-S

General Program of National Natural Science Foundation of China[82272086]

Computer Science ; Radiology, Nuclear Medicine & Medical Imaging

Computer Science, Software Engineering ; Computer Science, Theory & Methods ; Radiology, Nuclear Medicine & Medical Imaging

WOS:001109630700031

Web of Science

1.School of Computer Science, University of Nottingham Ningbo China, Ningbo; 315100, China
2.Research Institute of Trustworthy Autonomous Systems and Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen; 518055, China
3.Tomey Corporation, Nagoya; 451-0051, Japan
4.Institute of High Performance Computing (IHPC), Agency for Science, Technology and Research (A*STAR), Singapore, Singapore

Zhang, Yinglin,Xi, Ruiling,Fu, Huazhu,et al. Elongated Physiological Structure Segmentation via Spatial and Scale Uncertainty-Aware Network[C]. GEWERBESTRASSE 11, CHAM, CH-6330, SWITZERLAND:SPRINGER INTERNATIONAL PUBLISHING AG,2023.