Residential College | false |
Status | 已發表Published |
Boundary-Sensitive Loss Function with Location Constraint for Hard Region Segmentation | |
Jie Du1; Kai Guan1; Peng Liu2; Yuanman Li3![]() | |
2022-11-15 | |
Source Publication | IEEE Journal of Biomedical and Health Informatics
![]() |
ISSN | 2168-2194 |
Volume | 27Issue:2Pages:992-1003 |
Abstract | In computer-aided diagnosis and treatment planning, accurate segmentation of medical images plays an essential role, especially for some hard regions including boundaries, small objects and background interference. However, existing segmentation loss functions including distribution-, region- and boundary-based losses cannot achieve satisfactory performances on these hard regions. In this paper, a boundary-sensitive loss function with location constraint is proposed for hard region segmentation in medical images, which provides three advantages: i) our Boundary-Sensitive loss (BS-loss) can automatically pay more attention to the hard-to-segment boundaries (e.g., thin structures and blurred boundaries), thus obtaining finer object boundaries; ii) BS-loss also can adjust its attention to small objects during training to segment them more accurately; and iii) our location constraint can alleviate the negative impact of the background interference, through the distribution matching of pixels between prediction and Ground Truth (GT) along each axis. By resorting to the proposed BS-loss and location constraint, the hard regions in both foreground and background are considered. Experimental results on three public datasets demonstrate the superiority of our method. Specifically, compared to the second-best method tested in this study, our method improves performance on hard regions in terms of Dice similarity coefficient (DSC) and 95% Hausdorff distance (95%HD) of up to 4.17% and 73% respectively. In addition, it also achieves the best overall segmentation performance. Hence, we can conclude that our method can accurately segment these hard regions and improve the overall segmentation performance in medical images. |
Keyword | Hard Region Segmentation Intra-class Imbalance Boundary Sensitive Loss Location Constraint |
DOI | 10.1109/JBHI.2022.3222390 |
URL | View the original |
Indexed By | SCIE |
Language | 英語English |
WOS Research Area | Computer Science ; Mathematical & Computational Biology ; Medical Informatics |
WOS Subject | Computer Science, Information systemsComputer Science, Interdisciplinary Applications;mathematical & Computational Biology;medical Informatics |
WOS ID | WOS:000967164200001 |
Publisher | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC445 HOES LANE, PISCATAWAY, NJ 08855-4141 |
Scopus ID | 2-s2.0-85142820548 |
Fulltext Access | |
Citation statistics | |
Document Type | Journal article |
Collection | Faculty of Science and Technology DEPARTMENT OF COMPUTER AND INFORMATION SCIENCE |
Corresponding Author | Yuanman Li |
Affiliation | 1.NationalRegional Key Technology Engineering Laboratory for Medical Ultrasound, Guangdong Key Laboratory for Biomedical Measurements and Ultrasound Imaging, School of Biomedical Engineering, Health Science Center, Shenzhen University, Shenzhen 518060, Chin 2.Department of Computer and Information Science, University of Macau, Macau SAR 999078, China 3.Guangdong Key Laboratory of Intelligent Information Processing, College of Electronics and Information Engineering, Shenzhen University, Shenzhen 518060, China |
Recommended Citation GB/T 7714 | Jie Du,Kai Guan,Peng Liu,et al. Boundary-Sensitive Loss Function with Location Constraint for Hard Region Segmentation[J]. IEEE Journal of Biomedical and Health Informatics, 2022, 27(2), 992-1003. |
APA | Jie Du., Kai Guan., Peng Liu., Yuanman Li., & Tianfu Wang (2022). Boundary-Sensitive Loss Function with Location Constraint for Hard Region Segmentation. IEEE Journal of Biomedical and Health Informatics, 27(2), 992-1003. |
MLA | Jie Du,et al."Boundary-Sensitive Loss Function with Location Constraint for Hard Region Segmentation".IEEE Journal of Biomedical and Health Informatics 27.2(2022):992-1003. |
Files in This Item: | There are no files associated with this item. |
Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.
Edit Comment