Lesion segmentation method for multiple types of liver cancer based on balanced dice loss
Medical Physics · 2025
DOI: 10.1002/mp.17624 ↗Kurz gefasst
Fachartikel in der Zeitschrift Medical Physics, 2025. Verfasst von Jun Xie und 10 weiteren Autor:innen. Beteiligte Einrichtung: Information Technology Center, West China Hospital of Sichuan University, Chengdu, China. Hauptthemen laut MEDLINE: Liver Neoplasms, Image Processing, Computer-Assisted. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: West China Hospital, Sichuan University, The Municipal Goverment of Quzhou.
Abstract (Originalsprache)
Background
Obtaining accurate segmentation regions for liver cancer is of paramount importance for the clinical diagnosis and treatment of the disease. In recent years, a large number of variants of deep learning based liver cancer segmentation methods have been proposed to assist radiologists. Due to the differences in characteristics between different types of liver tumors and data imbalance, it is difficult to train a deep model that can achieve accurate segmentation for multiple types of liver cancer.
Purpose
In this paper, We propose a balance Dice Loss(BD Loss) function for balanced learning of multiple categories segmentation features. We also introduce a comprehensive method based on BD Loss to achieve accurate segmentation of multiple categories of liver cancer. Materials and methods We retrospectively collected computed tomography (CT) screening images and tumor segmentation of 591 patients with malignant liver tumors from West China Hospital of Sichuan University. We use the proposed BD Loss to train a deep model that can segment multiple types of liver tumors and, through a greedy parameter averaging algorithm (GPA algorithm) obtain a more generalized segmentation model. Finally, we employ model integration and our proposed post‐processing method, which leverages inter‐slice information, to achieve more accurate segmentation of liver cancer lesions.
Results
We evaluated the performance of our proposed automatic liver cancer segmentation method on the dataset we collected. The BD loss we proposed can effectively mitigate the adverse effects of data imbalance on the segmentation model. Our proposed method can achieve a dice per case (DPC) of 0.819 (95%CI 0.798–0.841), significantly higher than baseline which achieve a DPC of 0.768(95%CI 0.740–0.796).
Conclusions
The differences in CT images between different types of liver cancer necessitate deep learning models to learn distinct features. Our method addresses this challenge, enabling balanced and accurate segmentation performance across multiple types of liver cancer.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Information Technology Center, West China Hospital of Sichuan University, Chengdu, China.
- Information Technology Center, People's Hospital of Sanya, Sanya, Hainan, China.
- School of Computer Science and Engineering, University of Electronic Science and technology of China, Chengdu, Sichuan, China.
- Quzhou Affiliated Hospital of Wenzhou Medical University, Quzhou People's Hospital, Quzhou, Zhejiang, China.
- Department of Radiology, West China Hospital, Sichuan University, Chengdu, Sichuan, China.
- Yangtze Delta Region Institute(Quzhou), University of Electronic Science and Technology of China, Quzhou, Zhejiang, China.
Förderung
- West China Hospital, Sichuan University
- The Municipal Goverment of Quzhou
Zitieren
APA
Xie, J., Zhou, J., Yang, M., Xu, L., Li, T., Jia, H., Gong, Y., Li, X., Song, B., Wei, Y., & Liu, M. (2025). Lesion segmentation method for multiple types of liver cancer based on balanced dice loss. Medical Physics. https://doi.org/10.1002/mp.17624
Vancouver
Xie J, Zhou J, Yang M, Xu L, Li T, Jia H, et al. Lesion segmentation method for multiple types of liver cancer based on balanced dice loss. Medical Physics. 2025. doi:10.1002/mp.17624
BibTeX
@article{Xie2025,
author = {Xie, Jun and Zhou, Jiajun and Yang, Meiyi and Xu, Lifeng and Li, Tongtong and Jia, Haoyang and Gong, Yu and Li, Xiansong and Song, Bin and Wei, Yi and Liu, Ming},
title = {Lesion segmentation method for multiple types of liver cancer based on balanced dice loss},
journal = {Medical Physics},
year = {2025},
doi = {10.1002/mp.17624}
}
EUVIMED