详情页 - 四川省肿瘤医院知识库

当前位置：首页 > 详情页

Lesion segmentation method for multiple types of liver cancer based on balanced dice loss

文献详情

资源类型：

Pubmed体系：

作者：

机构： [1]Information Technology Center, West China Hospital of Sichuan University, Chengdu, China. [2]Information Technology Center, People's Hospital of Sanya, Sanya, Hainan, China. [3]School of Computer Science and Engineering, University of Electronic Science and technology of China, Chengdu, Sichuan, China. [4]Quzhou Affiliated Hospital of Wenzhou Medical University, Quzhou People's Hospital, Quzhou, Zhejiang, China. [5]Department of Radiology, West China Hospital, Sichuan University, Chengdu, Sichuan, China. [6]Yangtze Delta Region Institute(Quzhou), University of Electronic Science and Technology of China, Quzhou, Zhejiang, China.

出处：

DOI：

ISSN：

关键词： deep learning imbalanced learning liver tumor segmentation

摘要：

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.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.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.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).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.© 2025 The Author(s). Medical Physics published by Wiley Periodicals LLC on behalf of American Association of Physicists in Medicine.

基金：

语种：

PubmedID：

中科院(CAS)分区：

出版当年[2025]版：

无

最新[2023]版：

大类 | 2 区医学

小类 | 3 区核医学

第一作者：

第一作者机构： [1]Information Technology Center, West China Hospital of Sichuan University, Chengdu, China. [2]Information Technology Center, People's Hospital of Sanya, Sanya, Hainan, China.

共同第一作者：

通讯作者：

通讯机构： [4]Quzhou Affiliated Hospital of Wenzhou Medical University, Quzhou People's Hospital, Quzhou, Zhejiang, China. [6]Yangtze Delta Region Institute(Quzhou), University of Electronic Science and Technology of China, Quzhou, Zhejiang, China.

推荐引用方式(GB/T 7714)：

APA：

MLA：

相关文献

[1]Multimodal deep learning approaches for precision oncology: a comprehensive review [2]Dwell locations and dwell time prediction of cervical cancer brachytherapy using 3D U-net [3]A Deep Learning-Based Radiomics Model for Prediction of Survival in Glioblastoma Multiforme [4]A novel deep learning segmentation model for organoid-based drug screening [5]Efficient application of deep learning-based elective lymph node regions delineation for pelvic malignancies [6]Deep learning based clinical target volumes contouring for prostate cancer: Easy and efficient application [7]Cross-modal deep learning model for predicting pathologic complete response to neoadjuvant chemotherapy in breast cancer [8]Predicting cutaneous malignant melanoma patients' survival using deep learning: a retrospective cohort study [9]Computer-aided Hepatocellular Carcinoma Analysis [10]Multimodality deep learning radiomics predicts pathological response after neoadjuvant chemoradiotherapy for esophageal squamous cell carcinoma