Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2023 Feb 25;40(1):60-69.
doi: 10.7507/1001-5515.202208045.

[Hepatocellular carcinoma segmentation and pathological differentiation degree prediction method based on multi-task learning]

[Article in Chinese]
Han Wen  1   2 , Ying Zhao  3 , Yong Yang  1   2 , Hongkai Wang  4   5 , Ailian Liu  3   5 , Yu Yao  1   2 , Zhongliang Fu  1   2
Affiliations

[Hepatocellular carcinoma segmentation and pathological differentiation degree prediction method based on multi-task learning]

[Article in Chinese]
Han Wen et al. Sheng Wu Yi Xue Gong Cheng Xue Za Zhi. .

Abstract
in English, Chinese

Hepatocellular carcinoma (HCC) is the most common liver malignancy, where HCC segmentation and prediction of the degree of pathological differentiation are two important tasks in surgical treatment and prognosis evaluation. Existing methods usually solve these two problems independently without considering the correlation of the two tasks. In this paper, we propose a multi-task learning model that aims to accomplish the segmentation task and classification task simultaneously. The model consists of a segmentation subnet and a classification subnet. A multi-scale feature fusion method is proposed in the classification subnet to improve the classification accuracy, and a boundary-aware attention is designed in the segmentation subnet to solve the problem of tumor over-segmentation. A dynamic weighted average multi-task loss is used to make the model achieve optimal performance in both tasks simultaneously. The experimental results of this method on 295 HCC patients are superior to other multi-task learning methods, with a Dice similarity coefficient (Dice) of (83.9 ± 0.88)% on the segmentation task, while the average recall is (86.08 ± 0.83)% and an F1 score is (80.05 ± 1.7)% on the classification task. The results show that the multi-task learning method proposed in this paper can perform the classification task and segmentation task well at the same time, which can provide theoretical reference for clinical diagnosis and treatment of HCC patients.

肝细胞癌（HCC）是最常见的肝脏恶性肿瘤，其中HCC分割和病理分化程度预测是手术治疗和预后评估过程中的两个重要任务。现有方法通常独立地解决这两个问题，没有考虑两个任务的相关性。本文提出了一种多任务学习模型，旨在同时完成分割任务和病理分化程度分类任务。本文所提模型由分割子网和分类子网构成：在分类子网中提出了一种多尺度特征融合方法来提高分类精度；在分割子网中设计了一种边界感知注意力，用于解决肿瘤过分割问题。本文采用动态权重平均多任务损失，使模型在两个任务中同时获得最优的性能。研究结果显示，本文方法在295例HCC患者上的实验结果均优于其它多任务学习方法，在分割任务上戴斯相似系数（Dice）为（83.9 ± 0.88）%，同时在分类任务上的平均召回率为（86.08 ± 0.83）%，F1分数为（80.05 ± 1.7）%。该结果表明，本文提出的多任务学习方法能够同时较好地完成分类任务和分割任务，可为HCC患者的临床诊断和治疗提供理论参考。.

Keywords: Classification; Deep learning; Hepatocellular carcinoma; Multi-task learning; Segmentation.

PubMed Disclaimer

Conflict of interest statement

利益冲突声明：本文全体作者均声明不存在利益冲突。

Figures

图 1
图 1
Structure diagram of multi-task learning model 多任务学习模型结构图
图 2
图 2
Structure diagram of boundary-aware attention module 边界感知注意力模块结构图
图 3
图 3
Loss convergence graphs for segmentation task and classification task 分割任务和分类任务的损失收敛图
图 4
图 4
This paper uses Grad-CAM to visualize the feature map of stage5 in the model 本文采用Grad-CAM对模型中stage5的特征图可视化
图 5
图 5
Visualization of segmentation results for different multi-task learning methods 不同多任务学习方法的分割结果可视化图
图 6
图 6
Test set classification accuracy curves of feature fusion at different scales 不同尺度特征融合的测试集分类精度曲线
See this image and copyright information in PMC

Similar articles

See all similar articles

References

    1. Bray F, Ferlay J, Soerjomataram I, et al Global cancer statistics 2018: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA: a Cancer Journal for Clinicians. 2018;68(6):394–424. doi: 10.3322/caac.21492. - DOI - PubMed
    1. El–Serag H B, Rudolph K L Hepatocellular carcinoma: epidemiology and molecular carcinogenesis. Gastroenterology. 2007;132(7):2557–2576. doi: 10.1053/j.gastro.2007.04.061. - DOI - PubMed
    1. Yang D W, Jia X B, Xiao Y J, et al Noninvasive evaluation of the pathologic grade of hepatocellular carcinoma using MCF-3DCNN: a pilot study. BioMed research international. 2019;2019:9783106. - PMC - PubMed
    1. Valanarasu J M J, Sindagi V A, Hacihaliloglu I, et al KiU-Net: overcomplete convolutional architectures for biomedical image and volumetric segmentation. IEEE Transactions on Medical Imaging. 2022;41(4):965–976. doi: 10.1109/TMI.2021.3130469. - DOI - PubMed
    1. Oktay O, Schlemper J, Folgoc L L, et al Attention U-net: learning where to look for the pancreas. arXiv preprint. 2018;arXiv:1804.03999.

Publication types

LinkOut - more resources