广东工业大学学报 ›› 2024, Vol. 41 ›› Issue (01): 34-40.doi: 10.12052/gdutxb.230007

• 智慧医疗 • 上一篇    下一篇

基于多任务循环神经网络带状回归模型的乳腺癌个体生存分析

陈睿1, 蔡念1, 罗智浩1, 刘璇2,3, 黎剑2,3   

  1. 1. 广东工业大学 信息工程学院, 广东 广州 510006;
    2. 中山大学肿瘤防治中心 华南肿瘤学国家重点实验室, 广东 广州 510060;
    3. 中山大学肿瘤防治中心 广东省恶性肿瘤临床医学研究中心, 广东 广州 510060
  • 收稿日期:2023-01-13 出版日期:2024-01-25 发布日期:2024-02-01
  • 通信作者: 蔡念(1976–)，男，教授，博士，主要研究方向为机器视觉、机器学习、数字信号处理等，E-mail：cainian@sina.com
  • 作者简介:陈睿(1998–)，男，硕士研究生，主要研究方向为机器学习、生存分析等
  • 基金资助:
    国家自然科学基金资助面上项目(82172019)；广州市科技计划项目(202102010251)

Individual Survival Analysis of Breast Cancer Based on Multi-task Recurrent Neural Network Banded Regression Model

Chen Rui1, Cai Nian1, Luo Zhi-hao1, Liu Xuan2,3, Li Jian2,3   

  1. 1. School of Information Engineering, Guangdong University of Technology, Guangzhou 510006, China;
    2. State Key Laboratory of Oncology in South China, Sun Yat-sen University Cancer Center, Guangzhou 510060, China;
    3. Guangdong Clinical Research Center for Cancer, Sun Yat-sen University Cancer Center, Guangzhou 510060, China
  • Received:2023-01-13 Online:2024-01-25 Published:2024-02-01

HTML

PDF (PC)

329

摘要： 针对乳腺癌病程长、疾病发展较缓和的特点，提出了一种多任务循环神经网络带状回归模型进行乳腺癌个体生存分析。首先，提出一种基于循环神经网络的多任务带状回归模型，通过识别各病理特征对不同患者之间影响的区别，优化患者个体生存分析。其次，对带状校验矩阵的形式进行拓展并研究其对患者风险分布的影响。最后，在乳腺癌真实数据集上进行生存分析，不同患者之间产生明显的差异性，验证了模型的有效性。在2个乳腺癌真实数据集上进行的生存分析结果显示，基于循环神经网络的多任务带状回归模型的一致性指数(Concordance Index, C-index)较医学上常用的Cox回归模型有较大提升，并有着更小的95%置信区间。

关键词: 乳腺癌, 个体生存分析, 循环神经网络, 多任务带状回归

Abstract: In view of the characteristics of long course and mild disease development of breast cancer, a multi-task recurrent neural network banded regression model is proposed to analyze individual survival of breast cancer. First, a multi-task banded regression model based on recurrent neural network is proposed to optimize the individual survival analysis of patients by identifying the difference in the effects of various pathological features on different patients. Then, the form of the banded check matrix is expanded and its effect on the hazard distribution of patient is investigated. Finally, the survival analysis on the real datasets of breast cancer shows obvious differences among different patients, which verifies the validity of the model. The survival analysis on two real datasets of breast cancer shows that the C-index of the multi-task banded regression model based on recurrent neural network is greatly improved compared with the Cox regression model commonly used in medicine, and has a smaller 95% confidence interval.

Key words: breast cancer, individual survival analysis, recurrent neural network, multi-task banded regression

中图分类号: 

  • TP391
[1] ZHOU X, LI C, RAHAMAN M M, et al. A comprehensive review for breast histopathology image analysis using classical and deep neural networks [J]. IEEE Access, 2020, 8: 90931-90956.
[2] ARNOLD M, MORGAN E, RUMGAY H, et al. Current and future burden of breast cancer: global statistics for 2020 and 2040 [J]. The Breast, 2022, 66: 15-23.
[3] LOH S Y, YIP C H. Breast cancer as a chronic illness: implications for rehabilitation and medical education [J]. Journal of Health and Translational Medicine, 2006, 9(2): 3-11.
[4] GEORGE B, SEALS S, ABAN I. Survival analysis and regression models [J]. Journal of Nuclear Cardiology, 2014, 21(4): 686-694.
[5] GANGGAYAH M D, TAIB N A, HAR Y C, et al. Predicting factors for survival of breast cancer patients using machine learning techniques [J]. BMC Medical Informatics and Decision Making, 2019, 19(1): 1-17.
[6] SCHOBER P, VETTER T R. Survival analysis and interpretation of time-to-event data: the tortoise and the hare [J]. Anesthesia and Analgesia, 2018, 127(3): 792.
[7] KATZMAN J L, SHAHAM U, CLONINGER A, et al. DeepSurv: personalized treatment recommender system using a Cox proportional hazards deep neural network [J]. BMC Medical Research Methodology, 2018, 18(1): 1-12.
[8] LEE C, YOON J, VAN DER SCHAAR M. Dynamic-deephit: a deep learning approach for dynamic survival analysis with competing risks based on longitudinal data [J]. IEEE Transactions on Biomedical Engineering, 2019, 67(1): 122-133.
[9] TANG W, MA J, MEI Q, et al. SODEN: a scalable continuous-time survival model through ordinary differential equation networks[J]. J Mach Learn Res, 2022, 23: 34: 1-34: 29.
[10] YU C N, GREINER R, LIN H C, et al. Learning patient-specific cancer survival distributions as a sequence of dependent regressors [J]. Advances in Neural Information Processing Systems, 2011, 24: 1845-1853.
[11] FOTSO S. Deep neural networks for survival analysis based on a multi-task framework[EB/OL]. arXiv: 1801.05512(2018-01-17) [2023-01-09]. https://doi.org/10.48550/arXiv.1801.05512.
[12] HU S, FRIDGEIRSSON E, VAN WINGEN G, et al. Transformer-based deep survival analysis[C]//Survival Prediction-Algorithms, Challenges and Applications. New York: PMLR, 2021: 132-148.
[13] 王慧恒, 蔡念, 陈睿, 等. 面向癌症个体生存分析的多任务带状回归模型[J]. 计算机工程与应用, 2023, 59(10): 299-305.
WANG H H, CAI N, CHEN R, et al. Multi-task banded regression model for individual cancer survival analysis [J]. Computer Engineering and Applications, 2023, 59(10): 299-305.
[14] MEDSKER L R, JAIN L C. Recurrent neural networks [J]. Design and Applications, 2001, 5: 64-67.
[15] WU Y, HALABI S. Interval censoring[M]. Boca Raton: Chapman and Hall/CRC, 2019: 493-508.
[16] BUHLMANN H, GISLER A. Credibility in the regression case revisited (A late tribute to Charles A. Hachemeister) [J]. ASTIN Bulletin: The Journal of the IAA, 1997, 27(1): 83-98.
[17] YE K, LIM L H. Every matrix is a product of toeplitz matrices [J]. Foundations of Compu-tational Mathematics, 2016, 16(3): 577-598.
[18] CURTIS C, SHAH S P, CHIN S F, et al. The genomic and transcriptomic architecture of 2000 breast tumours reveals novel subgroups [J]. Nature, 2012, 486(7403): 346-352.
[19] SCHUMACHER M, BASTERT G, BOJAR H, et al. Randomized 2×2 trial evaluating hormonal treatment and the duration of chemotherapy in node-positive breast cancer patients [J]. Journal of Clinical Oncology, 1994, 12(10): 2086-2093.
[20] ANTOLINI L, BORACCHI P, BIGANZOLI E. A time-dependent discrimination index for survival data [J]. Statistics in Medicine, 2005, 24(24): 3927-3944.
[21] KVAMME H, BORGAN Ø, SCHEEL I. Time-to-event prediction with neural networks and Cox regression[EB/OL]. arXiv: 1907.00825 (2019-09-13) [2023-01-09]. https://doi.org/10.48550/arXiv.1907.00825.
[1] 吴家湖, 熊华, 宗睿, 赵曜, 周贤中. 基于循环神经网络的目标转弯机动类型识别[J]. 广东工业大学学报, 2020, 37(02): 67-73.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
版权所有 © 2017 《广东工业大学学报》编辑部
地址：广州市东风东路729号广东工业大学 邮编：510090
电话：020-37626653,020-37626139,020-37626396
邮箱：xbzrb@gdut.edu.cn
本系统由北京玛格泰克科技发展有限公司设计开发