计算机科学

计算机科学 ›› 2025, Vol. 52 ›› Issue (9): 4-15.doi: 10.11896/jsjkx.250100065

• 智能医学工程 • 上一篇    下一篇

机器学习在食管癌诊疗中的研究进展

王泳荃1, 苏梦琦2, 石清磊3,4, 马艺宁5, 孙扬帆5, 王昌淼4, 汪国有1, 袭肖明6, 尹义龙3, 万翔4   

  1. 1 华中科技大学人工智能与自动化学院 武汉 430074
    2 新加坡国立大学计算机学院 新加坡 119077
    3 山东大学软件学院 济南 250101
    4 深圳市大数据研究院 广东 深圳 518172
    5 香港中文大学(深圳)理工学院 广东 深圳 518172
    6 山东建筑大学计算机科学与技术学院 济南 250101
  • 收稿日期:2025-01-10 修回日期:2025-02-20 出版日期:2025-09-15 发布日期:2025-09-11
  • 通讯作者: 石清磊(shiqingleicmu@gmail.com)
  • 作者简介:(wangyongquan@hust.edu.cn)
  • 基金资助:
    2023大学发展基金-科研启动经费即食管癌的图像质量控制和智能诊断系统;福田健康医疗研究项目(FTWS002)

Research Progress of Machine Learning in Diagnosis and Treatment of Esophageal Cancer

WANG Yongquan1, SU Mengqi2, SHI Qinglei3,4, MA Yining5, SUN Yangfan5, WANG Changmiao4, WANG Guoyou1, XI Xiaoming6, YIN Yilong3, WAN Xiang4   

  1. 1 College of Artificial Intelligence and Automation,Huazhong University of Science and Technology,Wuhan 430074,China
    2 College of Computing,National University of Singapore,Singapore 119077,Singapore
    3 School of Software,Shandong University,Jinan 250101,China
    4 Shenzhen Research Institute of Big Data,Shenzhen,Guangdong 518172,China
    5 School of Science and Engineering,The Chinese University of Hong Kong,Shenzhen,Shenzhen,Guangdong 518172,China
    6 School of Computer Science and Technology,Shandong Jianzhu University,Jinan 250101,China
  • Received:2025-01-10 Revised:2025-02-20 Online:2025-09-15 Published:2025-09-11
  • About author:WANG Yongquan,born in 2001,postgraduate.Her main research interests include intelligent science technology and computer vision.
    SHI Qinglei,born in 1982,Ph.D,senior scientist.His main research interests include artificial intelligence technology in the diagnosis and treatment of tumors and neurological diseases,establishment of an intelligent assisted diagnosis and treatment decision-making system.
  • Supported by:
    2023 University Development Fund-Scientific Research Start-up GrantImage Quality Control and Intelligent Diagnostic System for Esophageal Cancer and Futian Health and Medical Research Project(FTWS002).

PDF (PC)

18

摘要： 食管癌(Esophageal Cancer,EC)是一种全球范围内高致死率的恶性肿瘤,尤其是在我国,由于早期诊断率低、预后不良,食管癌已成为临床诊疗中面临的重大挑战。近年来,机器学习(Machine Learning,ML)技术凭借多模态数据融合的智能分析方法,在推动食管癌诊疗精准化发展方面取得了显著进展。传统机器学习方法通过整合食管癌影像组学特征与临床文本信息,有效提升了早期病变诊断的敏感性,并为高风险患者的分层管理提供了科学支持。卷积神经网络(Convolutional Neural Network,CNN)以其高效的参数共享机制和卓越的局部特征提取能力,进一步增强了食管癌早期诊断与筛查的准确性。此外,将CNN与基于自注意力机制的Transformer模型相结合,显著提升了全局特征的建模能力,通过多模态数据的协同作用,其在食管癌病灶分割、早期诊断、疗效预测和生存分析等方面展现出广阔的应用前景。然而,食管癌病变的高度异质性以及图像数据类别不平衡问题,依然对机器学习技术的临床应用带来了较大挑战。为进一步推动食管癌智能诊疗技术的发展,聚焦于食管癌早期筛查与诊断、疗效预测与生存分析、影像分割3个关键领域,系统综述了传统机器学习、CNN及Transformer等前沿技术在EC诊疗中的研究现状与挑战,旨在为未来食管癌智能化诊疗研究提供有价值的参考与借鉴。

关键词: 食管癌, 机器学习, 鉴别诊断, 生存分析, 语义分割

Abstract: EC is a highly lethal malignancy worldwide,particularly in China.Its low early diagnosis rates and poor prognosis present significant challenges to clinical management.In recent years,ML technology,based on multi-modal data,has shown great potential in early EC diagnosis and treatment.Traditional ML methods integrate radiomic features from EC imaging and clinical textual data,thereby effectively improving the sensitivity of early lesion diagnosis and providing scientific support for the stratified management of high-risk patients.CNNs with their efficient parameter-sharing mechanisms and excellent local feature extraction capabilities,further enhance the accuracy of early EC diagnosis and screening.Moreover,combining CNNs with Transformer models based on self-attention mechanisms significantly strengthens global feature modeling,which demonstrating broad application potential in lesion segmentation,early diagnosis,treatment outcome prediction,and survival analysis of EC.However,the high heterogeneity of EC lesions and the class imbalance of imaging data continue to pose significant challenges to the clinical application of ML technologies.To advance intelligent diagnostic and therapeutic technologies for EC,this paper focuses on three critical areas:early screening and diagnosis,treatment outcome prediction and survival analysis,and image segmentation.It systematically reviews the current research status and challenges of traditional ML,CNNs,and emerging Transformer technologies in EC diagnosis and treatment,aiming to provide valuable insights and references for future research on intelligent EC diagnosis and treatment.

Key words: Esophageal cancer, Machine learning, Differential diagnosis, Survival analysis, Semantic segmentation

中图分类号: 

  • TP391
[1]SUNG H,FERLAY J,SIEGEL R L,et al.Global Cancer Statistics 2020:GLOBOCAN Estimates of Incidence and Mortality Worldwide for 36 Cancers in 185 Countries[J].CA Cancer J Clin,2021,71(3):209-249.
[2]QIU H,CAO S,XU R.Analys is of the time trend of China’s cancer incidence rate,mortality and burden based on the global epidemiol ogical data in 2020 and comparison with data from t he United States and the United Kingdom[J].Cancer,2022,41(4):165-177.
[3]DENG W,LIN S H.Advances in radiotherapy for esophagealcancer[J].Annals of Translational Medicine,2018,6(4):79.
[4]KATO H,NAKAJIMA M.Treatments for esophageal cancer:a review[J].General Thoracic and Cardiovascular Surgery,2013,61:330-335.
[5]SHAW P,SANKARANARAYANAN S,LORENZ P.EarlyEsophageal Malignancy Detection Using Deep Transfer Lear-ning and Explainable AI[C]//Proceedings of the 6th Internatio-nal Conference on Communication and Information Systems.IEEE,2022.
[6]WU C,ZHANG Y,WANG Y,et al.Multi-Modal IntermediateFeature Interaction Autoencoder for Overall Survival Prediction of Esophageal Squamous Cell Cancer[C]//Proceedings of the 2024 IEEE International Symposium on Biomedical Imaging.IEEE,2024.
[7]LI Z,LIU F,YANG W,et al.A survey of convolutional neural networks:analysis,applications,and prospects[J].IEEE Transactions on Neural Networks and Learning Systems,2021,33(12):6999-7019.
[8]YU Z,JIANG S,WANG L.Esophageal Image Segmentationwith Dual Attention Based on TransUNet[C]//Proceedings of the 2024 4th International Conference on Consumer Electronics and Computer Engineering.IEEE,2024.
[9]VASWANI A,SHAZEER N,PARMAR N,et al.Attention is all you need[C]//Proceedings of the 31st International Confe-rence on Neural Information Processing Systems.2017:6000-6010.
[10]WANG S,LI B Z,KHABSA M,et al.Linformer:Self-Attention with Linear Complexity[J].arXiv:2006.04768,2020.
[11]AZAD R,KAZEROUNI A,HEIDARI M,et al.Advances in medical image analysis with vision transformers:a comprehensive review[J].Medical Image Analysis,2024,91:103000.
[12]ERICKSON B J,KORFIATIS P,AKKUS Z,et al.Machinelearning for medical imaging[J].Radiographics:A Review Publication of the Radiological Society of North America,2017,37(2):505-515.
[13]YAMAGUCHI J,YONEYAMA A,MINAMOTO T.Automatic detection of early esophageal cancer from endoscope image using fractal dimension and discrete wavelet transform[C]//Procee-dings of the 12th International Conference on Information Technology-New Generations.IEEE,2015.
[14]XUE Y,LI N,WEI X,et al.Deep learning-based earlier detection of esophageal cancer using improved empirical wavelet transform from endoscopic image[J].IEEE Access,2020,8:123765-123772.
[15]PADHA A,SAHOO A.Quantum deep neural networks for time series analysis[J].Quantum Information Processing,2024,23(6):205.
[16]LYU H,KAPCIO K,PURRMAN K,et al.Applying Machine Learning to Predict Esophageal Cancer Recurrence after Esophagectomy[C]//Proceedings of the 2023 IEEE International Conference on Digital Health.IEEE,2023.
[17]SU Y,HUANG C,YANG C,et al.Prediction of Survival in Patients With Esophageal Cancer After Immunotherapy Based on Small-Size Follow-Up Data[J].IEEE Open Journal of Engineering in Medicine and Biology,2024(5):769-782.
[18]SUN J,YANG Y,WANG Y,et al.Survival risk prediction ofesophageal cancer based on self-organizing maps clustering and support vector machine ensembles[J].IEEE Access,2020,8:131449-131460.
[19]PRINCE T,WONDMANEHGETAHUN B,AMBACHEW-GOSHU K,et al.Multi-Classification and Segmentation of Esophageal Lesions Using an Improved Deep Learning Model from Endoscopic Images[C]//Proceedings of the 2023 Eighth International Conference on Science Technology Engineering and Mathematics.IEEE,2023.
[20]NGIAM J,KHOSLA A,KIM M,et al.Multimodal Deep Lear-ning[C]//Proceedings of the International Conference on Machine Learning.IEEE,2011.
[21]GUAN Y,CUI H,XU Y,et al.Predicting esophageal fistularisks using a multimodal self-attention network[C]//Procee-dings of the Medical Image Computing and Computer Assisted Intervention.2021.
[22]LIU D,JIANG H,RAO N,et al.Depth information-based automatic annotation of early esophageal cancers in gastroscopic images using deep learning techniques[J].IEEE Access,2020,8:97907-90919.
[23]FU Y,ZHOU Y,YUAN X,et al.Efficient Esophageal LesionDetection using Polarization Regularized Network Slimming[C]//Proceedings of the 2022 IEEE 8th International Confe-rence on Cloud Computing and Intelligent Systems.IEEE,2022.
[24]YAN X,ZHOU Y,YI Z.Self-supervised Feature Representation Distillation for Esophageal Cancer Screening[C]//Proceedings of the 2024 International Joint Conference on Neural Networks.IEEE,2024.
[25]VAN RIEL S,VAN DER SOMMEN F,ZINGER S,et al.Automatic detection of early esophageal cancer with CNNS using transfer learning[C]//Proceedings of the 2018 25th IEEE International Conference on Image Processing.IEEE,2018.
[26]ABURASAIN R Y.Esophageal Cancer Classification in Initial Stages Using Deep and Transfer Learning[C]//Proceedings of the 2024 IEEE International Conference on Advanced Systems and Emergent Technologies.IEEE,2024.
[27]TSAO Y M,MUKUNDAN A,KARMAKAR R,et al.Hyperspectral Imaging Applied to Identify Early Esophageal Cancer[C]//Proceedings of the 2024 Conference on Lasers and Electro-Optics Pacific Rim.IEEE,2024.
[28]DING S,HUANG H,LI Z,et al.SCNET:A novel UGI cancer screening framework based on semantic-level multimodal data fusion[J].IEEE Journal of Biomedical and Health Informatics,2020,25(1):143-151.
[29]GHATWARY N,ZOLGHARNI M,JANAN F,et al.Learningspatiotemporal features for esophageal abnormality detection from endoscopic videos[J].IEEE Journal of Biomedical and Health Informatics,2020,25(1):131-142.
[30]LIN Z,CAI W,HOU W,et al.CT-guided survival prediction of esophageal cancer[J].IEEE Journal of Biomedical and Health Informatics,2021,26(6):2660-2669.
[31]WU C,WANG S,WANG Y,et al.A Novel Multi-modal Population-graph based Framework for Patients of Esophageal Squamous Cell Cancer Prognostic Risk Prediction[J].IEEE Journal of Biomedical and Health Informatics,2024,29(5):3206-3219.
[32]HUANG G,ZHU J,LI J,et al.Channel-attention U-Net:Channel attention mechanism for semantic segmentation of esophagus and esophageal cancer[J].IEEE Access,2020,8:122798-122810.
[33]ZHOU D,HUANG G,LI J,et al.Eso-net:A novel 2.5D seg-mentation network with the multi-structure response filter for the cancerous esophagus[J].IEEE Access,2020,8:155548-155562.
[34]SUN Y,KHOR H G,HUANG S,et al.Second-Course Esophageal Gross Tumor Volume Segmentation in CT with Prior Anatomical and Radiotherapy Information[C]//Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention.IEEE,2023.
[35]YOUSEFI S,SOKOOTI H,ELMAHDY M S,et al.Esophageal tumor segmentation in CT images using a dilated dense attention Unet(DDAUnet)[J].IEEE Access,2021,9:99235-99248.
[36]GUO D,JIN D,ZHU Z,et al.Organ at risk segmentation for head and neck cancer using stratified learning and neural architecture search[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2020.
[37]LI H,LIU D,ZENG Y,et al.Single-Image-Based Deep Learning for Segmentation of Early Esophageal Cancer Lesions[J].ar-Xiv:2306,05912,2023.
[38]LIN Q,TAN W,CAI S,et al.Lesion-decoupling-based segmentation with large-scale colon and esophageal datasets for early cancer diagnosis[J].IEEE Transactions on Neural Networks and Learning Systems,2023,35(8):11142-11156.
[39]JIN Q,CUI H,SUN C,et al.Shape-aware contrastive deep su-pervision for esophageal tumor segmentation from CT scans[C]//Proceedings of the 2023 IEEE International Conference on Bioinformatics and Biomedicine.IEEE,2023.
[40]LOU X,ZHU Y,PUNITHAKUMAR K,et al.Esophagus segmentation in computed tomography images using a U-Net neural network with a semiautomatic labeling method[J].IEEE Access,2020,8:202459-202468.
[41]ZHOU Y,YUAN X,ZHANG X,et al.Evolutionary neural architecture search for automatic esophageal lesion identification and segmentation[J].IEEE Transactions on Artificial Intelligence,2021,3(3):436-450.
[42]WANG S,LI B Z,KHABSA M,et al.Linformer:Self-attention with linear complexity[J].arXiv:2006,04768,2020.
[43]CHEN T,KORNBLITH S,NOROUZI M,et al.A SimpleFramework for Contrastive Learning of Visual Representations[J].arXiv:2002.05709,2020.
[44]RAJKOMAR A,DEAN J,KOHANE I S.Machine Learning in Medicine[J].The New England Journal of Medicine,2019,380:1347-1358.
[45]TJOA E,GUAN C.A Survey on Explainable Artificial Intelligence(XAI):Toward Medical XAI[J].IEEE Transactions on Neural Networks and Learning Systems,2019,32:4793-4813.
[46]SAMEK W,MONTAVON G,VEDALDI A,et al.Explainable AI:Interpreting,Explaining and Visualizing Deep Learning[M].Cham:Springer,2019.
[47]KANG Z,ZHANG H,CHEN M,et al.EsccNet:A Hybrid CNN and Transformers Model for the Classification of Whole Slide Images of Esophageal Squamous Cell Carcinoma[C]//Procee-dings of the 2024 5th International Conference on Computer Engineering and Application.IEEE,2024.
[48]YUE H,LIU J,KUANG H,et al.A Fully Automated CT-Guided Learning for Survival Prediction of Esophageal Cancer[C]//2023 IEEE International Conference on Bioinformatics and Biomedicine(BIBM).2023:1670-1675.
[49]YAO J,YE X,XIA Y,et al.Effective opportunistic esophageal cancer screening using noncontrast CT imaging[C]//Procee-dings of the International Conference on Medical Image Computing and Computer-Assisted Intervention.Springer,2022.
[50]ZHANG Y,HE N,YANG J,et al.mmFormer:MultimodalMedical Transformer for Incomplete Multimodal Learning of Brain Tumor Segmentation[C]//Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention.2022.
[51]LI T,SAHU A K,TALWALKAR A,et al.Federated Learning:Challenges,Methods,and Future Directions[J].IEEE Signal
Processing Magazine,2019,37:50-60.
[52]FRAPPIER M.The Book of Why:The New Science of Cause and Effect[M].Basic Books,2018.
[53]MILLETARI F,NAVAB N,AHMADI S A.V-Net:Fully Con-volutional Neural Networks for Volumetric Medical Image Segmentation[J].arXiv:1606.04797,2016.
[54]ZHAO Y,WANG X,CHE T,et al.Multi-task deep learning for medical image computing and analysis:A review[J].Computers in Biology and Medicine,2022,153:106496.
[55]GU A,DAO T.Mamba:Linear-time sequence modeling with selective state spaces[J].arXiv:2312,00752,2023.
[56]SHI Q,DUAN W,CHEN W,et al.PGP:Prior-Guided Pretraining for Small-sample Esophageal Cancer Segmentation[C]//2024 IEEE International Conference on Bioinformatics and Biomedicine(BIBM).2024:3701-3704.
[57]ZHOU J,CUI G,ZHANG Z,et al.Graph Neural Networks:A Review of Methods and Applications[J].arXiv:1812.08434,2018.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市渝北区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发