切换至 "中华医学电子期刊资源库"

中华乳腺病杂志(电子版) ›› 2026, Vol. 20 ›› Issue (03) : 169 -173. doi: 10.3877/cma.j.issn.1674-0807.2026.03.006

综述

基于深度学习的MRI图像分析在乳腺癌诊疗中的应用
程妹1,2, 金亚彬3, 马丁瑞4, 程昊4, 詹玉莲5,(), 周丹1,2,()   
  1. 1 524000 湛江,广东医科大学第一临床医学院
    2 528000 佛山,佛山市第一人民医院/南方科技大学附属佛山医院乳腺外科
    3 528000 佛山,佛山市第一人民医院/南方科技大学附属佛山医院科研部
    4 401100 上海,上海交通大学自动化系
    5 510630 广州,广州市天河区中医医院超声科
  • 收稿日期:2024-12-31 出版日期:2026-06-01
  • 通信作者: 詹玉莲, 周丹
  • 基金资助:
    广东省中医药局课题(20231324); 佛山市登峰计划项目(2020B018)

Application of deep learning-based MRI image analysis in breast cancer diagnosis and treatment

Mei Cheng, Yabin Jin, Dingrui Ma   

  • Received:2024-12-31 Published:2026-06-01
引用本文:

程妹, 金亚彬, 马丁瑞, 程昊, 詹玉莲, 周丹. 基于深度学习的MRI图像分析在乳腺癌诊疗中的应用[J/OL]. 中华乳腺病杂志(电子版), 2026, 20(03): 169-173.

Mei Cheng, Yabin Jin, Dingrui Ma. Application of deep learning-based MRI image analysis in breast cancer diagnosis and treatment[J/OL]. Chinese Journal of Breast Disease(Electronic Edition), 2026, 20(03): 169-173.

MRI在乳腺癌诊疗中具有重要价值。近年来,深度学习作为人工智能的核心技术,为MRI精准分析提供了新的途径。本文对深度学习在乳腺癌MRI分析中的最新研究进展进行系统梳理,重点围绕筛查、病灶检测、分子分型识别、淋巴结状态评估、新辅助化疗疗效预测以及预后判断六大临床应用场景予以概述,继而讨论上述深度学习模型在当前的临床转化过程中面临的关键挑战,并对未来研究方向进行了展望,以期为相关研究与临床实践提供参考,促进深度学习技术在乳腺癌影像分析领域的进一步应用与发展。

[1]
Kim JHarper AMcCormack V, et al. Global patterns and trends in breast cancer incidence and mortality across 185 countries[J]. Nat Med202531(4):1154-1162.
[2]
Han BZheng RZeng H, et al. Cancer incidence and mortality in China, 2022[J]. J Natl Cancer Cent20244(1):47-53.
[3]
Mann GBSkandarajah ARZdenkowski N, et al. Postoperative radiotherapy omission in selected patients with early breast cancer following preoperative breast MRI (PROSPECT):primary results of a prospective two-arm study[J]. Lancet2024403(10423):261-270.
[4]
Jing XWielema MCornelissen LJ, et al. Using deep learning to safely exclude lesions with only ultrafast breast MRI to shorten acquisition and reading time[J]. Eur Radiol202232(12):8706-8715.
[5]
唐玮,何融泉,黄素宁. 深度学习在乳腺癌影像诊疗和预后预测中的应用[J/OL]. 中华乳腺病杂志(电子版)202317(6):323-328.
[6]
Hosny AParmar CQuackenbush J, et al. Artificial intelligence in radiology[J]. Nat Rev Cancer201818(8):500-510.
[7]
LeCun YBengio YHinton G. Deep learning[J]. Nature2015521(7553):436-444.
[8]
Elharrouss OAkbari YAlmadeed N, et al. Backbones-review:feature extractor networks for deep learning and deep reinforcement learning approaches in computer vision[J]. Comput Sci Rev202453:100645.
[9]
Litjens GKooi TBejnordi BE, et al. A survey on deep learning in medical image analysis[J]. Med Image Anal201742:60-88.
[10]
Chen TKornblith SNorouzi M, et al. A simple framework for contrastive learning of visual representations[C]//Proceedings of the 37th international conference on machine learning. Cambridge: JMLR. org, 2020:1597-1607.
[11]
Zhou BKhosla ALapedriza A, et al. Learning deep features for discriminative localization[C]//2016 IEEE conference on computer vision and pattern recognition (CVPR). Las Vegas:IEEE Computer Society, 2016:2921-2929.
[12]
Ardila DKiraly APBharadwaj S, et al. End-to-end lung cancer screening with three-dimensional deep learning on low-dose chest computed tomography[J]. Nat Med201925(6):954-961.
[13]
Azizi SCulp LFreyberg J, et al. Robust and data-efficient generalization of self-supervised machine learning for diagnostic imaging[J]. Nat Biomed Eng20237(6):756-779.
[14]
Radak MLafta HYFallahi H. Machine learning and deep learning techniques for breast cancer diagnosis and classification:a comprehensive review of medical imaging studies[J]. J Cancer Res Clin Oncol2023149(12):10473-10491.
[15]
Bakker MFde Lange SVPijnappel RM, et al. Supplemental MRI screening for women with extremely dense breast tissue[J]. N Engl J Med2019381(22):2091-2102.
[16]
Gui HJiao HLi L, et al. Breast tumor detection and diagnosis using an improved faster R-CNN in DCE-MRI[J]. Bioengineering202411(12):1217.
[17]
Jing XDorrius MDZheng S, et al. Localization of contrast-enhanced breast lesions in ultrafast screening MRI using deep convolutional neural networks[J]. Eur Radiol202434(3):2084-2092.
[18]
Anaby DShavin DZimmerman-Moreno G, et al. 'Earlier than early' detection of breast cancer in Israeli BRCA mutation carriers applying AI-based analysis to consecutive MRI scans[J]. Cancers (Basel)202315(12):3120.
[19]
Hirsch LHuang YMakse HA, et al. Early detection of breast cancer in MRI using AI[J]. Acad Radiol202532(3):1218-1225.
[20]
Salim MLiu YSorkhei M, et al. AI-based selection of individuals for supplemental MRI in population-based breast cancer screening:the randomized ScreenTrustMRI trial[J]. Nat Med202430(9):2623-2630.
[21]
Hu QWhitney HMGiger ML. A deep learning methodology for improved breast cancer diagnosis using multiparametric MRI[J]. Sci Rep202010(1):10536.
[22]
Witowski JHeacock LReig B, et al. Improving breast cancer diagnostics with deep learning for MRI[J]. Sci Transl Med202214(664):eabo4802.
[23]
Feng HCao JWang H, et al. A knowledge-driven feature learning and integration method for breast cancer diagnosis on multi-sequence MRI[J]. Magn Reson Imaging202069:40-48.
[24]
Wu JLi YGong W, et al. Multi-modality radiomics diagnosis of breast cancer based on MRI, ultrasound and mammography[J]. BMC Med Imaging202525(1):265.
[25]
Koboldt DCFulton RSMcLellan MD, et al. Comprehensive molecular portraits of human breast tumours[J]. Nature2012490(7418):61-70.
[26]
Yin HBai LJia H, et al. Noninvasive assessment of breast cancer molecular subtypes on multiparametric MRI using convolutional neural network with transfer learning[J]. Thorac Cancer202213(22):3183-3191.
[27]
Ma MGan LJiang Y, et al. Radiomics analysis based on automatic image segmentation of DCE-MRI for predicting triple-negative and nontriple-negative breast cancer[J]. Comput Math Methods Med20212021:2140465.
[28]
Fan MYuan CHuang G, et al. A framework for deep multitask learning with multiparametric magnetic resonance imaging for the joint prediction of histological characteristics in breast cancer[J]. IEEE J. Biomed. Health Inform202226(8):3884-3895.
[29]
Xie XZhou HMa M, et al. A deep learning model for predicting molecular subtype of breast cancer by fusing multiple sequences of DCE-MRI from two institutes[J]. Acad Radiol202431(9):3479-3488.
[30]
Martina Jaincy DEPattabiraman V. BCDCNN:breast cancer deep convolutional neural network for breast cancer detection using MRI images[J]. Sci Rep202515(1):29014.
[31]
Wang SDai YShen J, et al. Research on expansion and classification of imbalanced data based on SMOTE algorithm[J]. Sci Rep202111(1):24039.
[32]
Ghavidel APazos P. Machine learning (ML) techniques to predict breast cancer in imbalanced datasets:a systematic review[J]. J Cancer Surviv202519(1):270-294.
[33]
Pan XWang PJia S, et al. Multi-contrast learning-guided lightweight few-shot learning scheme for predicting breast cancer molecular subtypes[J]. Med Biol Eng Comput202462(5):1601-1613.
[34]
Zhang XLiu MRen W, et al. Predicting of axillary lymph node metastasis in invasive breast cancer using multiparametric MRI dataset based on CNN model[J]. Front Oncol202212:1069733.
[35]
Guo YJYin RZhang Q, et al. MRI-based kinetic heterogeneity evaluation in the accurate access of axillary lymph node status in breast cancer using a hybrid CNN-RNN model[J]. J Magn Reson Imaging202460(4):1352-1364.
[36]
Liu WLi LDeng J, et al. A comprehensive approach for evaluating lymphovascular invasion in invasive breast cancer:leveraging multimodal MRI findings, radiomics, and deep learning analysis of intra- and peritumoral regions[J]. Comput Med Imaging Graph2024116:102415.
[37]
Wang HMao X. Evaluation of the efficacy of neoadjuvant chemotherapy for breast cancer[J]. Drug Des Devel Ther202014:2423-2433.
[38]
李建辉,蔺光帅. 新辅助化疗对乳腺癌手术方式的影响 [J/OL]. 中华乳腺病杂志(电子版)202014(4):240-243.
[39]
Cortazar PZhang LUntch M, et al. Pathological complete response and long-term clinical benefit in breast cancer:the CTNeoBC pooled analysis[J]. Lancet2014384(9938):164-172.
[40]
Kim SYLee JCho N, et al. Deep-learning based discrimination of pathologic complete response using MRI in HER2-positive and triple-negative breast cancer[J]. Sci Rep202414(1):23065.
[41]
Janse MHAJanssen LMWolters-van der Ben EJM, et al. Deep learning-based radiomics does not improve residual cancer burden prediction post-chemotherapy in LIMA breast MRI trial[J]. Eur Radiol202636(2):850-862.
[42]
Mao NDai YZhou H, et al. A multimodal and fully automated system for prediction of pathological complete response to neoadjuvant chemotherapy in breast cancer[J]. Sci Adv202511(18):eadr1576.
[43]
Zhou ZAdrada BECandelaria RP, et al. Prediction of pathologic complete response to neoadjuvant systemic therapy in triple negative breast cancer using deep learning on multiparametric MRI[J]. Sci Rep202313(1):1171.
[44]
Gao YVentura-Diaz SWang X, et al. An explainable longitudinal multi-modal fusion model for predicting neoadjuvant therapy response in women with breast cancer[J]. Nat Commun202415(1):9613.
[45]
Yu YChen RYi J, et al. Non-invasive prediction of axillary lymph node dissection exemption in breast cancer patients post-neoadjuvant therapy:a radiomics and deep learning analysis on longitudinal DCE-MRI data[J]. Breast202477:103786.
[46]
Li ZGao JZhou H, et al. Multiregional dynamic contrast-enhanced MRI-based integrated system for predicting pathological complete response of axillary lymph node to neoadjuvant chemotherapy in breast cancer:multicentre study[J]. EBioMedicine2024107:105311.
[47]
Tang WJin CKong Q, et al. Development and validation of an MRI spatiotemporal interaction model for early noninvasive prediction of neoadjuvant chemotherapy response in breast cancer:a multicentre study[J]. eClinicalMedicine202585:103298.
[48]
Liu JLi XWang G, et al. Time-series MR images identifying complete response to neoadjuvant chemotherapy in breast cancer using a deep learning approach[J]. J Magn Reson Imaging202561(1):184-197.
[49]
Ma MGan LLiu Y, et al. Radiomics features based on automatic segmented MRI images:prognostic biomarkers for triple-negative breast cancer treated with neoadjuvant chemotherapy[J]. Eur J Radiol2022146:110095.
[50]
Ha RChang PMutasa S, et al. Convolutional neural network using a breast MRI tumor dataset can predict oncotype Dx recurrence score[J]. J Magn Reson Imaging201949(2):518-524.
[51]
Dammu HRen TDuong TQ. Deep learning prediction of pathological complete response, residual cancer burden, and progression-free survival in breast cancer patients[J]. PLoS One202318(1):e0280148.
[52]
Kelly CJKarthikesalingam ASuleyman M, et al. Key challenges for delivering clinical impact with artificial intelligence[J]. BMC Med201917(1):195.
[53]
Liu XDeng YNallanathan A, et al. Federated learning and meta learning:approaches, applications, and directions[J]. IEEE Commun Surv Tutorials202426(1):571-618.
[54]
Dobson JE. On reading and interpreting black box deep neural networks[J]. Int J Digit Humanit20235(2):431-449.
[55]
Lin FPCHosseinalipour SMichelusi N, et al. Delay-aware hierarchical federated learning[J]. IEEE Trans Cogn Commun Netw202410(2):674-688.
[56]
Nguyen HTSehwag VHosseinalipour S, et al. Fast-convergent federated learning[J]. IEEE J Sel Areas Commun202139(1):201-218.
[57]
Li YYang SRen X, et al. Multi-stage asynchronous federated learning with adaptive differential privacy[J]. IEEE Trans Pattern Anal Mach Intell202446(2):1243-1256.
[1] 王硕, 郑新宇. 乳腺癌术后同侧乳腺肿瘤复发的病理学认知与处理[J/OL]. 中华乳腺病杂志(电子版), 2026, 20(03): 133-137.
[2] 丁彩霞, 曲景辉, 裴英宏, 李静娜, 郑晓瑜, 徐岭植, 李思思. 基于RNA结合蛋白基因表达特征的乳腺癌预后预测模型构建及评价分析[J/OL]. 中华乳腺病杂志(电子版), 2026, 20(03): 138-147.
[3] 王美衡, 李杰, 陈策实, 许超汉. 乳腺癌串联重复表型的识别及分子功能特征分析[J/OL]. 中华乳腺病杂志(电子版), 2026, 20(03): 148-155.
[4] 范遥, 黄玉娥, 杨森果, 丁华, 张黔, 刘蜀. 线粒体基质导入因子23在三阴性乳腺癌中的表达及其作用机制[J/OL]. 中华乳腺病杂志(电子版), 2026, 20(03): 156-162.
[5] 王静坤, 计美妮, 王玉凤, 宣浩军. 真空辅助乳腺活检与空芯针穿刺活检在乳腺癌诊断中的对比研究[J/OL]. 中华乳腺病杂志(电子版), 2026, 20(03): 163-168.
[6] 何宇杭, 曹中伟. 中性粒细胞百分比-白蛋白比值与乳腺癌的关联性及预测效能研究[J/OL]. 中华普外科手术学杂志(电子版), 2026, 20(03): 279-283.
[7] 田爱洁, 何晨熙, 孔凡庭. 乳腺癌新辅助化疗后乳腺钼靶微钙化术前评估的临床研究[J/OL]. 中华普外科手术学杂志(电子版), 2026, 20(03): 284-288.
[8] 韩丽丽, 范慈勃, 陈纲. PALB2基因胚系突变与中国女性乳腺癌遗传风险及临床特征的关联研究[J/OL]. 中华普外科手术学杂志(电子版), 2026, 20(03): 289-291.
[9] 贾亚南, 尚迎晓, 甄江涛. 乳腺术后皮下高引流量淋巴漏1例[J/OL]. 中华普外科手术学杂志(电子版), 2026, 20(03): 303-304.
[10] 黄楚曦, 吴卓. 人工智能在膀胱癌影像中的应用进展[J/OL]. 中华腔镜泌尿外科杂志(电子版), 2026, 20(03): 241-247.
[11] 徐宏博, 胡玉良, 魏雪栋, 金李晨, 武克风, 陈逸伦, 陆兵, 周守军, 侯建全. 基于临床和CT影像组学特征的机器学习模型对经皮肾镜术后脓毒症的预测价值[J/OL]. 中华腔镜泌尿外科杂志(电子版), 2026, 20(03): 297-306.
[12] 谢雨欣, 朱亚琼, 张飞, 熊文韬, 郭新悦, 朱颖广, 李子昂, 赵宝峰, 张强. 粘连性肩关节囊炎患者腋囊厚度与查体角度及不同影像学测量的相关性研究[J/OL]. 中华肩肘外科电子杂志, 2026, 14(02): 71-77.
[13] 张忠, 王喆, 黄其日麦拉图, 齐岩松. 人工智能在肘关节骨关节炎诊疗中的应用进展[J/OL]. 中华肩肘外科电子杂志, 2026, 14(02): 109-114.
[14] 陈小坤, 杜顺达. 影像组学在肝细胞癌中的应用进展及挑战[J/OL]. 中华消化病与影像杂志(电子版), 2026, 16(02): 97-100.
[15] 高增霞, 贺云飞, 赵娜. DCE-MRI联合Gd-EOB-DTPA MRI纹理特征对肝细胞癌经导管动脉化疗栓塞术后疗效的评估[J/OL]. 中华消化病与影像杂志(电子版), 2026, 16(02): 108-113.
阅读次数
全文


摘要


AI


AI小编
你好!我是《中华医学电子期刊资源库》AI小编,有什么可以帮您的吗?