Research Advances in DCE-MRI-Based Breast Lesion Segmentation and Benign-Malignant Classification Methods
Huang Kaiyang1, Li Xiujuan2, Xie Yuanzhong2, Hou Jixue3, Han Baosan4, Nie Shengdong1*
1(Institute of Medical Imaging Engineering, University of Shanghai for Science and Technology, Shanghai 200091, China) 2(Medical Imaging Center, Tai'an Central Hospital Affiliated with Qingdao University, Tai'an 271000, Shandong,China) 3(Department of Thyroid and Breast Surgery, The First Affiliated Hospital of Shihezi University, Shihezi 832000, Xinjiang, China) 4(Department of Breast Surgery, Xinhua Hospital Affiliated to Shanghai Jiao Tong University School of Medicine, Shanghai 200092, China)
Abstract：Breast cancer is one of the most common malignant tumors threatening women′s health, and early and accurate diagnosis plays an important role in the prognosis of breast cancer patients. Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) provides an important technical support for segmentation of breast lesions and discrimination of benign and malignant by virtue of its high resolution and dynamic flow analysis capability.In this article, the research progress of breast lesion segmentation and classification techniques based on DCE-MRI was reviewed, starting from non-automated traditional image segmentation and machine learning models based on manual feature extraction, moving on to deep learning techniques represented by convolutional neural networks, and further extending to analysis strategies integrating multi-modal imaging data as well as other emerging technologies. The technical characteristics and clinical application value of various methods were elaborated in detail. The current status of breast lesion segmentation and benign-malignant classification technologies was summarized, and future development directions were outlined. Specifically, emphasis should be placed on multi-center data collaboration, model interpretability, and development strategies integrating artificial intelligence with clinical practice, so that a safe and efficient intelligent auxiliary diagnosis system could be established to provide reliable support for the precise diagnosis and treatment of breast cancer.
黄凯扬, 李秀娟, 谢元忠, 侯吉学, 韩宝三, 聂生东. 基于DCE-MRI的乳腺病灶分割与良恶性分类方法的研究进展[J]. 中国生物医学工程学报, 2025, 44(6): 730-737.
Huang Kaiyang, Li Xiujuan, Xie Yuanzhong, Hou Jixue, Han Baosan, Nie Shengdong. Research Advances in DCE-MRI-Based Breast Lesion Segmentation and Benign-Malignant Classification Methods. Chinese Journal of Biomedical Engineering, 2025, 44(6): 730-737.
[1] Arian A, Seyed-Kolbadi FZ, Yaghoobpoor S, et al. Diagnostic accuracy of intravoxel incoherent motion (IVIM) and dynamic contrast-enhanced (DCE) MRI to differentiate benign from malignant breast lesions: a systematic review and meta-analysis[J]. European Journal of Radiology, 2023, 167: 111051. [2] Chen Yanhong, Wang Lijun, Luo Ran, et al. A deep learning model based on dynamic contrast-enhanced magnetic resonance imaging enables accurate prediction of benign and malignant breast lessons[J]. Frontiers in Oncology, 2022, 12: 943415. [3] Fan Ming, Huang Guangyao, Lou Junhong, et al. Cross-parametric generative adversarial network-based magnetic resonance image feature synthesis for breast lesion classification[J]. IEEE Journal of Biomedical and Health Informatics, 2023, 27(11): 5495-5505. [4] Fusco R, Di Bernardo E, Piccirillo A, et al. Radiomic and artificial intelligence analysis with textural metrics extracted by contrast-enhanced mammography and dynamic contrast magnetic resonance imaging to detect breast malignant lesions[J]. Current Oncology, 2022, 29(3): 1947-1966. [5] Gui Haitian, Jiao Han, Li Li, et al. Breast tumor detection and diagnosis using an improved faster R-CNN in DCE-MRI[J]. Bioengineering, 2024, 11(12): 1217. [6] Ponraj A, Nagaraj P, Balakrishnan D, et al. A multi-patch-based deep learning model with VGG19 for breast cancer classifications in the pathology images[J]. Digital Health, 2025, 11: 20552076241313161. [7] Sun Rong, Zhang Xiaobing, Xie Yuanzhong, et al. Weakly supervised breast lesion detection in DCE-MRI using self-transfer learning[J]. Medical Physics, 2023, 50(8): 4960-4972. [8] Sun Shiyun, Ding Yingying, Li Zhuolin, et al. Multiparameter MRI model with DCE-MRI, DWI, and synthetic MRI improves the diagnostic performance of BI-RADS 4 lesions[J]. Frontiers in Oncology, 2021, 11: 699127. [9] Hizukuri A, Nakayama R, Nara M, et al. Computer-aided diagnosis scheme for distinguishing between benign and malignant masses on breast DCE-MRI images using deep convolutional neural network with Bayesian optimization[J]. Journal of Digital Imaging, 2021, 34: 116-123. [10] Zhou Jiejie, Zhang Yang, Chang Kaiting, et al. Diagnosis of benign and malignant breast lesions on DCE-MRI by using radiomics and deep learning with consideration of peritumor tissue[J]. Journal of Magnetic Resonance Imaging, 2020, 51(3): 798-809. [11] Jiang Zejun, Yin Jiandong. Performance evaluation of texture analysis based on kinetic parametric maps from breast DCE-MRI in classifying benign from malignant lesions[J]. Journal of Surgical Oncology, 2020, 121(8): 1181-1190. [12] Vamvakas A, Tsivaka D, Logothetis A, et al. Breast cancer classification on multiparametric MRI-increased performance of boosting ensemble methods[J]. Technology in Cancer Research & Treatment, 2022, 21: 15330338221087828. [13] Piantadosi G, Sansone M, Fusco R, et al. Multi-planar 3D breast segmentation in MRI via deep convolutional neural networks[J]. Artificial Intelligence in Medicine, 2020, 103: 101781. [14] Nowakowska S, Borkowski K, Ruppert CM, et al. Generalizable attention U-Net for segmentation of fibroglandular tissue and background parenchymal enhancement in breast DCE-MRI[J]. Insights into Imaging, 2023, 14(1): 185. [15] Isensee F, Jaeger PF, Kohl SAA, et al. nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation[J]. Nature Methods, 2021, 18(2): 203-211. [16] Douglas L, Bhattacharjee R, Fuhrman J, et al. U-Net breast lesion segmentations for breast dynamic contrast-enhanced magnetic resonance imaging[J]. Journal of Medical Imaging, 2023, 10(6): 064502. [17] Rahimpour M, Saint Martin MJ, Frouin F, et al. Visual ensemble selection of deep convolutional neural networks for 3D segmentation of breast tumors on dynamic contrast enhanced MRI[J]. European Radiology, 2023, 33(2): 959-969. [18] Wang Long, Zhang Ming, He Guangyuan, et al. Classification of breast lesions on DCE-MRI data using a fine-tuned MobileNet[J]. Diagnostics, 2023, 13(6): 1067. [19] Meng Mingzhu, Zhang Ming, Shen Dong, et al. Differentiation of breast lesions on dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) using deep transfer learning based on DenseNet201[J]. Medicine, 2022, 101(45): e31214. [20] Zhao Xiaoming, Liao Yuehui, Xie Jiahao, et al. BreastDM: a DCE-MRI dataset for breast tumor image segmentation and classification[J]. Computers in Biology and Medicine, 2023, 164: 107255. [21] Daimiel Naranjo I, Gibbs P, Reiner JS, et al. Breast lesion classification with multiparametric breast MRI using radiomics and machine learning: a comparison with radiologists′ performance [J]. Cancers, 2022, 14(7): 1743. [22] Du Yanan, Wang Dawei, Liu Menghan, et al. Study on the differential diagnosis of benign and malignant breast lesions using a deep learning model based on multimodal images[J]. Journal of Cancer Research and Therapeutics, 2024, 20(2): 625-632. [23] Dai Shuo, Liu Xueyan, Wei Wei, et al. A multi-scale, multi-task fusion UNet model for accurate breast tumor segmentation[J]. Computer Methods and Programs in Biomedicine, 2025, 258: 108484. [24] Han Xiaorui, Gong Zhengze, Guo Yuan, et al. Exploration of a noninvasive radiomics classifier for breast cancer tumor microenvironment categorization and prognostic outcome prediction[J]. European Journal of Radiology, 2024, 175: 111441. [25] Liu Xinmiao, Zhang Ji, Zhou Jiejie, et al. Multi-modality radiomics nomogram based on DCE-MRI and ultrasound images for benign and malignant breast lesion classification[J]. Frontiers in Oncology, 2022, 12: 992509. [26] Lyu Yidong, Chen Yan, Meng Lingsong, et al. Combination of ultrafast dynamic contrast-enhanced MRI-based radiomics and artificial neural network in assessing BI-RADS 4 breast lesions: Potential to avoid unnecessary biopsies[J]. Frontiers in Oncology, 2023, 13: 1074060. [27] Qin Chuanbo, Wu Yujie, Zeng Junying, et al. Joint transformer and multi-scale CNN for DCE-MRI breast cancer segmentation[J]. Soft Computing, 2022, 26(17): 8317-8334. [28] Song Wei, Pan Xiang, Fan Ming, et al. Clinical knowledge integrated multi-task learning network for breast tumor segmentation and pathological complete response prediction[J]. Biomedical Signal Processing and Control, 2025, 106: 107772. [29] Zhou Yue, Chen Houjin, Li Yanfeng, et al. Multi-task learning for segmentation and classification of tumors in 3D automated breast ultrasound images[J]. Medical Image Analysis, 2021, 70: 101918. [30] Zheng Shenhai, Li Jianfei, Qiao Lihong, et al. Multi-task interaction learning for accurate segmentation and classification of breast tumors in ultrasound images[J]. Physics in Medicine and Biology, 2025.1567577. [31] Madhu G, Meher Bonasi A, Kautish S, et al. UCapsNet: a two-stage deep learning model using U-Net and capsule network for breast cancer segmentation and classification in ultrasound imaging[J]. Cancers, 2024, 16(22): 3777. [32] Zhang Jiadong, Cui Zhiming, Shi Zhenwei, et al. A robust and efficient AI assistant for breast tumor segmentation from DCE-MRI via a spatial-temporal framework[J]. Patterns, 2023, 4(9): 100826. [33] Zhu Jingjin, Geng Jiahui, Shan Wei, et al. Development and validation of a deep learning model for breast lesion segmentation and characterization in multiparametric MRI[J]. Frontiers in Oncology, 2022, 12: 946580. [34] Wang Wenjiang, Li Jiaojiao, Wang Zimeng, et al. Study on the classification of benign and malignant breast lesions using a multi-sequence breast MRI fusion radiomics and deep learning model[J]. European Journal of Radiology Open, 2024, 13: 100607. [35] Ghasemi A, Hashtarkhani S, Schwartz D L, et al. Explainable artificial intelligence in breast cancer detection and risk prediction: a systematic scoping review[J]. Cancer Innovation, 2024, 3(5): e136. [36] Yang Yuzhe, Zhang Haoran, Gichoya JW, et al. The limits of fair medical imaging AI in real-world generalization[J]. Nature Medicine, 2024, 30(10): 2838-2848. [37] Zhang Jie, Zhang Zongming. Ethics and governance of trustworthy medical artificial intelligence[J]. BMC Medical Informatics and Decision Making, 2023, 23(1): 7. [38] Garrucho L, Kushibar K, Reidel CA, et al. A large-scale multicenter breast cancer DCE-MRI benchmark dataset with expert segmentations[J]. Scientific Data, 2025, 12(1): 453. [39] Shukla S, Rajkumar S, Sinha A, et al. Federated learning with differential privacy for breast cancer diagnosis enabling secure data sharing and model integrity[J]. Scientific Reports, 2025, 15(1): 13061. [40] Oviedo F, Kazerouni AS, Liznerski P, et al. Cancer detection in breast MRI screening via explainable AI anomaly detection[J]. Radiology, 2025, 316(1): e241629. [41] Abimouloud ML, Bensid K, Elleuch M, et al. Advancing breast cancer diagnosis: token vision transformers for faster and accurate classification of histopathology images[J]. Visual Computing for Industry, Biomedicine, and Art, 2025, 8(1): 1. [42] Wilkinson LS, Dunbar JK, Lip G. Clinical integration of artificial intelligence for breast imaging[J]. Radiologic Clinics, 2024, 62(4): 703-716.
