基于快速深度卷积神经网络的乳腺钼靶影像分类方法

doi:10.3969/j.issn.0258-8021.2026.04.007

Abstract
Figure/Table
References
Related Citation (15)

Download: PDF (10553 KB) HTML (1 KB)
Export: BibTeX | EndNote (RIS)

Abstract Breast cancer is one of the most common cancers among women worldwide. Early detection, diagnosis and treatment are necessary to elevate survival rates and quality of life for breast cancer patients. Mammography has been recognized as the most popular modality for breast cancer screening. However, it is quite challenging to interpret mammograms accurately primarily due to the overlapping of tissues, under the universal screening model which yields a large number of mammographic images. Many methods have been developed for computer-aided diagnosis schemes to classify patients into benign and malignant with mammography. These models are useful for early breast cancer detection, while approaches are needed to improve accuracy and reduce the time and costs. In this paper, we proposed a new lightweight deep convolutional neural network to classify breast cancer rapidly with mammograms. A public digital database for screening mammography, the Digital Database for Screening Mammography (DDSM), was used in this study. The dataset contains 2 604 patients, of which 854 cases were pathologically confirmed benign, 141 cases were benign without callback, 914 patients were malignant confirmed by biopsy and pathology examinations and 695 were negative patients. We first enhanced the data with image processing methods including rotating, flipping, brightening, adding salt-and-pepper noise and Gaussian noise. The post-processing image dataset has 48 300 mammograms, including 5 208 original mammographic images and 43 092 enhanced images. We proposed a deep neural network model named classification of mammograms convolutional neural network (CMCNNet) by embedding VGGNet and inception modules to classify breast cancer with mammograms. Results showed that the new network architecture achieved an accuracy of 99.38% at a learning rate of 0.000 5. In addition, we figured out that when the number of convolution kernels was set to 32-32-32-32 corresponding to the convolutional layer group, and the size of the convolutional kernel was set to 3×3, the accuracy increased to 99.60%. Finally, the proposed model was validated on 48 300 mammographic images (2 604 patients). A three-fold cross-validation method was applied to different models using AlexNet, VGGNet, Inception-V3, ResNet, as well as the CMCNNet. Results showed that CMCNNet achieved an accuracy of 99.86% that outperformed all the other models adopted in this study with the same iteration numbers for training. In addition, the CMCNNet model needed the least training time. Results of the parameter optimization study and the new network model proposed in this paper have profound practical significance for the classification of breast cancer using mammography.

Key words： mammography breast cancer classification visual geometry group network (VGG) deep learning

Received: 10 December 2025

PACS:

R318

Corresponding Authors: ^*E-mail: yaneli@zafu.edu.cn

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	Cai Lvjun
	Fu Yixuan
	Ruan Yaoping
	Li Yane

Cite this article:

Cai Lvjun,Fu Yixuan,Ruan Yaoping, et al. A Fast Deep Convolutional Neural Network for Mammograms Classification[J]. Chinese Journal of Biomedical Engineering, 2026, 45(4): 469-481.

URL:

http://cjbme.csbme.org/EN/10.3969/j.issn.0258-8021.2026.04.007 OR http://cjbme.csbme.org/EN/Y2026/V45/I4/469

[1] Jemal A, Sung H, Kelly K, et al. The Cancer Atlas [M/OL] (第 4 版). Lyon: International Agency for Research on Cancer. https://www.iarc.who.int/cancer-atlas/. 2025-06/2025-11-02.
[2] Zhang Y, Ji Y, Liu S, et al. Global burden of female breast cancer: new estimates in 2022, temporal trend and future projections up to 2050 based on the latest release from GLOBOCAN[J]. Journal of the National Cancer Center, 2025, 5(3): 287-296.
[3] 牟思博, 周昌明, 郑莹. 2025年美国癌症统计数据解读及对中国癌症防治工作的借鉴意义[J]. 中国癌症杂志, 2025, 35(6): 523-530.
[4] Siegel RL, Miller KD, Fuchs HE. Cancer statistics, 2022[J]. CA Cancer J Clin, 2022, 72(1): 7-33.
[5] Ngan TT, Nguyen NTQ, Van Minh H. Effectiveness of clinical breast examination as a ‘standalone’ screening modality: an overview of systematic reviews[J]. BMC Cancer, 2020, 20: 1070.
[6] Siegel RL, Miller KD, Jemal A. Cancer statistics, 2020[J]. CA Cancer J Clin, 2020, 70(1): 7-30.
[7] Halperin EC, Wazer DE, Perez CA. Principles and Practice of Radiation Oncology [M] (7th Edition). Philadelphia: Lippincott Williams and Wilkins, 2018.
[8] Gram EG, Siersma V, Brodersen JB. Long-term psychosocial consequences of false-positive screening mammography: a cohort study with follow-up of 12-14 years in Denmark[J]. BMJ Open, 2023, 13(1): e072188.
[9] Yale Medicine. Dense breasts (Fact sheets)[EB/OL]. https://www.yalemedicine.org. 2022/2025-11-06.
[10] Xiong X, Zheng LW, Ding Y, et al. Breast cancer: pathogenesis and treatments[J]. Signal Transduction and Targeted Therapy, 2025, 10(1): 49.
[11] Zebari DA, Ibrahim DA, Zeebaree DQ, et al. Systematic review of computing approaches for breast cancer detection based computer aided diagnosis using mammogram images[J]. Applied Artificial Intelligence, 2021, 35(15): 2157-2203.
[12] Balali GI, Yar DD, Dela V, et al. Breast cancer: a review of mammography and clinical breast examination for early detection of cancer[J]. OA Lib J, 2020, 7(1): 1-19.
[13] Houssein EH, Emam MM, Ali AA. Deep and machine learning techniques for medical imaging-based breast cancer: a comprehensive review[J]. Expert Syst Appl, 2021, 167: 114161.
[14] Murtaza G, Shuib L, Abdul Wahab AW, et al. Deep learning-based breast cancer classification through medical imaging modalities: state of the art and research challenges[J]. Artif Intell Rev, 2020, 53(3): 1655-1720.
[15] 郑太雄, 江明哲, 冯明驰. 基于视觉的采摘机器人目标识别与定位方法研究综述[J]. 仪器仪表学报, 2021, 42(9): 28-51.
[16] Wickramasinghe I, Kalutarage H. Naive Bayes: applications, variations and vulnerabilities: a review of literature with code snippets for implementation[J]. Soft Computing, 2021, 25(3): 2277-2293.
[17] Hu J, Szymczak S. A review on longitudinal data analysis with random forest[J]. Briefings in Bioinformatics, 2023, 24: bbad002.
[18] Costa V G, Pedreira C E. Recent advances in decision trees: an updated survey[J]. Artificial Intelligence Review, 2023, 56(5): 4765-4800.
[19] Bjorland LS, Mahesparan R, Fluge Ø, et al. Impact of extent of resection on outcome from glioblastoma using the RANO resect group classification system: a retrospective, population-based cohort study[J]. Neuro-Oncology Advances, 2023, 5: vdad126.
[20] Jabeen K, Khan MA, Hameed MA, et al. A novel fusion framework of deep bottleneck residual convolutional neural network for breast cancer classification from mammogram images[J]. Frontiers in Oncology, 2024, 14: 1347856.
[21] Lou Q, Li Y, Qian Y, et al. Mammogram classification based on a novel convolutional neural network with efficient channel attention[J]. Comput Biol Med, 2022, 150(1): 106082.
[22] Jiang J, Peng J, Hu C, et al. Breast cancer detection and classification in mammogram using a three-stage deep learning framework based on PAA algorithm[J]. Artif Intell Med, 2022, 134(1): 102419.
[23] Patil RA, Dixit VV. Detection and classification of mammogram using ResNet-50[J]. Multimedia Tools and Applications, 2025: 1-24.
[24] Liao C, Wen X, Qi S, et al. FSE-Net: feature selection and enhancement network for mammogram classification[J]. Phys Med Biol, 2023, 68(12): 125009.
[25] Kermouni Serradj N, Messadi M, Lazzouni S. Classification of mammographic ROI for microcalcification detection using multifractal approach[J]. J Digit Imaging, 2022, 35(6): 1544-1559.
[26] Bouzar-Benlabiod L, Harrar K, Yamoun L, et al. A novel breast cancer detection architecture based on a CNN-CBR system for mammogram classification[J]. Comput Biol Med, 2023, 163(1): 107133.
[27] Rosadi MI, Fatichah C, Yuniarti A. The effect of batch size on the performance MobileNet-V3 model for breast cancer classification of ultrasound and mammography images[C]//2024 11th International Conference on Information Technology, Computer, and Electrical Engineering (ICITACEE). Semarang: IEEE, 2024: 54-58.
[28] Kayalvizhi R, Heartlin Maria H, Malarvizhi S, et al. Hardware deployment of deep learning model for classification of breast carcinoma from digital mammogram images[J]. Med Biol Eng Comput, 2023, 61(10): 2843-2857.
[29] Ullah A, Elahi H, Sun Z, et al. Comparative analysis of AlexNet, ResNet18 and SqueezeNet with diverse modification and arduous implementation[J]. Arab J Sci Eng, 2022, 47(2): 2397-2417.
[30] Zhang X. The AlexNet, LeNet-5 and VGG NET applied to CIFAR-10[C]//2021 2nd International Conference on Big Data & Artificial Intelligence & Software Engineering (ICBASE). Zhuhai: IEEE, 2021: 414-419.
[31] Si C, Yu W, Zhou P, et al. Inception transformer[J]. Advances in Neural Information Processing Systems, 2022, 35: 23495-23509.
[32] Koonce B. ResNet 50[M]//Convolutional Neural Networks with Swift for TensorFlow: Image Recognition and Dataset Categorization. Berkeley: Apress, 2021: 63-72.
[33] Punn NS, Agarwal S. Multi-modality encoded fusion with 3D inception U-net and decoder model for brain tumor segmentation[J]. Multimedia Tools and Applications, 2021, 80(20): 30305-30320.
[34] Sait ARW, Nagaraj R. An enhanced LightGBM-based breast cancer detection technique using mammography images[J]. Diagnostics (Basel), 2024, 14(2): 227.
[35] Kulkarni S, Rabidas R. Fully convolutional network for automated detection and diagnosis of mammographic masses[J]. Multimed Tools Appl, 2023, 92(9): 1-22.
[36] Du H, Yao MM, Liu S, et al. Automatic calcification morphology and distribution classification for breast mammograms with multi-task graph convolutional neural network[J]. IEEE J Biomed Health Inform, 2023, 27(6): 3782-3793.