Abstract：Breast cancer is a highly prevalent malignancy among women globally and exhibits significant clinical characteristic differences across ethnic groups. However, studies on the imaging features of breast cancer in different ethnic populations remain limited. This study included 366 breast cancer patients from multiple ethnic groups (153 Han, 134 Tibetan, and 79 Yi) and analyzed the clinical and imaging characteristics of each group, aiming to explore cross-ethnic differences and provide evidence for personalized diagnosis and treatment. Using clinical pathological data and mammography data, deep learning models based on ResNet networks of varying depths were developed for multi-ethnic classification and Ki-67 prediction. The results indicated that, compared to Han patients, Tibetan and Yi patients were diagnosed at younger ages (P<0.05) and exhibited significantly higher breast density. Tibetan patients also showed a higher proportion of HER2 positivity. In the multi-ethnic classification task, the ResNet34 model demonstrated the best classification performance, with a macro-average AUC of 0.880 on test data (Han: 0.911, Tibetan: 0.974, Yi: 0.742). Model visualization revealed that the model focused more on glandular regions for Tibetan patients, whereas it paid more attention to tumor regions for Han patients. In the multi-ethnic Ki-67 prediction task, the ethnicity-specific models (Han AUC=0.820, Tibetan AUC=0.842, Yi AUC=0.970) significantly outperformed the mixed-ethnic model (AUC=0.818), with the Yi model showing the most substantial improvement in predictive performance. In conclusion, significant differences existed in clinical and imaging features of the breast cancer patients across ethnic groups. The ethnicity-specific deep learning prediction models showed superior performance in assessing the Ki-67 proliferation index, offering valuable insights for the development of personalized diagnostic and treatment strategies for breast cancer patients from different ethnic backgrounds.
王云飞, 范明, 周鹏, 厉力华. 基于深度学习的多民族乳腺X线摄影诊断分析研究[J]. 中国生物医学工程学报, 2025, 44(5): 541-550.
Wang Yunfei, Fan Ming, Zhou Peng, Li Lihua. Multi-Ethnic Mammographic Diagnosis Analysis Based on Deep Learning. Chinese Journal of Biomedical Engineering, 2025, 44(5): 541-550.
[1] Siegel RL, Miller KD, Wagle NS, et al.Cancer statistics, 2023[J].CA Cancer J Clin, 2023, 73(1): 17-48. [2] Hirko KA, Rocque G, Reasor E, et al.The impact of race and ethnicity in breast cancer-disparities and implications for precision oncology[J].BMC Med, 2022, 20(1): 72. [3] Lei S, Zheng R, Zhang S, et al.Global patterns of breast cancer incidence and mortality: A population-based cancer registry data analysis from 2000 to 2020[J].Cancer Commun (Lond), 2021, 41(11): 1183-1194. [4] Ozdemir BC, Dotto GP.Racial differences in cancer susceptibility and survival: more than the color of the skin?[J].Trends Cancer, 2017, 3(3): 181-197. [5] Hoskins KF, Danciu OC, Ko NY, et al.Association of race/ethnicity and the 21-gene recurrence score with breast cancer-specific mortality among US women[J].JAMA Oncol, 2021, 7(3): 370-378. [6] Yedjou CG, Sims JN, Miele L, et al.Health and racial disparity in breast cancer[J].Adv Exp Med Biol, 2019, 1152: 31-49. [7] Bansil S, Silva A, Taniguchi A, et al.Racial/ethnic differences among tumor-infiltrating lymphocytes in breast cancer tumors[J].Oncologist, 2023, 28(2): 116-122. [8] 曹天泽.中国人群乳腺癌的临床病理特点与民族差异性研究[D].武汉:武汉大学, 2018. [9] 成芳, 张茜.新疆2019例汉族 、维吾尔族乳腺癌临床病理资料分析[J].肿瘤防治研究, 2010, 37(11): 1312-1314. [10] 丛亚婷, 孙婧, 郑娅楠.内蒙古地区蒙古族与汉族乳腺癌患者病理学特点分析及差异性研究[J].内蒙古医学杂志, 2021, 53(3): 253-260. [11] 龙欣甜, 文洪梅, 李云飞, 等.云南省23354例乳腺癌患者生存状况分析[J].实用肿瘤杂志, 2025, 40(1): 6-13. [12] 李欣欣, 姚娟, 陈鹰, 等.新疆维吾尔族和汉族女性乳腺癌患者钼靶 X 线表现与免疫组织化学指标表达差异[J].中华实用诊断与治疗杂志, 2018, 32(11): 1068-1070. [13] 周晓峰, 张英轸, 任登峰, 等.青海地区女性乳腺癌术后临床病理特征及预后因素分析[J].中华肿瘤防治杂志, 2022, 29(4): 253-261. [14] Mao N, Yin P, Wang Q, et al.Added value of radiomics on mammography for breast cancer diagnosis: a feasibility study[J].J Am Coll Radiol, 2019, 16(4 Pt A): 485-491. [15] Hong S, Song SY, Park B, et al.Effect of digital mammography for breast cancer screening: a comparative study of more than 8 million korean women[J].Radiology, 2020, 294(2): 247-255. [16] Isensee F, Jaeger PF, Kohl SA A, et al.nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation[J].Nat Methods, 2021, 18(2): 203-211. [17] Goldhirsch A, Wood WC, Coates AS, et al.Strategies for subtypes--dealing with the diversity of breast cancer: highlights of the St.Gallen International Expert Consensus on the Primary Therapy of Early Breast Cancer 2011[J].Ann Oncol, 2011, 22(8): 1736-1747. [18] Zeng W.Image data augmentation techniques based on deep learning: a survey[J].Math Biosci Eng, 2024, 21(6): 6190-6224. [19] He K, Zhang X, Ren S, et al.Deep residual learning for image recognition[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Las Vegas:IEEE, 2016: 770-778. [20] 王雯, 王成辉, 张巍.维、汉女性患者乳腺癌的分子分型及临床特征的比较分析[J].新疆医科大学学报, 2012, 35(9): 1172-1174. [21] John EM, McGuire V, Kurian AW, et al.Racial/ethnic disparities in survival after breast cancer diagnosis by estrogen and progesterone receptor status: a pooled analysis[J].Cancer Epidem Biomar, 2021, 30(2): 351-363. [22] 国家统计局.中国统计年鉴[M].北京:中国统计出版社, 2021. [23] 杨兆龙.四川人口的民族构成与分布特征[J].人口学刊, 1988 (1): 24-29. [24] 罗正富, 李文碧.四川少数民族的构成、人口分布特征及形成原因[J].西南师范大学学报(哲学社会科学版), 1994(3): 13-15. [25] 王光进, 张悦, 刘冶容.甘孜州藏族与彝族结膜囊细菌状况对照研究[J].国际眼科杂志, 2013, 13(1): 142-144. [26] Akanji MA, Rotimi D, Adeyemi OS.Hypoxia-inducible factors as an alternative source of treatment strategy for cancer[J].Oxid Med Cell Longev, 2019, 2019: 8547846. [27] Calderon-Gerstein WS, Torres-Samaniego G.High altitude and cancer: an controversy[J].Respir Physiol Neurobiol, 2021, 289: 103655. [28] Banys-Paluchowski M, Witzel I, Riethdorf S, et al.The clinical relevance of serum vascular endothelial growth factor (VEGF) in correlation to circulating tumor cells and other serum biomarkers in patients with metastatic breast cancer[J].Breast Cancer Res Treat, 2018, 172(1): 93-104. [29] Zhang H, Niu S, Chen H, et al.Radiomics signatures for predicting the Ki-67 level and HER-2 status based on bone metastasis from primary breast cancer[J].Frontiers in Cell and Developmental Biology, 2024, 11:1220320. [30] Panico A, Gatta G, Salvia A, et al.Radiomics in breast imaging: future development[J].J Pers Med, 2023, 13(5):862. [31] Posso M, Louro J, Sanchez M, et al.Mammographic breast density: How it affects performance indicators in screening programmes?[J].Eur J Radiol, 2019, 110: 81-87. [32] Bird RE, Wallace TW, Yankaskas BC.Analysis of cancers missed at screening mammography[J].Radiology, 1992, 184(3): 613-617.
