MORPHOLOGICAL PREDICTORS OF BREAST TUMOUR MALIGNANCY BASED ON CELLULAR NUCLEAR CHARACTERISTICS
DOI:
https://doi.org/10.69980/54m2ph07Keywords:
Breast cancer, Nuclear morphology, Histopathology, Logistic regression, Digital pathologyAbstract
Breast cancer (BC) remains one of the leading causes of cancer-related morbidity and mortality among women worldwide. Quantitative assessment of cellular nuclear morphology has emerged as a promising approach for improving the accuracy and objectivity of breast tumour diagnosis while supporting computational pathology and artificial intelligence-assisted diagnostic systems. A secondary analytical cross-sectional study was conducted using the publicly available BC Wisconsin (Diagnostic) Dataset comprising 569 breast tumour cases, including 357 benign and 212 malignant lesions. Thirty nuclear morphological characteristics were evaluated and categorized into mean, standard error, and worst measurements. Descriptive statistics, Welch's independent samples t-test with Benjamini–Hochberg correction, Pearson correlation analysis, and multivariable binary logistic regression were performed to identify independent predictors of breast tumour malignancy. Malignant tumours demonstrated significantly greater nuclear size, irregularity, and structural complexity than benign tumours across most morphological variables. Worst nuclear characteristics exhibited the strongest discriminatory ability, while correlation analysis revealed strong associations among several nuclear size and boundary-related features. After adjustment for multicollinearity, area worst, texture worst, perimeter standard error, smoothness worst, concavity worst, concave points standard error, symmetry worst, and compactness standard error were identified as independent predictors of breast tumour malignancy. Quantitative nuclear morphological characteristics provide reliable and objective indicators for distinguishing benign from malignant breast tumours. The identified independent predictors may support computer-assisted diagnosis, digital pathology, and artificial intelligence-based clinical decision-support systems, contributing to improved diagnostic consistency and advancing precision oncology.
References
1. Alizadeh, E., Castle, J., Quirk, A., Taylor, C. D., Xu, W., & Prasad, A. (2020). Cellular morphological features are predictive markers of cancer cell state. Computers in biology and medicine, 126, 104044.
2. Binder, A., Bockmayr, M., Hägele, M., Wienert, S., Heim, D., Hellweg, K., ... & Klauschen, F. (2021). Morphological and molecular breast cancer profiling through explainable machine learning. Nature Machine Intelligence, 3(4), 355-366.
3. Cserni, G., Quinn, C. M., Foschini, M. P., Bianchi, S., Callagy, G., Chmielik, E., ... & European Working Group for Breast Screening Pathology. (2021). Triple-negative breast cancer histological subtypes with a favourable prognosis. Cancers, 13(22), 5694.
4. Das, A., Nair, M. S., & Peter, S. D. (2020). Computer-aided histopathological image analysis techniques for automated nuclear atypia scoring of breast cancer: a review. Journal of digital imaging, 33(5), 1091-1121.
5. do Nascimento, R. G., & Otoni, K. M. (2020). Histological and molecular classification of breast cancer: what do we know?. Mastology, 30, 1-8.
6. Dodington, D. W., Lagree, A., Tabbarah, S., Mohebpour, M., Sadeghi-Naini, A., Tran, W. T., & Lu, F. I. (2021). Analysis of tumor nuclear features using artificial intelligence to predict response to neoadjuvant chemotherapy in high-risk breast cancer patients. Breast Cancer Research and Treatment, 186(2), 379-389.
7. Fischer, E. G. (2020). Nuclear morphology and the biology of cancer cells. Acta cytologica, 64(6), 511-519.
8. Heng, Y. J., Lester, S. C., Tse, G. M., Factor, R. E., Allison, K. H., Collins, L. C., ... & Beck, A. H. (2017). The molecular basis of breast cancer pathological phenotypes. The Journal of pathology, 241(3), 375-391.
9. Jia-Mei, C., Li, Y., Xu, J., Gong, L., Lin-Wei, W., Wen-Lou, L., & Liu, J. (2017). Computer-aided prognosis on breast cancer with hematoxylin and eosin histopathology images: A review. Tumor Biology, 39(3).
10. Katayama, A., Toss, M. S., Parkin, M., Sano, T., Oyama, T., Quinn, C. M., ... & Rakha, E. A. (2022). Nuclear morphology in breast lesions: refining its assessment to improve diagnostic concordance. Histopathology, 80(3), 515-528.
11. Lu, C., Lewis, J. S., Dupont, W. D., Plummer, W. D., Janowczyk, A., & Madabhushi, A. (2017). An oral cavity squamous cell carcinoma quantitative histomorphometric-based image classifier of nuclear morphology can risk stratify patients for disease-specific survival. Modern Pathology, 30(12), 1655-1665.
12. Lu, C., Romo-Bucheli, D., Wang, X., Janowczyk, A., Ganesan, S., Gilmore, H., ... & Madabhushi, A. (2018). Nuclear shape and orientation features from H&E images predict survival in early-stage estrogen receptor-positive breast cancers. Laboratory investigation, 98(11), 1438-1448.
13. Masood, S. (2016). Breast cancer subtypes: morphologic and biologic characterization. Women’s Health, 12(1), 103-119.
14. McCaffrey, C., Jahangir, C., Murphy, C., Burke, C., Gallagher, W. M., & Rahman, A. (2024). Artificial intelligence in digital histopathology for predicting patient prognosis and treatment efficacy in breast cancer. Expert review of molecular diagnostics, 24(5), 363-377.
15. Mercan, C., Balkenhol, M., Salgado, R., Sherman, M., Vielh, P., Vreuls, W., ... & Ciompi, F. (2022). Deep learning for fully-automated nuclear pleomorphism scoring in breast cancer. NPJ breast cancer, 8(1), 120.
16. Mi, H., Bivalacqua, T. J., Kates, M., Seiler, R., Black, P. C., Popel, A. S., & Baras, A. S. (2021). Predictive models of response to neoadjuvant chemotherapy in muscle-invasive bladder cancer using nuclear morphology and tissue architecture. Cell Reports Medicine, 2(9).
17. Rajbongshi, N., Bora, K., Nath, D. C., Das, A. K., & Mahanta, L. B. (2018). Analysis of morphological features of benign and malignant breast cell extracted from fnac microscopic image using the pearsonian system of curves. Journal of cytology, 35(2), 99-104.
18. Rawat, R. R., Ruderman, D., Macklin, P., Rimm, D. L., & Agus, D. B. (2018). Correlating nuclear morphometric patterns with estrogen receptor status in breast cancer pathologic specimens. NPJ Breast Cancer, 4(1), 32.
19. Sanati, S. (2019). Morphologic and molecular features of breast ductal carcinoma in situ. The American journal of pathology, 189(5), 946-955.
20. Singh, I., & Lele, T. P. (2022). Nuclear morphological abnormalities in cancer: a search for unifying mechanisms. In Nuclear, chromosomal, and genomic architecture in biology and medicine (pp. 443-467). Cham: Springer International Publishing.
21. Turkki, R., Byckhov, D., Lundin, M., Isola, J., Nordling, S., Kovanen, P. E., ... & Linder, N. (2019). Breast cancer outcome prediction with tumour tissue images and machine learning. Breast cancer research and treatment, 177(1), 41-52.
22. UCI Machine Learning. (2016). Breast Cancer Wisconsin (Diagnostic) Data Set [Data set]. Kaggle. https://www.kaggle.com/datasets/uciml/breast-cancer-wisconsin-data
23. Whitney, J., Corredor, G., Janowczyk, A., Ganesan, S., Doyle, S., Tomaszewski, J., ... & Madabhushi, A. (2018). Quantitative nuclear histomorphometry predicts oncotype DX risk categories for early stage ER+ breast cancer. BMC cancer, 18(1), 610.
24. Zhao, S., Chen, D. P., Fu, T., Yang, J. C., Ma, D., Zhu, X. Z., ... & Shao, Z. M. (2023). Single-cell morphological and topological atlas reveals the ecosystem diversity of human breast cancer. Nature Communications, 14(1), 6796.
