Artificial intelligence in determining the molecular biological subtype of breast cancer

Aim. To investigate the possibility of using radiation diagnostic data to determine various molecular subtypes of breast cancer (BC) using artificial intelligence technologies.

Materials and methods. The material for the study was retrospective data of 344 patients treated at the Sverdlovsk Regional Oncology Dispensary in the period from 2021 to 2023. The average age of the study sample was 56.8 ± 10.6 years, ranging from 33 to 82 years. All patients were diagnosed with BC, confirmed histologically. Molecular subtypes of BC were assessed based on trepan biopsy and surgical material. All patients underwent mammographic, ultrasound, and magnetic resonance imaging examinations, and sets of diagnostic features were identified that most accurately correspond to various molecular subtypes of BC. To achieve this goal, the authors identified the following diagnostic features: age, maximum diameter of the formation measured for various methods of radiation diagnostics, morphological features (contours, spatial orientation, shape of the detected formations or areas of reconstruction, heterogeneity of the structure of formations, presence of calcifications, characteristics of blood flow in the tumor) and dynamic parameters of paramagnetic accumulation during magnetic resonance imaging of the mammary gland.

Based on the histological examination data, the degree of tumor differentiation (G), proliferative activity index (Ki-67), regional lymph node status (presence or absence of metastases), and molecular-immunohistochemical tumor subtype were assessed. An analysis was conducted to determine whether there was a statistically significant relationship between diagnostic features and molecular subtypes of BC. The analysis was performed by conducting chi-square tests for features and subtypes (classes) of BC, previously converted to binary form. From the arrays of values s  elected for the study of diagnostic features, training and test samples were formed, and an algorithm for the classification model of artificial intelligence was determined. The accuracy of BC typing was ensured by using a combination of 7 diagnostic features and 6 classification models: five single-class and one multi-class. The gradient boosting algorithm (GradientBoostingRegressor) was used to train single-class models. The strategy “one (class) versus the rest” was used to train the multi-class model using the OneVsRestClassifier and gradient boosting (GradientBoostingClassifier) algorithms. The quality of the trained model was tested on test data. Statistical data processing, development of classification models, their testing and assessment of the quality of training were performed in the Jupyter Notebook environment v.6.5.2.

Results. The training quality indicators of single-class models for recognizing BC subtypes were as follows: sensitivity in determining luminal A subtype (LA) was 67.0 %, luminal B subtype (LB) – 72.7 %, luminal B HER2-positive subtype (LBH) – 81.8 %, non-luminal HER2-positive (HER) and triple negative breast cancer (TNC) – 100 %. The specificity was 90.2 % for LA, 83.0 % for LB, 89.7 % for LBH, 98.3 % and 93.5 % in the cases of HER and TNC, respectively.

The area under the ROC curve (AUC) depending on the molecular subtype was determined as follows: for LA – 0.88, for LB – 0.86, for LBH – 0.87, for HER – 0.96, and for TNC – 1.000. The multiclass model also showed low sensitivity values, except for the TNC (100 %) and HER (85.7 %) subtypes, low levels of positive predictive value for all subtypes, except for TNC (91.7 %), and high specificity and negative predictive value for all subtypes. The area under the ROC curve for the multiclass model was for the subtypes: LA – 0.88, LB – 0.86, LBH – 0.86, HER – 0.95 and for TNC – 1.00.

Conclusion. The possibility of using certain combinations of diagnostic features obtained as a result of radiation diagnostic methods to determine the probability of a molecular biological subtype of BC was proven. This indicates the presence of prerequisites for the creation of a new diagnostic tool for typing BC using classification models of artificial intelligence. In the future, its implementation will reduce the likelihood of an error in determining the molecular biological subtype of BC, especially in situations where the doctor»s opinion and the results of the immunohistochemical study do not coincide.

1. Ross J.S., Fletcher J.A., Linette G.P. et al. The HER2/neu gene and protein in breast cancer 2003: Biomarker and target of therapy. Oncologist 2003;8(4);307–25. DOI: 10.1634/theoncologist.8-4-307

2. Tsang J., Tse G. Molecular classification of breast cancer. Adv Anat Pathol 2020;27(1):27–35. DOI: 10.1097/PAP.0000000000000232

3. Gusterson B., Eaves C. Basal-like breast cancers: From pathology to biology and back again. Stem Cell Rep 2018;10(6):1676–86. DOI: 10.1016/j.stemcr.2018.04.023

4. Lehmann B., Abramson V., Sanders M. et al. TBCRC 032 IB/II multicenter study: Molecular insights to AR antagonist and PI3K inhibitor efficacy in patients with AR+ metastatic triple-negative breast cancer. Clin Cancer Res 2020;26(9):2111–23. DOI: 10.1158/1078-0432.CCR-19-2170

5. WHO Classification of Tumours Editorial Board. Breast Tumours: World Health Organization classification of tumours. 5th edn. Lyon: IARC Press, 2019. DOI: 10.1111/his.14091

6. Duffy S.W., Tabár L., Yen A.M. et al. Beneficial effect of consecutive screening mammography examinations on mortality from breast cancer: A prospective study. Radiology 2021;299(3);541–7. DOI: 1148/radiol.2021203935

7. Johnson K., Conat E., Soo M.S. Molecular subtypes of breast cancer: A review for breast radiologists. Breast Image 2021;3(1):12– 24. DOI: 10.1093/jbi/wbaa110

8. Hou X., Li X., Han Y. et al. Triple-negative breast cancer survival prediction using artificial intelligence through integrated analysis of tertiary lymphoid structures and tumor budding. Cancer 2024;130(S8):1499–512. DOI: 10.1002/cncr.35261

9. Liu Y., Zhen T., Fu Y. et al. AI-powered segmentation of invasive carcinoma regions in breast cancer immunohistochemical whole- slide images. Сancers (Basel) 2023;16(1):167. DOI: 10.3390/cancers16010167

10. Alekseeva M.G., Zubov A.I., Novikov M.Yu. Artificial Intelligence in Medicine. Mezhdunarodnyy nauchno-issledovatelskiy zhurnal = International Research Journal 2022;7(121). (In Russ.). DOI: 10.23670/IRJ.2022.121.7.038

11. Ostankovich A.A., Vayman S.D., Tananakin A.P. et al. Diagnostics of breast cancer using markers of digital mammography image processing. Baykalskiy meditsinskiy zhurnal = Baikal Medical Journal 2003;1(4):35–8. (In Russ.).

12. Sadykov S.S., Bulanova Yu.A., Sadykov Yu.A. et al. Automated processing and analysis of mammographic images: monograph. Vladimir: Izd-vo VlGU, 2014. 208 p. (In Russ.).

13. Pasynkov D.V., Klyushkin I.V., Busygina O.V. Method for increasing the sensitivity and specificity of systems for computer analysis of high-density mammographic images of breast parenchyma. Kazanskiy meditsinskiy zhurnal = Kazan Medical Journal 2016;97(3):444–9. (In Russ.). DOI: 10.17750/KMJ2016-443

14. Pospekhova N.I., Golovina D.A., Filippova M.G. et al. Molecular biological subtypes of breast cancer in carriers of mutations in the BRCA1 gene. Uspekhi molekulyarnoy onkologii = Advances in Molecular Oncology 2020;7(4):29–36. (In Russ.). DOI: 10.17650/2313-805X-2020-7-4-29-36

15. Pavlova N.V., Orlova V.S., Batlutskaya I.V. et al. The role of highly penetrant mutations in the BRCA1 and CHEK2 genes in the nature of associations of matrix metalloproteinase gene polymorphisms with breast cancer. Nauchnye rezultaty biomeditsinskikh issledovaniy = Scientific Results of Biomedical Research 2022;8(2);180–97. (In Russ.). DOI: 10.18413/2658-6533-2022-8-2-0-4

16. Zheng Sh., Yang Z., Du G. et al. Discrimination between HER2-overexpressing, -low-expressing, and -zero-expressing statuses in breast cancer using multiparametric MRI-based radiomics. Eur Radiol 2024;34(9):6132–44. DOI: 10.1007/s00330-024-10641-7

17. Song S.E., Cho K.R., Cho Y. et al. Machine learning with multiparametric breast MRI for prediction of Ki-67 and histologic grade in early-stage luminal breast cancer. Eur Radiol 2022;32(2):853–63. DOI: 10.1007/s00330-021-08127-x

18. Ma M., Liu R., Wen C. et al. Predicting the molecular subtype of breast cancer and identifying interpretable imaging features using machine learning algorithms. Eur Radiol 2022;32(3):1652–62. DOI: 10.1007/s00330-021-08271-4