Role of morphologic magnetic resonance features in predicting lymphovascular invasion of malignant breast neoplasms by hybrid morpho-radiomic models

Purpose of the study: to improve the reliability of prediction of lymphovascular invasion (LVI) by hybrid morpho-radiomic naive Bayesian models in patients with malignant breast cancer (MBC) by elucidating the role of morphologic magnetic resonance (m-MR) features.

Materials and Methods. Data from 191 patients with MBC were analyzed in the form of 13 m-MR features, 6194 radiomic MR (r-MR) indicators of the whole tumor volume, and the target feature, LVI. Among the m-MR features, predictors of LVI were selected using crosstabulation, multivariate logistic regression, and Entropy-MDL discretization. Among 6194 r-MR indicators, predictors of LVI were selected by Entropy-MDL discretization. The selected indicators were used in training the naive Bayes algorithm. The performance of LVI predictors was compared.

Results. According to multivariate logistic regression, the odds of LVI increased when tumor rim feature was detected on DWI image 4.05-fold (OR 4.05, 95%CI: 1.63–10.47, p = 0.003), peritumoral edema 5.66-fold (OR 5.66, 95%CI: 2.27–14.94, p < 0.001). 3 hybrid models with high discriminatory abilities were obtained: 1 model with DWI rim and radiomic signature from 4 p-MR indicators (AUC = 0.886, sensitivity – 89.5%, specificity – 79.1%, classification correctness – 89.5%, correctness of prediction of LVI – 73.3% and its absence – 95.2%), 2 model with peritumoral edema and radiomic signature from 6 p-MR indicators (AUC = 0.879, sensitivity – 82.5%, specificity – 80,9%, classification correctness – 82.5%, correctness in predicting LVI – 80.0% and its absence – 83.3%) and 3 models with peritumoral edema, rim DWI sign and radiomic signature from 8 p-MR indicators (AUS = 0.957, sensitivity – 96.5%, specificity – 90.2%, classification correctness – 96.5%, correctness in predicting LVI – 86.7% and its absence – 100%). Removing the DWI rim feature from 1 model worsens its discriminatory power (AUC-ROC, 0.801 ± 0.074 vs 0.886 ± 0.059, p = 0.001) and correctness of LVI prediction (40 vs 73%, p = 0.066). Similar but less pronounced, non-statistically significant changes were observed after removal of the peritumoral edema feature from the 2 models (AUC-ROC, 0.843 ± 0.067 vs 0.879 ± 0.060, p = 0.190; LVI prediction correctness, 60 vs 80%, p = 0.232). Removing 2 m-MR features from the 3 model worsens its discriminatory power (AUC-ROC, 0.957 ± 0.038 vs 0.901 ± 0.055, p = 0.024) and correctness of LVI prediction (80 vs 86.7%, p = 0.624).

Conclusion. The use of hybrid models combining m-MR traits and r-MR indices improve the discriminatory power of prediction compared to models using only intratumoral r-MR indices.

1. Drzhevetskaya K.S., Korzhenkova G.P. Results of two years of mammographic screening in the Kaluga region. Bulletin of Radiology and Radiology. 2022; 103 (4–6): 18–27. https://doi.org/10.20862/0042-4676-2022-103-4-6-18-27 (In Russian)

2. Meskikh E.V., Nudnov N.V., Mukhutdinova G.Z., Vorobyeva V.O. Rare form of breast cancer and foci in the lung: should we always wait for metastases? Bulletin of Radiology and Radiology. 2022; 103 (4–6): 88–93. https://doi.org/10.20862/0042-4676-2022-103-4-6-88-93 (In Russian)

3. Tyurin I.E., Rozhkova N.I., Artamonova E.V. et al. The role of contrast methods of research in early diagnosis and treatment planning of breast cancer. Bulletin of Radiology and Radiology. 2024; 105 (2): 48–57. https://doi.org/10.20862/0042-4676-2024-105-2-48-57 (In Russian)

4. Sung H., Ferlay J., Siegel R.L. et al. Global Cancer Statistics 2020: GLOBOCAN Estimates of Incidence and Mortality Worldwide for 36 Cancers in 185 Countries. CA Cancer J. Clin. 2021; 71 (3): 209–249. https://doi.org/10.3322/caac.21660

5. Rakha E.A., Martin S., Lee A.H. et al. The prognostic significance of lymphovascular invasion in invasive breast carcinoma. Cancer. 2012; 118 (15): 3670–3680. https://doi.org/10.1002/cncr.26711

6. Rakha E.A., Abbas A., Pinto Ahumada P. et al. Diagnostic concordance of reporting lymphovascular invasion in breast cancer. J. Clin. Pathol. 2018; 71 (9): 802–805. https://doi.org/10.1136/jclinpath-2017-204981

7. Gujam F.J., Going J.J., Edwards J. et al. The role of lymphatic and blood vessel invasion in predicting survival and methods of detection in patients with primary operable breast cancer. Crit. Rev. Oncol. Hematol. 2014; 89 (2): 231–241. https://doi.org/10.1016/j.critrevonc.2013.08.014

8. Zhang S., Zhang D., Yi S. et al. The relationship of lymphatic vessel density, lymphovascular invasion, and lymph node metastasis in breast cancer: a systematic review and meta-analysis. Oncotarget. 2017; 8 (2): 2863–2873. https://doi.org/10.18632/oncotarget.13752

9. Zhong Y.M., Tong F., Shen J. Lympho-vascular invasion impacts the prognosis in breast-conserving surgery: a systematic review and meta-analysis. BMC Cancer. 2022; 22 (1): 102. https://doi.org/10.1186/s12885-022-09193-0

10. Pinder S.E., Ellis I.O., Galea M. et al. Pathological prognostic factors in breast cancer. III. Vascular invasion: Relationship with recurrence and survival in a large study with long-term follow-up. Histopathology. 1994; 24: 41–47. https://doi.org/10.1111/j.1365-2559.1994.tb01269.x

11. Ejlertsen B., Jensen M.B., Rank F. et al. Population-based study of peritumoral lymphovascular invasion and outcome among patients with operable breast cancer. J. Natl. Cancer Inst. 2009; 101: 729–735. https://doi.org/10.1093/jnci/djp090

12. Gajdos C., Tartter P.I., Bleiweiss I.J. Lymphatic invasion, tumor size, and age are independent predictors of axillary lymph node metastases in women with T1 breast cancers. Ann. Surg. 1999; 230: 692–696. https://doi.org/10.1097/00000658-199911000-00012

13. Viale G., Zurrida S., Maiorano E. et al. Predicting the status of axillary sentinel lymph nodes in 4351 patients with invasive breast carcinoma treated in a single institution. Cancer. 2005; 103: 492–500. https://doi.org/10.1002/cncr.20809

14. Uematsu T., Kasami M., Watanabe J. et al. Is lymphovascular invasion degree one of the important factors to predict neoadjuvant chemotherapy efficacy in breast cancer? Breast Cancer. 2011; 18 (4): 309–313. https://doi.org/10.1007/s12282-010-0211-z

15. Burstein H.J., Curigliano G., Thürlimann B. et al. Panelists of the St Gallen Consensus Conference Customizing local and systemic therapies for women with early breast cancer: The St. Gallen International Consensus Guidelines for treatment of early breast cancer 2021. Ann. Oncol. 2021; 32: 1216–1235. https://doi.org/10.1016/j.annonc.2021.06.023

16. Willems S.M., van Deurzen C.H., van Diest P.J. Diagnosis of breast lesions: fine-needle aspiration cytology or core needle biopsy? A review. J. Clin. Pathol. 2012; 65 (4): 287–292. https://doi.org/10.1136/jclinpath-2011-200410

17. Bulte J.P., Simsek D., Bult P. et al. Trends in pre-operative needle biopsy use in invasive breast cancer diagnosis: a Dutch nationwide population study. Acta Oncol. 2020; 59 (12): 1469–1473. https://doi.org/10.1080/0284186X.2020.1830168

18. Tripathi K., Yadav R., Maurya S.K. A Comparative Study Between Fine-Needle Aspiration Cytology and Core Needle Biopsy in Diagnosing Clinically Palpable Breast Lumps. Cureus. 2022; 14 (8): e27709. https://doi.org/10.7759/cureus.27709

19. Casaubon J.T., Tomlinson-Hansen S.E., Regan J.P. Fine Needle Aspiration of Breast Masses. 2023 Jul 23. In: StatPearls [Internet]. Treasure Island (FL): StatPearls Publishing; 2024 Jan–.

20. Gelezhe P.B., Blokhin I.A., Semenov S.S., Caruso D. Magnetic resonance imaging radiomics in prostate cancer: what is currently known? Digital Diagnostics. 2021; 2 (4): 441−452. https://doi.org/10.17816/DD70170 (In Russian)

21. Gelezhe P.B., Blokhin I.A., Semyonov S.S. Radiomics for diagnostics and treatment of prostate cancer. Medical Physics. 2022; 1 (93): 21. (In Russian)

22. Govorukhina V.G., Semyonov S.S., Gelezhe P.B. et al. Role of mammography in breast cancer radiomics. Digital Diagnostics. 2021; 2 (2): 185−199. https://doi.org/10.17816/DD70479 (In Russian)

23. Solodkiy V.A., Nudnov N.V., Ivannikov M.E. et al. Dosiomics in medical image analysis and prospects of its use in clinical practice. Digital Diagnostics. 2023; 4 (3): 340−355. https://doi.org/10.17816/DD420053 (In Russian)

24. Syrkashev E.M., Burov A.A., Podurovskaya Y.L. et al. Radiomics of fetal magnetic resonance imaging in congenital diaphragmatic hernia. Medical Visualization. 2024; 28 (1): 157–167. https://doi.org/10.24835/1607-0763-1359 (In Russian)

25. Ye D.M., Wang H.T., Yu T. The Application of Radiomics in Breast MRI: A Review. Technol Cancer Res Treat. 2020; 19: 1533033820916191. https://doi.org/10.1177/1533033820916191

26. Liu Z., Feng B., Li C. et al. Preoperative prediction of lymphovascular invasion in invasive breast cancer with dynamic contrast-enhanced-MRI-based radiomics. J. Magn. Reson. Imaging. 2019; 50 (3): 847–857. https://doi.org/10.1002/jmri.26688

27. Wu Z., Lin Q., Song H. et al. Evaluation of Lymphatic Vessel Invasion Determined by D2-40 Using Preoperative MRI-Based Radiomics for Invasive Breast Cancer. Acad. Radiol. 2023; 30 (11): 2458–2468. https://doi.org/10.1016/j.acra.2022.11.024

28. Zhang J., Wang G., Ren J. et al. Multiparametric MRI-based radiomics nomogram for preoperative prediction of lymphovascular invasion and clinical outcomes in patients with breast invasive ductal carcinoma. Eur. Radiol. 2022; 32 (6): 4079–4089. https://doi.org/10.1007/s00330-021-08504-6

29. Feng B., Liu Z., Liu Y. et al. Predicting lymphovascular invasion in clinically node-negative breast cancer detected by abbreviated magnetic resonance imaging: Transfer learning vs. radiomics. Front. Oncol. 2022; 12: 890659. https://doi.org/10.3389/fonc.2022.890659.

30. Jiang Y., Zeng Y., Zuo Z. et al. Leveraging multimodal MRI-based radiomics analysis with diverse machine learning models to evaluate lymphovascular invasion in clinically node-negative breast cancer. Heliyon. 2023; 10 (1): e23916. https://doi.org/10.1016/j.heliyon.2023.e23916

31. Ma Q., Li Z., Li W. et al. MRI radiomics for the preoperative evaluation of lymphovascular invasion in breast cancer: A meta-analysis Eur. J. Radiol. 2023; 168, art. no. 111127

32. Jiang D., Qian Q., Yang X. et al. Machine learning based on optimal VOI of multi-sequence MR images to predict lymphovascular invasion in invasive breast cancer. Heliyon. 2024; 10 (7): e29267. https://doi.org/10.1016/j.heliyon.2024.e29267

33. van Griethuysen J.J., Fedorov A., Parmar C. et al. Computational radiomics system to decode the radiographic phenotype. Cancer Res. 2017; 77 (21): e104–e107.

34. Aurélien J. Applied machine learning with Scikit-Learn and TensorFlow: concepts, tools and techniques for creating intelligent systems: Translated from English. SPB: LLC “Alfa-book”, 2018. 688 р. (In Russian)

35. Glassner E. Deep learning without math. Т. 1: Fundamentals: Translated from English by V.Y. Yarotsky. Moscow: DMK Press, 2019. 584 р. (In Russian)

36. Burkov A. Machine learning without unnecessary words. SPb: Peter, 2020. 192 р. (In Russian)

37. GOST P 53022.3–2008. Clinical laboratory technologies. Requirements for the quality of clinical laboratory tests. Part 3. Rules for assessment of clinical informativeness of laboratory tests. Moscow: Standardinform, 2008. 26 р. (In Russian)

38. Vasiliev Y.A. et al. Computer vision in radiation diagnostics: the first stage of the Moscow experiment: Monograph. 2nd edition, revised and supplemented. Moscow: Publishing Solutions, 2023. 376 р. (In Russian)

39. Tyrov I.A., Vasiliev Y.A., Arzamasov K.M. et al. Assessment of maturity of artificial intelligence technologies for healthcare: methodology and its application on the materials of the Moscow experiment on computer vision in radiation diagnostics. Physician and Information Technology. 2022; 4: 76–92. https://doi.org/10.25881/18110193_2022_4_76 (In Russian)

40. Cheon H., Kim H.J., Lee S.M. et al. Preoperative MRI features associated with lymphovascular invasion in node-negative invasive breast cancer: a propensity-matched analysis. J. Magn. Reson. Imaging. 2017; 46 (4): 1037–1044. https://doi.org/10.1002/jmri.25710

41. Harada T.L., Uematsu T., Nakashima K. et al. Evaluation of Breast Edema Findings at T2-weighted Breast MRI Is Useful for Diagnosing Occult Inflammatory Breast Cancer and Can Predict Prognosis after Neoadjuvant Chemotherapy. Radiology. 2021; 299 (1): 53–62. https://doi.org/10.1148/radiol.2021202604

42. Lee H.J., Lee J.E., Jeong W.G. et al. HER2-Positive Breast Cancer: Association of MRI and Clinicopathologic Features With Tumor-Infiltrating Lymphocytes. Am. J. Roentgenol. 2022; 218 (2): 258–269. https://doi.org/10.2214/AJR.21.26400

43. Choi B.B. Dynamic contrast enhanced-MRI and diffusion-weighted image as predictors of lymphovascular invasion in node-negative invasive breast cancer. Wld J. Surg. Oncol. 2021; 19 (1): 76. https://doi.org/10.1186/s12957-021-02189-3

44. Kang B.J., Lipson J.A., Planey K.R. et al. Rim sign in breast lesions on diffusion-weighted magnetic resonance imaging: diagnostic accuracy and clinical usefulness. J. Magn. Reson. Imaging. 2015; 41 (3): 616–623. https://doi.org/10.1002/jmri.24617

45. Choi Y., Kim S.H., Youn I.K. et al. Rim sign and histogram analysis of apparent diffusion coefficient values on diffusion-weighted MRI in triple-negative breast cancer: comparison with ER-positive subtype. Plos One. 2017; 12: e0177903. https://doi.org/10.1371/journal.pone.0177903