A new prediction model of triple-negative breast cancer based on ultrasound radiomics

Background: This study aims to assess the diagnostic potential of a radiomics model based on ultrasonic imaging and characteristics for triple-negative breast cancer (TNBC). Methods: We retrospectively assessed the data of 127 patients with breast tumors, dividing them into training (n = 88) and testing (n = 39) sets. Four machine learning (ML) algorithms were employed, and we compared three distinct prediction models. Accuracy, sensitivity, specificity and the area under the receiver operating characteristic curve (AUC) served as the metrics for evaluating the predictive capacity of these models for TNBC. Results: Multivariate logistic regression analysis identified margin (odds ratio (OR) 0.296; 95% confidence interval (CI) 0.127–0.692; p = 0.005) and posterior echo (OR 0.323; 95% CI 0.112–0.930; p = 0.036) as independent TNBC predictors. We selected thirteen key image features to construct an ultrasonic imaging radiomics model. In the ultrasonic imaging radiomics model, the AUC values for logistic regression (LR), support vector machine (SVM), decision tree (DT), and random forest (RF) were 0.78, 0.80, 0.84 and 0.95 for the training set, and 0.68, 0.55, 0.71 and 0.65 for the testing set, respectively. In the ultrasonic feature model, the AUC values for LR, SVM, DT and RF were 0.73, 0.54, 0.73 and 0.73 for the training set, and 0.58, 0.82, 0.59 and 0.60 for the testing set, respectively. In the comprehensive model, which combines ultrasonic feature and radiomics feature models, the AUC values for LR, SVM, DT and RF were 0.85, 0.92, 0.78 and 0.92 for the training set, and 0.64, 0.69, 0.63 and 0.76 for the testing set, respectively. Conclusions: Compared with ultrasonic feature and radiomics feature models, the comprehensive model demonstrated better diagnostic performance and could identify TNBC more effectively.

Radiomics; Triple-negative breast cancer (TNBC); Ultrasound; Prediction mode; Machine learning

[1] Sung H, Ferlay J, Siegel RL, Laversanne M, Soerjomataram I, Jemal A, et al. Global cancer statistics 2020: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA: A Cancer Journal for Clinicians. 2021; 71: 209–249.

[2] Ma M, Liu R, Wen C, Xu W, Xu Z, Wang S, et al. Predicting the molecular subtype of breast cancer and identifying interpretable imaging features using machine learning algorithms. European Radiology. 2022; 32: 1652–1662.

[3] Li Y, Zhang H, Merkher Y, Chen L, Liu N, Leonov S, et al. Recent advances in therapeutic strategies for triple-negative breast cancer. Journal of Hematology & Oncology. 2022; 15: 121.

[4] Derakhshan F, Reis-Filho JS. Pathogenesis of triple-negative breast cancer. Annual Review of Pathology: Mechanisms of Disease. 2022; 17: 181–204.

[5] Freitas AJA, Causin RL, Varuzza MB, Calfa S, Hidalgo Filho CMT, Komoto TT, et al. Liquid biopsy as a tool for the diagnosis, treatment, and monitoring of breast cancer. International Journal of Molecular Sciences. 2022; 23: 9952.

[6] Gao Y, Luo Y, Zhao C, Xiao M, Ma L, Li W, et al. Nomogram based on radiomics analysis of primary breast cancer ultrasound images: prediction of axillary lymph node tumor burden in patients. European Radiology. 2021; 31: 928–937.

[7] Zhang X, Zhang Y, Zhang G, Qiu X, Tan W, Yin X, et al. Deep learning with radiomics for disease diagnosis and treatment: challenges and potential. Frontiers in Oncology. 2022; 12: 773840.

[8] Greener JG, Kandathil SM, Moffat L, Jones DT. A guide to machine learning for biologists. Nature Reviews Molecular Cell Biology. 2022; 23: 40–55.

[9] Arfat Y, Mittone G, Esposito R, Cantalupo B, De Ferrari Gm, Aldinucci M. Machine learning for cardiology. Minerva Cardiology and Angiology. 2022; 70: 75–91.

[10] Wagner MW, Namdar K, Biswas A, Monah S, Khalvati F, Ertl-Wagner BB. Radiomics, machine learning, and artificial intelligence—what the neuroradiologist needs to know. Neuroradiology. 2021; 63: 1957–1967.

[11] Gong X, Wang L, Miao L, Chen N, Li J. PIMedSeg: progressive interactive medical image segmentation. Computer Methods and Programs in Biomedicine. 2023; 241: 107776.

[12] van Griethuysen JJM, Fedorov A, Parmar C, Hosny A, Aucoin N, Narayan V, et al. Computational radiomics system to decode the radiographic phenotype. Cancer Research. 2017; 77: e104–e107.

[13] Stoltzfus JC. Logistic regression: a brief primer. Academic Emergency Medicine. 2011; 18: 1099–1104.

[14] Flayer CH, Perner C, Sokol CL. A decision tree model for neuroimmune guidance of allergic immunity. Immunology & Cell Biology. 2021; 99: 936–948.

[15] Rigatti SJ. Random Forest. Journal of Insurance Medicine. 2017; 47: 31–39.

[16] Katsura C, Ogunmwonyi I, Kankam HK, Saha S. Breast cancer: presentation, investigation and management. British Journal of Hospital Medicine. 2022; 83: 1–7.

[17] Kawiak A. Molecular research and treatment of breast cancer. International Journal of Molecular Sciences. 2022; 23: 9617.

[18] Wojcinski S, Soliman AA, Schmidt J, Makowski L, Degenhardt F, Hillemanns P. Sonographic features of triple-negative and non-triple-negative breast cancer. Journal of Ultrasound in Medicine. 2012; 31: 1531–1541.

[19] Yang Q, Liu H, Liu D, Song Y. Ultrasonographic features of triple-negative breast cancer: a comparison with other breast cancer subtypes. Asian Pacific Journal of Cancer Prevention. 2015; 16: 3229–3232.

[20] Li Z, Tian J, Wang X, Wang Y, Wang Z, Zhang L, et al. Differences in multi-modal ultrasound imaging between triple negative and non-triple negative breast cancer. Ultrasound in Medicine & Biology. 2016; 42: 882–890.

[21] Wang D, Zhu K, Tian J, Li Z, Du G, Guo Q, et al. Clinicopathological and ultrasonic features of triple-negative breast cancers: a comparison with hormone receptor-positive/human epidermal growth factor receptor-2-negative breast cancers. Ultrasound in Medicine & Biology. 2018; 44: 1124–1132.

[22] Tian L, Wang L, Qin Y, Cai J. Systematic review and meta-analysis of the malignant ultrasound features of triple-negative breast cancer. Journal of Ultrasound in Medicine. 2020; 39: 2013–2025.

[23] Gillies RJ, Kinahan PE, Hricak H. Radiomics: images are more than pictures, they are data. Radiology. 2016; 278: 563–577.

[24] Sha YS, Chen JF. MRI-based radiomics for the diagnosis of triple-negative breast cancer: a meta-analysis. Clinical Radiology. 2022; 77: 655–663.

[25] Feng Q, Hu Q, Liu Y, Yang T, Yin Z. Diagnosis of triple negative breast cancer based on radiomics signatures extracted from preoperative contrast-enhanced chest computed tomography. BMC Cancer. 2020; 20: 579.

[26] Ge S, Yixing Y, Jia D, Ling Y. Application of mammography-based radiomics signature for preoperative prediction of triple-negative breast cancer. BMC Medical Imaging. 2022; 22: 166.

[27] Galal A, Talal M, Moustafa A. Applications of machine learning in metabolomics: disease modeling and classification. Frontiers in Genetics. 2022; 13: 1017340.