Machine learning analysis of breast ultrasound to classify triple negative and HER2+ breast cancer subtypes

Article type: Research Article

Authors: Ferre, Romuald^a; | Elst, Janne^a | Senthilnathan, Seanthan^a | Lagree, Andrew^b | Tabbarah, Sami^b | Lu, Fang-I^c | Sadeghi-Naini, Ali^d | Tran, William T.^{b; e; f} | Curpen, Belinda^{a; g}

Affiliations: [a] Department of Medical Imaging, Sunnybrook Health Sciences Centre, Toronto, ON, Canada | [b] Department of Radiation Oncology, Sunnybrook Health Sciences Centre, Toronto, ON, Canada | [c] Department of Laboratory Medicine and Molecular Diagnostics, Sunnybrook Health Sciences Centre, Toronto, ON, Canada | [d] Department of Electrical Engineering and Computer Science, York University, Toronto, ON, Canada | [e] Department of Radiation Oncology, University of Toronto, Toronto, ON, Canada | [f] Temerty Centre for AI Research and Education, University of Toronto, ON, Canada | [g] Department of Medical Imaging, University of Toronto, Toronto, ON, Canada

Correspondence: [*] Corresponding author: Romuald Ferre, Department of Medical Imaging, Sunnybrook Health Sciences Centre, 2075 Bayview Avenue, Toronto, ON, M4N 3M5, Canada. Tel.: +1 (416) 480 6130. E-mail: romuald.ferre@gmail.com

Abstract: OBJECTIVES:Early diagnosis of triple-negative (TN) and human epidermal growth factor receptor 2 positive (HER2+) breast cancer is important due to its increased risk of micrometastatic spread necessitating early treatment and for guiding targeted therapies. This study aimed to evaluate the diagnostic performance of machine learning (ML) classification of newly diagnosed breast masses into TN versus non-TN (NTN) and HER2+ versus HER2 negative (HER2−) breast cancer, using radiomic features extracted from grayscale ultrasound (US) b-mode images. MATERIALS AND METHODS:A retrospective chart review identified 88 female patients who underwent diagnostic breast US imaging, had confirmation of invasive malignancy on pathology and receptor status determined on immunohistochemistry available. The patients were classified as TN, NTN, HER2+ or HER2− for ground-truth labelling. For image analysis, breast masses were manually segmented by a breast radiologist. Radiomic features were extracted per image and used for predictive modelling. Supervised ML classifiers included: logistic regression, k-nearest neighbour, and Naïve Bayes. Classification performance measures were calculated on an independent (unseen) test set. The area under the receiver operating characteristic curve (AUC), sensitivity (%), and specificity (%) were reported for each classifier. RESULTS:The logistic regression classifier demonstrated the highest AUC: 0.824 (sensitivity: 81.8%, specificity: 74.2%) for the TN sub-group and 0.778 (sensitivity: 71.4%, specificity: 71.6%) for the HER2 sub-group. CONCLUSION:ML classifiers demonstrate high diagnostic accuracy in classifying TN versus NTN and HER2+ versus HER2− breast cancers using US images. Identification of more aggressive breast cancer subtypes early in the diagnostic process could help achieve better prognoses by prioritizing clinical referral and prompting adequate early treatment.

Keywords: Machine learning, ultrasound, triple negative breast cancer, HER2+ breast cancer

DOI: 10.3233/BD-220018

Journal: Breast Disease, vol. 42, no. 1, pp. 59-66, 2023