Differentiating types of breast cancer from digital mammography images with artificial intelligence methods

Abstract

Objectives: Breast cancer (BCA) is one of the world’s most prevalent cancer and the top cause of mortality. For many decades, mammography has been used routinely for screening of early breast cancer and diagnosing symptomatic patients. The main purpose of this work is to investigate the usefulness of machine learning techniques using mammography images. Methods: A total of 194 patients who underwent ultrasound examination after observing suspicious lesions on mammography images and were diagnosed with BCA by ultrasound-guided core needle biopsy were included in the study. A set of mammography images with complete cancer subtypes was used. A transfer learning-based computer vision method was adopted in this study. AlexNet was to extract the features and select the most significant features using a feature selection function. Our deep learning-based model attained more than 80% accuracy in classifying malignant and benign cancers. However, the employed deep learning model cannot classify subtypes accurately. Results: Per the results, the commonly used image classification model is highly accurate in distinguishing malignant and benign changes, however unable to classify cancer subtypes. Conclusions: In conclusion, machine learning can still not simulate conventional immunohistochemistry subtyping using tissue biopsy.