Authors:
Adél Bajcsi
;
Camelia Chira
and
Annamária Szenkovits
Affiliation:
Babeș–Bolyai University, Cluj-Napoca, Cluj, Romania
Keyword(s):
Breast Lesion Classification, ResNet-50, Self-Explanatory Models, Mammogram Analysis.
Abstract:
Breast cancer is one of the leading causes of mortality among women diagnosed with cancer. In recent years, numerous computer-aided diagnosis (CAD) systems have been proposed for the classification of breast lesions. This study investigates self-explanatory deep learning models, namely BagNet and ProtoPNet, for the classification of breast abnormalities. Our aim is to train models to distinguish between benign and malignant lesions in breast tissue using publicly available datasets, namely MIAS and DDSM. The study provides a comprehensive numerical comparison of the two self-explanatory models and their respective backbones, as well as a visual evaluation of model performance. The results indicate that, while the backbone (black-box model) exhibits slightly better performance, it does so at the expense of interpretability. Conversely, BagNet, despite being a simpler model, achieves results comparable to those of ProtoPNet. In addition, transfer learning and data augmentation techniqu
es are employed to enhance the performance of the CAD system.
(More)