Authors:
Lucia Lombardi
1
;
Myriam Giusy Tibaldi
1
;
Rachele Catalano
1
;
Mario Cesarelli
2
;
Antonella Santone
1
and
Francesco Mercaldo
1
Affiliations:
1
Department of Medicine and Health Sciences “Vincenzo Tiberio”, University of Molise, Campobasso, Italy
;
2
Department of Engineering, University of Sannio, Benevento, Italy
Keyword(s):
Artificial Intelligence, Deep Learning, Digital Pathology, Breast Cancer.
Abstract:
Breast cancer is the most prevalent cancer among women globally, making early and accurate detection essential for effective treatment and improved survival rates. This is the reason why, early and accurate breast cancer detection is crucial for proper treatment planning to save a life. This paper presents a method designed to detect and localize breast cancer using deep learning, specifically convolutional neural networks. The approach classifies histological images of breast tissue as either tumor-positive or tumor-negative. We utilize several deep learning models, including a custom-built CNN, EfficientNet, ResNet50, VGG-16, VGG-19, and MobileNet. Fine-tuning was also applied to VGG-16, VGG-19, and Mo bileNet to enhance performance. The aim is to provide a more effective network, able to correctly detect and localise breast cancer, that could support the physician in making clinical decisions. It could also prove to be a successful model to speed up the diagnostic process and dete
ct the possible presence of the disease at an early stage. Additionally, we introduce a novel deep learning model called MR Net, aimed at providing a more accurate network for breast cancer detection and localization, potentially assisting clinicians in making informed decisions. This model could also accelerate the diagnostic process, enabling early detection of the disease. Furthermore, we propose a method for explainable predictions by generating heatmaps that highlight the regions within tissue images that the model focuses on when predicting a label, revealing the detection of benign, atypical, and malignant tumors. We evaluate both the quantitative and qualitative performance of MR Net and the other models, also presenting explainable results that allow visualization of the tissue areas identified by the model as relevant to the presence of breast cancer.
(More)