USING RESNET18 IN A DEEP-LEARNING FRAMEWORK AND ASSESSING THE EFFECTS OF ADAPTIVE LEARNING RATES IN THE IDENTIFICATION OF MALIGNANT BREAST MASSES IN MAMMOGRAMS

Abstract

Breast cancer is a prevalent disease that primarily affects women globally, but it can also affect men. Early detection is crucial for better treatment outcomes, and mammography is a common screening method. Recommendations for mammograms vary by age and country. Early breast cancer screening is vital for timely interventions. This paper aims to introduce AI methods through deep learning approaches utilizing pretrained CNN-based models for the diagnosis of masses depicted in breast images. These masses may be either malignant or benign, necessitating distinct management strategies for each scenario. The pretrained model ResNet18 applied to a combined dataset of three datasets (INbreast+MIAS+DDSM) yielded the best estimated result, with an accuracy of 95% (94.90% precision, 94.91% recall and 94.91% F1-score). [JJCIT 2024; 10(1.000): 93-107]

Keywords

• malignant breast cancer
• lesion classification
• transfer learning
• residual network (resnet18)
• adaptive learning rate