CUTTING-EDGE CNN APPROACHES FOR BREAST HISTOPATHOLOGICAL CLASSIFICATION: THE IMPACT OF SPATIAL ATTENTION MECHANISMS

This paper investigates advanced techniques for breast Histopathological Classification using two robust convolutional neural network (CNN) architectures: Inception V3 and VGG19. Spatial attention mechanisms are integrated to enhance the models' capability to focus on crucial regions within histology images. These enhancements improve diagnostic accuracy by allowing the models to concentrate on critical features for accurate detection. The research leverages two prominent datasets, BACH for multiclass classification and BreaKHis for binary classification, which provides extensive collections of breast cancer histology images, enabling thorough training and evaluation of the proposed models. InceptionV3 with spatial attention mechanism achieved an accuracy of 99.73% for binary classification and 99.06% for multiclass classification. Integrating spatial attention mechanisms is anticipated to significantly advance the development of automated breast cancer detection systems, offering potential improvements in early diagnosis and treatment planning. This study demonstrates how combining state-of-the-art CNN architectures with attention mechanisms can significantly improve medical image analysis, ultimately contributing to better patient outcomes.