Abstract

The diagnosis of breast cancer depends on histopathology for precise and trusted evaluation between malignant tumor cells and benign cells. The analysis demands significant time and creates additional room for human errors. A deep learning approach for computer-aided diagnosis (CAD) establishes techniques to enhance the classification performance in this study. The proposed methods utilize One-hot encoding with VGG-16 for feature extraction to achieve 98% accuracy with BreakHis data while DBN for feature learning reaches 98% accuracy on BreakHis and 96% on Kaggle. SSGAN addresses unannotated images effectively with up to 89% accuracy. Through its application, deep learning technology proves to enhance breast cancer identification while decreasing the workload on medical pathologists. One-hot encoding remains efficient for computations yet the DBN extraction method produces superior features. The SSGAN model increases labeling accuracy when it uses available labeled data and unlabeled data to lower annotation expenses. Deep learning technologies validate their ability to transform breast cancer histopathological diagnosis through precision-enhanced efficient examination methods especially with semi-supervised GAN systems.