Breast cancer classification using machine learning and deep learning: a systematic review of WBCD-based research and future directions
S. Aarif Ahamed, Amitabh Wahi · 2025
Breast Cancer is one among the predominant causes of cancer-related deaths in women all over the world. Accurate classification of this cancer is crucial for early and effective treatment, which helps in maximising survival rates. This review paper aims to provide a comprehensive outline of Machine Learning (ML), Deep Learning (DL), and Hybrid Learning (HL) models applied in breast cancer classification using the Wisconsin Breast Cancer Diagnosis (WBCD) Dataset. In this paper, we have analysed 50 plus studies which are published between 2010 and 2024. Focusing on ML, DL and HL models, their performance are measured by metrics. This review paper also highlights the strengths and weakness of the various models applied to the dataset. Some of the models analysed here are Artificial Neural Network (ANN), Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), and Support vector Machines (SVM). The results showcase that deep Learning models performed better than machine learning models, and hybrid models still enhanced the accuracy of classification than deep learning models. We have also mentioned the future scope of deep learning and hybrid learning models.