Image Classification in Breast Histopathology Using Transfer and Ensemble Learning

Breast cancer has the highest prevalence in women globally. The classification of breast cancer histopathological images has always been a hot spot of clinical concern. In Computer-Aided Diagnosis (CAD), traditional models mostly use a single network to extract features, which has significant limitations. Besides, many networks are trained and optimized on patient-level datasets, ignoring the lower-level labels. This paper proposes a deep ensemble model based on image-level labels for the binary classification of benign and malignant breast histopathological images. First, the BreakHis dataset is randomly divided into training, validation and test sets. Then, data augmentation techniques are used to balance the number of benign and malignant samples. Thirdly, VGG-16, Xception, Resnet-50, Densenet-201 are selected as the base classifiers resulting from their complementarity. Finally, with accuracy as the ensemble weight, an accuracy of 98.90% is achieved. In order to verify the capabilities of our method, the latest Transformer and Multilayer Perception (MLP) models have been experimentally compared on the same dataset. Our model wins with a 5–20% advantage, emphasizing the ensemble model’s far-reaching significance in classification tasks.