Automatic Breast Cancer Classification from Histopathological Images

Breast cancer (BC) is a common health problem of major significance, as it is the most widely kind of cancer among women which leads to morbidity and mortality. Pathological diagnosis is considered as the golden standard of BC detection. However, the investigation of histopathology images is a challenging task. Automatic diagnosis of BC could lower the death rate by constructing a computer aided diagnosis (CAD) system capable of accurately diagnosing BC and reducing the time consumed by pathologists during examinations. This paper presents a CAD system to classify BC to benign and malignant. The proposed CAD method consists of 4 stages; image pre-processing, feature extraction and fusion, feature reduction, and classification. The CAD is based on fusion features extracted with ResNet Deep Convolution Neural Network (DCNN) with features of wavelets packet decomposition (WPD) and histograms of oriented gradient (HOG). Next, the feature data were reduced by utilizing principle component analysis (PCA). Finally, the reduced features are used to train different individual classifiers. Results show that the highest accuracy of 97.1% is achieved. The results were compared with recent related CAD systems. The comparison showed that the proposed CAD system is capable of accurately classifying BC to benign and malignant compared to other work. Thus, it can be used to help medical experiments in investigation procedures.