Abstract
Cancer identification and classification from histopathological images of the breast depends greatly on experts, and computer-aided diagnosis can play an important role in disagreement of experts. This automatic process has increased the accuracy of the classification at a reduced cost. The advancement in Convolution Neural Network (CNN) structure has outperformed the traditional approaches in biomedical imaging applications. One of the limiting factors of CNN is it uses spatial image features only for classification. The spectral features from the transform domain have equivalent importance in the complex image classification algorithm. This paper proposes a new CNN structure to classify the histopathological cancer images based on integrating the spectral features obtained using a multi-resolution wavelet transform with the spatial features of CNN. In addition, batch normalization process is used after every layer in the convolution network to improve the poor convergence problem of CNN and the deep layers of CNN are trained with spectral–spatial features. The proposed structure is tested on malignant histology images of the breast for both binary and multi-class classification of tissue using the BreaKHis Dataset and the Breast Cancer Classification Challenge 2015 Datasest. Experimental results show that the combination of spectral–spatial features improves classification accuracy of the CNN network and requires less training parameters in comparison with the well known models (i.e., VGG16 and ALEXNET). The proposed structure achieves an average accuracy of 97.58% and 97.45% with 7.6 million training parameters on both datasets, respectively.
Highlights
Agency for Research on Cancer (IARC) [1,2,3]
We proposed a method for histopathological cancer image classification based on a modified Convolution Neural Network (CNN) model
The weakness of the traditional CNN model is that its classification depends on the spatial features only that can be obtained from the training dataset
Summary
Agency for Research on Cancer (IARC) [1,2,3]. The clinical diagnosis of breast cancer includes inspection of medical images including mammograms, MRI, ultrasound, and histopathology images obtained from a biopsy [4,5]. This helps to enrich the standard of healthcare with quick and accurate quantification of the tissues This magnification process requires zooming and focusing on each image and later, scanning of these images entirely for correct diagnosis. Either supervised or unsupervised algorithms are used to classify these features belongs to any one of the category [9] Though these approaches have been proven successful in promoting discrimination problems such as healthy and invasive cancer-causing region, the information retrieved by these features is limited for more complex tasks. A new approach of CNN is developed for cancer image classification between normal, benign, in-situ, and invasive types by concentrating on modifying the CNN architecture considering computation cost.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have