Breast Cancer Classification in Histopathological Images using Convolutional Neural Network

Mohamad Mahmoud

doi:10.14569/ijacsa.2018.090310

Abstract

Computer based analysis is one of the suggested means that can assist oncologists in the detection and diagnosis of breast cancer. On the other hand, deep learning has been promoted as one of the hottest research directions very recently in the general imaging literature, thanks to its high capability in detection and recognition tasks. Yet, it has not been adequately suited to the problem of breast cancer so far. In this context, I propose in this paper an approach for breast cancer detection and classification in histopathological images. This approach relies on a deep convolutional neural networks (CNN), which is pretrained on an auxiliary domain with very large labelled images, and coupled with an additional network composed of fully connected layers. The network is trained separately with respect to various image magnifications (40x, 100x, 200x and 400x). The results presented in the patient level achieved promising scores compared to the state of the art methods.

Highlights

Computer based analysis is one of the suggested means that can assist oncologists in the detection and diagnosis of breast cancer
In order to produce stained histology slides, samples of tissue are taken from the breast during biopsy
In order to realistically assess any breast cancer (BC) diagnosis system, the experiments shall be performed on a large-scale dataset accommodating 1) numerous patients, 2) abundant images

Summary

Dataset Description

In order to realistically assess any BC diagnosis system, the experiments shall be performed on a large-scale dataset accommodating 1) numerous patients, 2) abundant images. The Breast Cancer Histopathological Image Classification (BreakHis), which was established recently in [22], is an optimal dataset as it meets all the above requirements. It is composed of 9,109 microscopic images of breast tumour tissue collected from 82 patients using different magnifying factors (40X, 100X, 200X, and 400X). Samples present in the dataset were collected by SOB method, named partial mastectomy or excisional biopsy This type of procedure, compared to any methods of needle biopsy, removes the larger size of tissue sample and is performed in a hospital with general anaesthetic.

Proposed Methodology

Experimental Results