Two-Stage Convolutional Neural Network for Breast Cancer Histology Image Classification

Abstract

This paper explores the problem of breast tissue classification of microscopy images. Based on the predominant cancer type the goal is to classify images into four categories of normal, benign, in situ carcinoma, and invasive carcinoma. Given a suitable training dataset, we utilize deep learning techniques to address the classification problem. Due to the large size of each image in the training dataset, we propose a patch-based technique which consists of two consecutive convolutional neural networks. The first "patch-wise" network acts as an auto-encoder that extracts the most salient features of image patches while the second "image-wise" network performs classification of the whole image. The first network is pre-trained and aimed at extracting local information while the second network obtains global information of an input image. We trained the networks using the ICIAR 2018 grand challenge on BreAst Cancer Histology (BACH) dataset. The proposed method yields 95% accuracy on the validation set compared to previously reported 77% accuracy rates in the literature. Our code is publicly available at https://github.com/ImagingLab/ICIAR2018.

Utilizing Automated Breast Cancer Detection to Identify Spatial Distributions of Tumor-Infiltrating Lymphocytes in Invasive Breast Cancer

“…In previous work, several research groups carried out image analyses focused on detection of metastatic breast cancer [38][39][40] and mitosis [41][42][43] using highly curated but relatively small datasets from algorithm evaluation challenges [24][25][26][27] 44 proposed a fully convolutional framework for semantic segmentation of histology images via structured crowdsourcing. This was the first work using crowdsourcing in pathology task which involved a total of 25 participants at different expertise levels from medical students to expert pathologists to generate training data for a deep learning algorithm.…”

PLANET: Improved Convolutional Neural Networks with Image Enhancement for Image Classification

“…Due to the hardware barriers, we propose an improved two-stage convolutional neural network for high-resolution image classification with a newly proposed image enhancement approach named PLANET. It follows [20] to create many more training samples, and the flowchart of PLANET is illustrated in Figure 1. PLANET first extracts fixed-size patches from an input image by sliding a window of size K × K on the image and taking S as the stride.…”

Deep Convolution Neural Network Based Breast Cancer Bigdata Analysis for Crowd Cloud Sourcing

“…So, the healthcare industry is paying more attention in developing an efficient application using machine learning algorithms [2]. In the earlier works, some of the researchers have focused on detecting breast cancer using image analysis for analysing the cancers have spread beyond the breast, other organs and nearby lymph nodes [3][4][5], and cell biology [6][7][8] using selective but small datasets from algorithm evaluation challenges [9][10][11][12].…”