# Double Transfer Learning for Breast Cancer Histopathologic Image Classification

## TL;DR

This paper introduces a double transfer learning approach combining CNN feature extraction and patch filtering to improve breast cancer histopathologic image classification accuracy, outperforming existing methods.

## Contribution

It proposes a novel double transfer learning method that enhances classification by filtering irrelevant patches and extracting features using Inception-v3 CNN.

## Key findings

- Achieved a 4.4% total accuracy improvement
- Outperformed state-of-the-art in 3 of 4 magnification factors
- Effective patch filtering enhances classifier performance

## Abstract

This work proposes a classification approach for breast cancer histopathologic images (HI) that uses transfer learning to extract features from HI using an Inception-v3 CNN pre-trained with ImageNet dataset. We also use transfer learning on training a support vector machine (SVM) classifier on a tissue labeled colorectal cancer dataset aiming to filter the patches from a breast cancer HI and remove the irrelevant ones. We show that removing irrelevant patches before training a second SVM classifier, improves the accuracy for classifying malign and benign tumors on breast cancer images. We are able to improve the classification accuracy in 3.7% using the feature extraction transfer learning and an additional 0.7% using the irrelevant patch elimination. The proposed approach outperforms the state-of-the-art in three out of the four magnification factors of the breast cancer dataset.