Inception Architecture and Residual Connections in Classification of Breast Cancer Histology Images
This work addresses the challenging problem of multi-class breast cancer image classification for medical practitioners, but it is incremental as it applies an existing method to a specific dataset.
The paper tackled multi-class classification of breast cancer histology images using an Inception v4 network with data augmentation and ensemble methods, achieving 89% accuracy on a 4-class task and 93.7% on a binary carcinoma/non-carcinoma task on a test set of 80 images.
This paper presents results of applying Inception v4 deep convolutional neural network to ICIAR-2018 Breast Cancer Classification Grand Challenge, part a. The Challenge task is to classify breast cancer biopsy results, presented in form of hematoxylin and eosin stained images. Breast cancer classification is of primary interest to the medical practitioners and thus binary classification of breast cancer images have been under investigation by many researchers, but multi-class categorization of histology breast images have been challenging due to the subtle differences among the categories. In this work extensive data augmentation is conducted to reduce overfitting and effectiveness of committee of several Inception v4 networks is studied. We report 89% accuracy on 4 class classification task and 93.7% on carcinoma/non-carcinoma two class classification task using our test set of 80 images.