HEp-2 Cell Image Classification with Deep Convolutional Neural Networks

TL;DR

This paper introduces a deep CNN-based framework for classifying HEp-2 cell images, improving accuracy and adaptability across datasets, which aids autoimmune disease diagnosis.

Contribution

It presents a novel CNN framework with data augmentation strategies that outperforms existing models in HEp-2 cell image classification.

Findings

Outperforms existing models with data augmentation

Demonstrates high adaptability across datasets

Ranks high in ICPR 2014 competition

Abstract

Efficient Human Epithelial-2 (HEp-2) cell image classification can facilitate the diagnosis of many autoimmune diseases. This paper presents an automatic framework for this classification task, by utilizing the deep convolutional neural networks (CNNs) which have recently attracted intensive attention in visual recognition. This paper elaborates the important components of this framework, discusses multiple key factors that impact the efficiency of training a deep CNN, and systematically compares this framework with the well-established image classification models in the literature. Experiments on benchmark datasets show that i) the proposed framework can effectively outperform existing models by properly applying data augmentation; ii) our CNN-based framework demonstrates excellent adaptability across different datasets, which is highly desirable for classification under varying laboratory settings. Our system is ranked high in the cell image classification competition hosted by ICPR 2014.