CHEST X-RAY IMAGE CLASSIFICATION USING FASTER R-CNN

Taufik Rahmat1, Azlan Ismail1,2, Sharifah Aliman1,3

1Faculty of Computer and Mathematical Sciences
2Knowledge and Software Engineering Research Group
3Advanced Analytics Engineering Centre
Universiti Teknologi MARA (UiTM) 40450 Shah Alam,
Selangor, Malaysia
This email address is being protected from spambots. You need JavaScript enabled to view it., This email address is being protected from spambots. You need JavaScript enabled to view it., This email address is being protected from spambots. You need JavaScript enabled to view it.

Abstract

Chest x-ray image analysis is the common medical imaging exam needed to assess different pathologies. Having an automated solution for the analysis can contribute to minimizing the workloads, improve efficiency and reduce the potential of reading errors. Many methods have been proposed to address chest x-ray image classification and detection. However, the application of regional-based convolutional neural networks (CNN) is currently limited. Thus, we propose an approach to classify chest x-ray images into either one of two categories, pathological or normal based on Faster Regional-CNN model. This model utilizes Region Proposal Network (RPN) to generate region proposals and perform image classification. By applying this model, we can potentially achieve two key goals, high confidence in the classification and reducing the computation time. The results show the applied model achieved higher accuracy as compared to the medical representatives on the random chest x-ray images. The classification model is also reasonably effective in classifying between finding and normal chest x-ray image captured through a live webcam.

Keywords: Image Classification, Chest X-ray Analysis, CNN, faster R-CNN, Region Proposal Network
Published On: 27 June 2019

Full Download