Automatic Detection of Tuberculosis from Chest X-Rays using Convolutional Neural Network
K. G. Satheeshkumar1, V Arunachalam2

1KG Satheeshkumar*, SENSE,VIT University, Vellore, Tamil Nadu, India.
2V Arunachalam, Department of Micro and Nano Electronics, SENSE, VIT University , Vellore, Tamil Nadu, India.
Manuscript received on May 03, 2020. | Revised Manuscript received on May 15, 2020. | Manuscript published on June 30, 2020. | PP: 72-77 | Volume-9 Issue-5, June 2020. | Retrieval Number: E9292069520/2020©BEIESP | DOI: 10.35940/ijeat.E9292.069520
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (

Abstract: Tuberculosis is one of the single infectious diseases which is one among the top ten causes of deaths. Eradication is only possible by timely diagnosis of disease and treatment at its early stage. But unfortunately, timely detection is lagging due to many reasons. In this angle we present a novel scheme for automatic detection of tuberculosis from chest X-ray images. The proposed method accurately detects the malady by performing graph cut segmentation followed by classification using convolutional neural network. The classifier facilitates the chest X-rays to be classified as normal or abnormal. Simulation results show that the accuracy of 94%, sensitivity of 96% and specificity of 84% obtained from the proposed system are comparable and even better than the existing reported methods.
Keywords: Chest x-ray (CXR), Convolutional Neural Network (CNN),deep learning, graph cut.