Detection of Tuberculosis in Chest X-rays using U-Net Architecture
S.Usha Kiruthika1, S. Kanaga Suba Raja2, V. Balaji3, C.J.Raman4, S. S. L. Durai Arumugam5

1S. Usha Kiruthika*  Currently working as an Assistant Professor in the Department of Computer Science and Engineering in SRM Institute of Science and Technology, Kattankulathur Campus.
2Dr. S.Kanaga Suba Raja, Easwari Engineering College, Chennai, India,
3Mr.V.Balaji, Department of Information Technology, Easwari Engineering College, Chennai, India.
4Mr. S. S. L. Durai Arumugam, Assistant Professor, Easwari Engineering College, Chennai, Tamil Nadu, India.
5Dr. C.J.Raman , Associate Professor , Department of Information Technology, St. Joseph’s College of Engineering, Chennai, Tamil Nadu, India.

Manuscript received on October 16, 2019. | Revised Manuscript received on 22 October, 2019. | Manuscript published on November 10, 2019. | PP: 2514-2519 | Volume-9 Issue-1, November 2019. | Retrieval Number: A4834119119/2019©BEIESP | DOI: 10.35940/ijitee.A4834.119119
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: X-rays are the most commonly performed which are costly diagnostic imaging tests ordered by physicians. Here we are proposing an artificial intelligence system that can reliably separate normal from abnormal would be invaluable in addressing the problem of undiagnosed disease and the lack of radiologists in low-resource settings. The aim of this study is to develop and validate a deep learning system to detect chest x-ray abnormalities and hence detect Tuberculosis (TB) and to provide a tool for Computer Aided Diagnosis (CAD).In this paper by trying to explore existing systems of Image Processing and Deep learning architectures, we are trying to achieve radiologist level detection as well as lower False Negative detection of TB by using ensemble datasets and algorithms. The prototype of a WebApp is created and can be checked on https://parth-patel12.github.io where one can upload the chest x-ray which give probabilities of the chest x-ray to be normal or TB affected.
Keywords: Autism, Generative Adversarial Network, Convolutional Neural Networks, Artificial Neural Network, Tuberculosis, Computer Aided Diagnosis.
Scope of the Article: Artificial Intelligence