Automatic Tuberculosis Screening using Chest Radiographs
S. Leopauline1, R. Kalpana2, P. Sharmila3
1S.Leopauline,, Department of Electronics and Communication Engineering, Vel Tech Multi Tech Dr.Rangarajan Dr.Sakunthala Engineering College, Chennai, India.
2R.Kalpana, Department of Electronics and Communication Engineering, Vel Tech Multi Tech Dr.Rangarajan Dr.Sakunthala Engineering College, Chennai, India.
3P.Sharmila, Department of Electronics and Communication Engineering, Vel Tech Multi Tech Dr.Rangarajan Dr.Sakunthala Engineering College, Chennai, India.
Manuscript received on November 22, 2019. | Revised Manuscript received on December 15, 2019. | Manuscript published on December 30, 2019. | PP: 2665-2668 | Volume-9 Issue-2, December, 2019. | Retrieval Number: A1507109119/2019©BEIESP | DOI: 10.35940/ijeat.A1507.129219
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 (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Tuberculosis is considered to be dreadful disease also became greater peril in many regions of the world. Demonising tuberculosis still remains a challenging process where Opportunistic infections in immune compromised HIV/AIDS patients. If it is left untreated, rate of patients with tuberculosis are huge. We have standard diagnostics methods which are not considered to be accurate.They are sluggish and un faithful. An effort towards detection of tuberculosis is made in this paper by automated approach using chest radio graphs. In this method primary step is to segment an image suing texture method and lung region is extracted using graph cut extraction method. For the above said method a set of texture and shape features are formed on the lung region to enable the CXR,then binary classifier is used to detect normal or abnormal images. In proposed method we use Artificial Neural Networks (ANN) for screening and to identify the presence of tuberculosis
Keywords: CXR, Texture segmentation, Graph cut extraction, ANN Network, Tuberculosis.