Alexandros Karargyris1, Jenifer Siegelman2,3, Dimitris Tzortzis4, Stefan Jaeger5, Sema Candemir5, Zhiyun Xue5, K C Santosh5, Szilárd Vajda5, Sameer Antani5, Les Folio6, George R Thoma5. 1. Communications Engineering Branch, Lister Hill National Center for Biomedical Communications, National Library of Medicine, National Institutes of Health, Bethesda, MD, USA. akarargyris@gmail.com. 2. Division of Emergency Radiology, Department of Radiology, Brigham and Women's Hospital, Boston, MA, USA. 3. Center for Evidence Based Imaging, Harvard Medical School, Boston, MA, USA. 4. Ugeianet Diagnostic Center, General Hospital of Athens KAT, Athens, Greece. 5. Communications Engineering Branch, Lister Hill National Center for Biomedical Communications, National Library of Medicine, National Institutes of Health, Bethesda, MD, USA. 6. Radiology Department, Clinical Center, National Institutes of Health, Bethesda, MD, USA.
Abstract
PURPOSE: To improve detection of pulmonary and pleural abnormalities caused by pneumonia or tuberculosis (TB) in digital chest X-rays (CXRs). METHODS: A method was developed and tested by combining shape and texture features to classify CXRs into two categories: TB and non-TB cases. Based on observation that radiologist interpretation is typically comparative: between left and right lung fields, the algorithm uses shape features to describe the overall geometrical characteristics of the lung fields and texture features to represent image characteristics inside them. RESULTS: Our algorithm was evaluated on two different datasets containing tuberculosis and pneumonia cases. CONCLUSIONS: Using our proposed algorithm, we were able to increase the overall performance, measured as area under the (ROC) curve (AUC) by 2.4 % over our previous work.
PURPOSE: To improve detection of pulmonary and pleural abnormalities caused by pneumonia or tuberculosis (TB) in digital chest X-rays (CXRs). METHODS: A method was developed and tested by combining shape and texture features to classify CXRs into two categories: TB and non-TB cases. Based on observation that radiologist interpretation is typically comparative: between left and right lung fields, the algorithm uses shape features to describe the overall geometrical characteristics of the lung fields and texture features to represent image characteristics inside them. RESULTS: Our algorithm was evaluated on two different datasets containing tuberculosis and pneumonia cases. CONCLUSIONS: Using our proposed algorithm, we were able to increase the overall performance, measured as area under the (ROC) curve (AUC) by 2.4 % over our previous work.
Authors: Sema Candemir; Stefan Jaeger; Kannappan Palaniappan; Jonathan P Musco; Rahul K Singh; Alexandros Karargyris; Sameer Antani; George Thoma; Clement J McDonald Journal: IEEE Trans Med Imaging Date: 2013-11-13 Impact factor: 10.048
Authors: Szilárd Vajda; Alexandros Karargyris; Stefan Jaeger; K C Santosh; Sema Candemir; Zhiyun Xue; Sameer Antani; George Thoma Journal: J Med Syst Date: 2018-06-29 Impact factor: 4.460
Authors: Mutlu Demirer; Sema Candemir; Matthew T Bigelow; Sarah M Yu; Vikash Gupta; Luciano M Prevedello; Richard D White; Joseph S Yu; Rainer Grimmer; Michael Wels; Andreas Wimmer; Abdul H Halabi; Alvin Ihsani; Thomas P O'Donnell; Barbaros S Erdal Journal: Radiol Artif Intell Date: 2019-11-27
Authors: Miriam Harris; Amy Qi; Luke Jeagal; Nazi Torabi; Dick Menzies; Alexei Korobitsyn; Madhukar Pai; Ruvandhi R Nathavitharana; Faiz Ahmad Khan Journal: PLoS One Date: 2019-09-03 Impact factor: 3.240