Combination of texture and shape features to detect pulmonary abnormalities in digital chest X-rays

Alexandros Karargyris; Jenifer Siegelman; Dimitris Tzortzis; Stefan Jaeger; Sema Candemir; Zhiyun Xue; K C Santosh; Szilárd Vajda; Sameer Antani; Les Folio; George R Thoma

doi:10.1007/s11548-015-1242-x

Combination of texture and shape features to detect pulmonary abnormalities in digital chest X-rays

Int J Comput Assist Radiol Surg. 2016 Jan;11(1):99-106. doi: 10.1007/s11548-015-1242-x. Epub 2015 Jun 20.

Authors

Alexandros Karargyris¹, Jenifer Siegelman^{2

3}, Dimitris Tzortzis⁴, Stefan Jaeger⁵, Sema Candemir⁵, Zhiyun Xue⁵, K C Santosh⁵, Szilárd Vajda⁵, Sameer Antani⁵, Les Folio⁶, George R Thoma⁵

Affiliations

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.

PMID: 26092662
DOI: 10.1007/s11548-015-1242-x

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.

Keywords: Remote; Screen; Software; Telemedicine; Tuberculosis.

MeSH terms

Algorithms
Humans
Lung / diagnostic imaging*
Pneumonia / diagnostic imaging*
Radiography, Thoracic / methods*
Tuberculosis / diagnostic imaging*