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

被引:78
作者
Karargyris, Alexandros [1 ]
Siegelman, Jenifer [2 ,3 ]
Tzortzis, Dimitris [4 ]
Jaeger, Stefan [1 ]
Candemir, Sema [1 ]
Xue, Zhiyun [1 ]
Santosh, K. C. [1 ]
Vajda, Szilard [1 ]
Antani, Sameer [1 ]
Folio, Les [5 ]
Thoma, George R. [1 ]
机构
[1] Natl Lib Med, Lister Hill Natl Ctr Biomed Commun, Commun Engn Branch, NIH, Bldg 10, Bethesda, MD 20892 USA
[2] Brigham & Womens Hosp, Dept Radiol, Div Emergency Radiol, 75 Francis St, Boston, MA 02115 USA
[3] Harvard Univ, Sch Med, Ctr Evidence Based Imaging, Boston, MA USA
[4] Gen Hosp Athens KAT, Ugeianet Diagnost Ctr, Athens, Greece
[5] NIH, Ctr Clin, Dept Radiol, Bethesda, MD 20892 USA
关键词
Tuberculosis; Screen; Software; Remote; Telemedicine; TUBERCULOSIS; RADIOGRAPHS;
D O I
10.1007/s11548-015-1242-x
中图分类号
R318 [生物医学工程];
学科分类号
100103 [病原生物学];
摘要
To improve detection of pulmonary and pleural abnormalities caused by pneumonia or tuberculosis (TB) in digital chest X-rays (CXRs). 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. Our algorithm was evaluated on two different datasets containing tuberculosis and pneumonia cases. 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.
引用
收藏
页码:99 / 106
页数:8
相关论文
共 10 条
[1]
Beard D., 2009, THESIS U MISSOURI CO
[2]
Lung Segmentation in Chest Radiographs Using Anatomical Atlases With Nonrigid Registration [J].
Candemir, Sema ;
Jaeger, Stefan ;
Palaniappan, Kannappan ;
Musco, Jonathan P. ;
Singh, Rahul K. ;
Xue, Zhiyun ;
Karargyris, Alexandros ;
Antani, Sameer ;
Thoma, George ;
McDonald, Clement J. .
IEEE TRANSACTIONS ON MEDICAL IMAGING, 2014, 33 (02) :577-590
[3]
Folio LR, 2012, CHEST IMAGING: AN ALGORITHMIC APPROACH TO LEARNING, P1, DOI 10.1007/978-1-4614-1317-2
[4]
Automatic Tuberculosis Screening Using Chest Radiographs [J].
Jaeger, Stefan ;
Karargyris, Alexandros ;
Candemir, Sema ;
Folio, Les ;
Siegelman, Jenifer ;
Callaghan, Fiona ;
Xue, Zhiyun ;
Palaniappan, Kannappan ;
Singh, Rahul K. ;
Antani, Sameer ;
Thoma, George ;
Wang, Yi-Xiang ;
Lu, Pu-Xuan ;
McDonald, Clement J. .
IEEE TRANSACTIONS ON MEDICAL IMAGING, 2014, 33 (02) :233-245
[5]
Automatic screening for tuberculosis in chest radiographs: a survey [J].
Jaeger, Stefan ;
Karargyris, Alexandros ;
Candemir, Sema ;
Siegelman, Jenifer ;
Folio, Les ;
Antani, Sameer ;
Thoma, George ;
McDonald, Clement J. .
QUANTITATIVE IMAGING IN MEDICINE AND SURGERY, 2013, 3 (02) :89-99
[6]
Karargyris A, 2011, IEEE ENG MED BIO, P7779, DOI 10.1109/IEMBS.2011.6091917
[7]
Automatically Detecting Rotation in Chest Radiographs Using Principal Rib-Orientation Measure for Quality Control [J].
Santosh, K. C. ;
Candemir, Sema ;
Jaeger, Stefan ;
Karargyris, Alexandros ;
Antani, Sameer ;
Thoma, George R. .
INTERNATIONAL JOURNAL OF PATTERN RECOGNITION AND ARTIFICIAL INTELLIGENCE, 2015, 29 (02)
[8]
The MathWorks Inc, MATL MEAS PROP IM RE
[9]
The role and performance of chest X-ray for the diagnosis of tuberculosis: A cost-effectiveness analysis in Nairobi, Kenya [J].
van Cleeff, MRA ;
Kivihya-Ndugga, L ;
Meme, H ;
Odhiambo, JA ;
Klatser, PR .
BMC INFECTIOUS DISEASES, 2005, 5 (1)
[10]
Computer-aided diagnosis in chest radiography: Beyond nodules [J].
van Ginneken, Bram ;
Hogeweg, Laurens ;
Prokop, Mathias .
EUROPEAN JOURNAL OF RADIOLOGY, 2009, 72 (02) :226-230