Testing Global Histogram Equalization and Unsharp Mask Algo-rithms for Processing Conventional Chest X-Ray Images.

authors:

avatar A Mohammadi 1 , avatar J Aghazadeh 2 , avatar AA Ghate 1 , avatar SB Moosavi-toomatari 3 , * , avatar N Se-pehrvand 4 , avatar SE Moosavi-toomatari 5 , avatar M Mohammad Ghasemi-rad 3

Associate Professor, Department of Radiology,
Assistant Professor, Department of Neurosurgery, Imam Khomeini Training Hospital, Urmia University of Medical Sciences, Urmia, Iran,
Medical Doctor, Students Research Committee, Urmia University of Medi-cal Sciences, Urmia, Iran,
Medical Doctor, National Institute of Health Research, Tehran University of Medical Sciences, Tehran, Iran,
Medical Intern, Students Research Com-mittee, Tabriz University of Medical Sciences, Tabriz, Iran.
Shiraz E-Medical Journal: Vol.12, issue 4; 172-8
published online: October 1, 2011
article type: Research Article
received: April 3, 2011
accepted: June 25, 2011

how to cite: Mohammadi A, Aghazadeh J, Ghate A, Moosavi-toomatari S, Se-pehrvand N, et al. Testing Global Histogram Equalization and Unsharp Mask Algo-rithms for Processing Conventional Chest X-Ray Images.. Shiraz E-Med J. 2011;12(4): 172-8. 

Abstract

Introduction:

Imaging methods are progressing in a rapidly manner, but the problem which we, as the health providers always encounter with is the expensive costs of different devices and our limited budget to provide them.

Aims:

The aim of this study is to evaluate the usefulness of Histogram Equalization (HE) and Unsharp Mask (UM) on the conventional CXR images.

Methods and Material:

In Urmia University of Medical Sciences, we designed a windows-based computer program that contains histogram equalization (HE), unsharp mask (UM) and com-bination of HE and UM algorithms with adjusted parameters to process conventional chest x-ray (CXR) images. Two series of CXR images including 49 images without major pulmonary disorder and 45 images with pulmonary parenchymal disorders were selected. After convert-ing them to digital format, images were processed with HE, UM and combination of HE and UM techniques. In each series, original and processed images were saved in 4 databases. Two board-certified general radiologists (with 6 and 5 years experience) analyzed images. Saved images were displayed to radiologists randomly and separately. Quality of each image was saved as a scale from 1 (very low quality) to 5 (excellent). We used a variance-based statistical technique to analyze quality.

Statistical analysis used:

To compare the quality of each algorithm (GHE, UM and combina-tion of GHE and UM), a variance-based statistical analysis was done.

Results:

In the first series images, HE and combination of HE and UM algorithms increased quality of images, but UM technique was not suitable, solely. Also, all three techniques in-creased quality of second series images.

Conclusions:

The use of digital image processing algorithms such as HE or UM on conven-tional CXR images can increase quality of images.

Full Text

Full text is available in PDF