DocumentCode :
994354
Title :
Tree-structured vector quantization of CT chest scans: image quality and diagnostic accuracy
Author :
Cosman, P.C. ; Tseng, C. ; Gray, R.M. ; Olshen, R.A. ; Moses, L.E. ; Davidson, H.C. ; Bergin, C.J. ; Riskin, E.A.
Author_Institution :
Dept. of Electr. Eng., Stanford Univ., CA, USA
Volume :
12
Issue :
4
fYear :
1993
fDate :
12/1/1993 12:00:00 AM
Firstpage :
727
Lastpage :
739
Abstract :
The authors apply a lossy compression algorithm to medical images, and quantify the quality of the images by the diagnostic performance of radiologists, as well as by traditional signal-to-noise ratios and subjective ratings. The authors´ study is unlike previous studies of the effects of lossy compression in that they consider nonbinary detection tasks, simulate actual diagnostic practice instead of using paired tests or confidence rankings, use statistical methods that are more appropriate for nonbinary clinical data than are the popular receiver operating characteristic curves, and use low-complexity predictive tree-structured vector quantization for compression rather than DCT-based transform codes combined with entropy coding. The authors´ diagnostic tasks are the identification of nodules (tumors) in the lungs and lymphadenopathy in the mediastinum from computerized tomography (CT) chest scans. Radiologists read both uncompressed and lossy compressed versions of images. For the image modality, compression algorithm, and diagnostic tasks the authors consider, the original 12 bit per pixel (bpp) CT image can be compressed to between 1 bpp and 2 bpp with no significant changes in diagnostic accuracy. The techniques presented here for evaluating image quality do not depend on the specific compression algorithm and are useful new methods for evaluating the benefits of any lossy image processing technique
Keywords :
computerised tomography; lung; medical image processing; CT chest scans; confidence rankings; diagnostic accuracy; image quality; lossy compression algorithm; lung nodules identification; mediastinum lymphadenopathy; medical images; nonbinary detection tasks; paired tests; radiologists; receiver operating characteristic curves; signal-to-noise ratios; statistical methods; subjective ratings; tree-structured vector quantization; Biomedical imaging; Compression algorithms; Computed tomography; Image coding; Medical diagnostic imaging; Medical simulation; Performance loss; Predictive models; Signal to noise ratio; Vector quantization;
fLanguage :
English
Journal_Title :
Medical Imaging, IEEE Transactions on
Publisher :
ieee
ISSN :
0278-0062
Type :
jour
DOI :
10.1109/42.251124
Filename :
251124
Link To Document :
بازگشت