Tree-structured vector quantization of CT chest scans: image quality and diagnostic accuracy

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...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on medical imaging 1993-12, Vol.12 (4), p.727-739
Main Authors: Cosman, P.C., Tseng, C., Gray, R.M., Olshen, R.A., Moses, L.E., Davidson, H.C., Bergin, C.J., Riskin, E.A.
Format: Article
Language:English
Subjects:
550601 - Medicine- Unsealed Radionuclides in Diagnostics
ACCURACY
Biological and medical sciences
Biomedical imaging
BODY
BODY AREAS
CHEST
Compression algorithms
Computed tomography
COMPUTERIZED TOMOGRAPHY
DIAGNOSIS
DIAGNOSTIC TECHNIQUES
DISEASES
Image coding
IMAGE PROCESSING
Investigative techniques, diagnostic techniques (general aspects)
LUNGS
Medical diagnostic imaging
Medical sciences
Medical simulation
NEOPLASMS
ORGANS
Performance loss
Predictive models
PROCESSING
Radiodiagnosis. Nmr imagery. Nmr spectrometry
RADIOLOGY AND NUCLEAR MEDICINE
RESPIRATORY SYSTEM
Signal to noise ratio
TOMOGRAPHY
Vector quantization
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.< >
ISSN:0278-0062
1558-254X
DOI:10.1109/42.251124