Ali Erginay · enciclopedia

Publicaciones › Retinopatía diabética: clínica, función y progresión

Evaluation of the effect of JPEG and JPEG2000 image compression on the detection of diabetic retinopathy

Evaluación del efecto de la compresión de imágenes JPEG y JPEG2000 en la detección de retinopatía diabética

Año2006
FuenteEye (London, England)
Tipoarticle · Evaluation Study, Journal Article
Autores (8)J Conrath, A Erginay, R Giorgi, A Lecleire-Collet, E Vicaut, J-C Klein, A Gaudric, P Massin
Posición de Erginay2 de 8
Citas32 (OpenAlex)
EnlacesDOI 10.1038/sj.eye.6702238 · PubMed 16456597 · OpenAlex
LíneasInteligencia artificial y análisis automático de imágenes Cribado, telemedicina (OPHDIAT) y epidemiología de la retinopatía diabética Edema macular diabético y sus tratamientos Retinopatía diabética: clínica, función y progresión

En pocas palabras

Se estudió cómo la compresión de imágenes afecta la detección de retinopatía diabética. Se compararon los algoritmos de compresión JPEG y JPEG2000 en 45 fotografías de fondo de ojo. Se encontró que la compresión a niveles altos puede afectar la detección de algunas lesiones, pero JPEG2000 mostró resultados ligeramente mejores que JPEG en ciertos casos.

Resumen divulgativo generado automáticamente a partir del resumen original; puede contener imprecisiones.

Resumen original

To compare the effect of classic Joint Photographic Experts Group (JPEG) and JPEG2000 compression algorithms on detection of diabetic retinopathy (DR) lesions. In total, 45 colour fundus photographs obtained with a digital nonmydriatic fundus camera were saved in uncompressed Tagged Interchanged Files Format (TIFF) format (1.26 MB). They were graded jointly by two retinal specialists at a 1 month interval for soft exudates, hard exudates, macular oedema, newvessels, intraretinal microvascular abnormalities (IRMA), and retinal haemorrhages and/or microaneurysms. They were compressed to 118, 58, 41, and 27 KB by both algorithms and 24 KB by classic JPEG, placed in random order and graded again jointly by the two retina specialists. Subjective image quality was graded, and sensitivity, specificity, positive and negative predictive values, and kappa statistic were calculated for all lesions at all compression ratios. Compression to 118 KB showed no effect on image quality and kappa values were high (0.94-1). Image degradation became important at 27 KB for both algorithms. At high compression levels, IRMA and HMA detection were most affected with JPEG2000 performing slightly better than classic JPEG. Performance of classic JPEG and JPEG2000 algorithms is equivalent when compressing digital images of DR lesions from 1.26 MB to 118 KB and 58 KB. Higher compression ratios show slightly better results with JPEG2000 compression, but may be insufficient for screening purposes.

Términos MeSH

Algorithms Aneurysm Data Compression Diabetic Retinopathy Diagnostic Techniques, Ophthalmological Fundus Oculi Humans Microcirculation Photography Retinal Hemorrhage Retinal Vessels Retrospective Studies Sensitivity and Specificity