Ali Erginay · enciclopedia

Publicaciones › Inteligencia artificial y análisis automático de imágenes

Improved Automated Detection of Diabetic Retinopathy on a Publicly Available Dataset Through Integration of Deep Learning

Detección Automatizada Mejorada de Retinopatía Diabética en un Conjunto de Datos Públicamente Disponible a Través de la Integración de Aprendizaje Profundo

Año2016
FuenteInvestigative ophthalmology & visual science
Tipoarticle · Comparative Study, Journal Article, Multicenter Study
Autores (7)Michael David Abràmoff, Yiyue Lou, Ali Erginay, Warren Clarida, Ryan Amelon, James C Folk, Meindert Niemeijer
Posición de Erginay3 de 7
Citas1218 (OpenAlex)
EnlacesDOI 10.1167/iovs.16-19964 · PubMed 27701631 · OpenAlex · Texto completo en acceso abierto
LíneasInteligencia artificial y análisis automático de imágenes Cribado, telemedicina (OPHDIAT) y epidemiología de la retinopatía diabética Edema macular diabético y sus tratamientos Enfermedades vasculares, genéticas e inflamatorias de la retina Retinopatía diabética: clínica, función y progresión

En pocas palabras

Se estudió la detección automatizada de retinopatía diabética utilizando un algoritmo mejorado con aprendizaje profundo. Los resultados mostraron una mayor precisión en la detección de la enfermedad en comparación con un algoritmo anterior sin aprendizaje profundo. Se encontró que el algoritmo mejorado logró una sensibilidad del 96,8% y una especificidad del 87,0%.

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

Resumen original

PURPOSE: To compare performance of a deep-learning enhanced algorithm for automated detection of diabetic retinopathy (DR), to the previously published performance of that algorithm, the Iowa Detection Program (IDP)-without deep learning components-on the same publicly available set of fundus images and previously reported consensus reference standard set, by three US Board certified retinal specialists. METHODS: We used the previously reported consensus reference standard of referable DR (rDR), defined as International Clinical Classification of Diabetic Retinopathy moderate, severe nonproliferative (NPDR), proliferative DR, and/or macular edema (ME). Neither Messidor-2 images, nor the three retinal specialists setting the Messidor-2 reference standard were used for training IDx-DR version X2.1. Sensitivity, specificity, negative predictive value, area under the curve (AUC), and their confidence intervals (CIs) were calculated. RESULTS: Sensitivity was 96.8% (95% CI: 93.3%-98.8%), specificity was 87.0% (95% CI: 84.2%-89.4%), with 6/874 false negatives, resulting in a negative predictive value of 99.0% (95% CI: 97.8%-99.6%). No cases of severe NPDR, PDR, or ME were missed. The AUC was 0.980 (95% CI: 0.968-0.992). Sensitivity was not statistically different from published IDP sensitivity, which had a CI of 94.4% to 99.3%, but specificity was significantly better than the published IDP specificity CI of 55.7% to 63.0%. CONCLUSIONS: A deep-learning enhanced algorithm for the automated detection of DR, achieves significantly better performance than a previously reported, otherwise essentially identical, algorithm that does not employ deep learning. Deep learning enhanced algorithms have the potential to improve the efficiency of DR screening, and thereby to prevent visual loss and blindness from this devastating disease.

Términos MeSH

Algorithms Automation Diabetic Retinopathy Diagnosis, Computer-Assisted Diagnostic Techniques, Ophthalmological Female Follow-Up Studies Humans Male Middle Aged Neural Networks, Computer Ophthalmologists ROC Curve Retina Retrospective Studies