Articles producció científica> Medicina i Cirurgia

A New Deep Learning Algorithm with Activation Mapping for Diabetic Retinopathy: Backtesting after 10 Years of Tele-Ophthalmology

  • Datos identificativos

    Identificador: imarina:9281706
    Autores:
    Pareja-Rios, AliciaCeruso, SabatoRomero-Aroca, PedroBonaque-Gonzalez, Sergio
    Resumen:
    We report the development of a deep learning algorithm (AI) to detect signs of diabetic retinopathy (DR) from fundus images. For this, we use a ResNet-50 neural network with a double resolution, the addition of Squeeze-Excitation blocks, pre-trained in ImageNet, and trained for 50 epochs using the Adam optimizer. The AI-based algorithm not only classifies an image as pathological or not but also detects and highlights those signs that allow DR to be identified. For development, we have used a database of about half a million images classified in a real clinical environment by family doctors (FDs), ophthalmologists, or both. The AI was able to detect more than 95% of cases worse than mild DR and had 70% fewer misclassifications of healthy cases than FDs. In addition, the AI was able to detect DR signs in 1258 patients before they were detected by FDs, representing 7.9% of the total number of DR patients detected by the FDs. These results suggest that AI is at least comparable to the evaluation of FDs. We suggest that it may be useful to use signaling tools such as an aid to diagnosis rather than an AI as a stand-alone tool.
  • Otros:

    Autor según el artículo: Pareja-Rios, Alicia; Ceruso, Sabato; Romero-Aroca, Pedro; Bonaque-Gonzalez, Sergio;
    Departamento: Medicina i Cirurgia
    Autor/es de la URV: Romero Aroca, Pedro
    Palabras clave: Tele-ophthalmology Diabetic retinopathy Deep learning Artificial-intelligence Artificial intelligence
    Resumen: We report the development of a deep learning algorithm (AI) to detect signs of diabetic retinopathy (DR) from fundus images. For this, we use a ResNet-50 neural network with a double resolution, the addition of Squeeze-Excitation blocks, pre-trained in ImageNet, and trained for 50 epochs using the Adam optimizer. The AI-based algorithm not only classifies an image as pathological or not but also detects and highlights those signs that allow DR to be identified. For development, we have used a database of about half a million images classified in a real clinical environment by family doctors (FDs), ophthalmologists, or both. The AI was able to detect more than 95% of cases worse than mild DR and had 70% fewer misclassifications of healthy cases than FDs. In addition, the AI was able to detect DR signs in 1258 patients before they were detected by FDs, representing 7.9% of the total number of DR patients detected by the FDs. These results suggest that AI is at least comparable to the evaluation of FDs. We suggest that it may be useful to use signaling tools such as an aid to diagnosis rather than an AI as a stand-alone tool.
    Áreas temáticas: Medicine, general & internal Medicine (miscellaneous) Medicine (all)
    Acceso a la licencia de uso: https://creativecommons.org/licenses/by/3.0/es/
    Direcció de correo del autor: pedro.romero@urv.cat
    Identificador del autor: 0000-0002-7061-8987
    Fecha de alta del registro: 2024-09-07
    Versión del articulo depositado: info:eu-repo/semantics/publishedVersion
    Enlace a la fuente original: https://www.mdpi.com/2077-0383/11/17/4945
    URL Documento de licencia: https://repositori.urv.cat/ca/proteccio-de-dades/
    Referencia al articulo segun fuente origial: Journal Of Clinical Medicine. 11 (17):
    Referencia de l'ítem segons les normes APA: Pareja-Rios, Alicia; Ceruso, Sabato; Romero-Aroca, Pedro; Bonaque-Gonzalez, Sergio; (2022). A New Deep Learning Algorithm with Activation Mapping for Diabetic Retinopathy: Backtesting after 10 Years of Tele-Ophthalmology. Journal Of Clinical Medicine, 11(17), -. DOI: 10.3390/jcm11174945
    DOI del artículo: 10.3390/jcm11174945
    Entidad: Universitat Rovira i Virgili
    Año de publicación de la revista: 2022
    Tipo de publicación: Journal Publications
  • Palabras clave:

    Medicine (Miscellaneous),Medicine, General & Internal
    Tele-ophthalmology
    Diabetic retinopathy
    Deep learning
    Artificial-intelligence
    Artificial intelligence
    Medicine, general & internal
    Medicine (miscellaneous)
    Medicine (all)
  • Documentos:

  • Cerca a google

    Search to google scholar