Computer-Aided Diagnosis of Diabetic Retinopathy Lesions Based on Knowledge Distillation in Fundus Images

Ernesto Moya-Albor (), Alberto Lopez-Figueroa, Sebastian Jacome-Herrera, Diego Renza and Jorge Brieva ()
Additional contact information
Ernesto Moya-Albor: Facultad de Ingeniería, Universidad Panamericana, Augusto Rodin 498, Ciudad de México 03920, Mexico
Alberto Lopez-Figueroa: Facultad de Ingeniería, Universidad Panamericana, Augusto Rodin 498, Ciudad de México 03920, Mexico
Sebastian Jacome-Herrera: Facultad de Ingeniería, Universidad Panamericana, Augusto Rodin 498, Ciudad de México 03920, Mexico
Diego Renza: Facultad de Ingeniería, Universidad Militar Nueva Granada, Carrera 11 101-80, Bogota 110111, Colombia
Jorge Brieva: Facultad de Ingeniería, Universidad Panamericana, Augusto Rodin 498, Ciudad de México 03920, Mexico

Mathematics, 2024, vol. 12, issue 16, 1-25

Abstract: At present, the early diagnosis of diabetic retinopathy (DR), a possible complication of diabetes due to elevated glucose concentrations in the blood, is usually performed by specialists using a manual inspection of high-resolution fundus images based on lesion screening, leading to problems such as high work-intensity and accessibility only in specialized health centers. To support the diagnosis of DR, we propose a deep learning-based (DL) DR lesion classification method through a knowledge distillation (KD) strategy. First, we use the pre-trained DL architecture, Inception-v3, as a teacher model to distill the dataset. Then, a student model, also using the Inception-v3 model, is trained on the distilled dataset to match the performance of the teacher model. In addition, a new combination of Kullback–Leibler (KL) divergence and categorical cross-entropy (CCE) loss is used to measure the difference between the teacher and student models. This combined metric encourages the student model to mimic the predictions of the teacher model. Finally, the trained student model is evaluated on a validation dataset to assess its performance and compare it with both the teacher model and another competitive DL model. Experiments are conducted on the two datasets, corresponding to an imbalanced and a balanced dataset. Two baseline models (Inception-v3 and YOLOv8) are evaluated for reference, obtaining a maximum training accuracy of 66.75% and 90.90%, respectively, and a maximum validation accuracy of 35.94% and 81.52%, both for the imbalanced dataset. On the other hand, the proposed DR classification model achieves an average training accuracy of 99.01% and an average validation accuracy of 97.30%, overcoming the baseline models and other state-of-the-art works. Experimental results show that the proposed model achieves competitive results in DR lesion detection and classification tasks, assisting in the early diagnosis of diabetic retinopathy.

Keywords: knowledge distillation; fundus images; diabetic retinopathy; lesion classification; convolutional neural networks; Inception-v3; Kullback–Leibler divergence; categorical cross-entropy; computer-aided diagnosis disease; health (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2227-7390/12/16/2543/pdf (application/pdf)
https://www.mdpi.com/2227-7390/12/16/2543/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jmathe:v:12:y:2024:i:16:p:2543-:d:1458323

Access Statistics for this article

Mathematics is currently edited by Ms. Emma He

More articles in Mathematics from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().