Assessing ResNeXt and RegNet Models for Diabetic Retinopathy Classification: A Comprehensive Comparative Study
<b>Background/Objectives:</b> Diabetic retinopathy is a leading cause of vision impairment worldwide, and the development of reliable automated classification systems is crucial for early diagnosis and clinical decision-making. This study presents a comprehensive comparative evaluation o...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-08-01
|
| Series: | Diagnostics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4418/15/15/1966 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849239757170671616 |
|---|---|
| author | Samara Acosta-Jiménez Valeria Maeda-Gutiérrez Carlos E. Galván-Tejada Miguel M. Mendoza-Mendoza Luis C. Reveles-Gómez José M. Celaya-Padilla Jorge I. Galván-Tejada Antonio García-Domínguez |
| author_facet | Samara Acosta-Jiménez Valeria Maeda-Gutiérrez Carlos E. Galván-Tejada Miguel M. Mendoza-Mendoza Luis C. Reveles-Gómez José M. Celaya-Padilla Jorge I. Galván-Tejada Antonio García-Domínguez |
| author_sort | Samara Acosta-Jiménez |
| collection | DOAJ |
| description | <b>Background/Objectives:</b> Diabetic retinopathy is a leading cause of vision impairment worldwide, and the development of reliable automated classification systems is crucial for early diagnosis and clinical decision-making. This study presents a comprehensive comparative evaluation of two state-of-the-art deep learning families for the task of classifying diabetic retinopathy using retinal fundus images. <b>Methods:</b> The models were trained and tested in both binary and multi-class settings. The experimental design involved partitioning the data into training (70%), validation (20%), and testing (10%) sets. Model performance was assessed using standard metrics, including precision, sensitivity, specificity, F1-score, and the area under the receiver operating characteristic curve. <b>Results:</b> In binary classification, the ResNeXt101-64x4d model and RegNetY32GT model demonstrated outstanding performance, each achieving high sensitivity and precision. For multi-class classification, ResNeXt101-32x8d exhibited strong performance in early stages, while RegNetY16GT showed better balance across all stages, particularly in advanced diabetic retinopathy cases. To enhance transparency, SHapley Additive exPlanations were employed to visualize the pixel-level contributions for each model’s predictions. <b>Conclusions:</b> The findings suggest that while ResNeXt models are effective in detecting early signs, RegNet models offer more consistent performance in distinguishing between multiple stages of diabetic retinopathy severity. This dual approach combining quantitative evaluation and model interpretability supports the development of more robust and clinically trustworthy decision support systems for diabetic retinopathy screening. |
| format | Article |
| id | doaj-art-c68f44c4eed0498dbe4d255a2851dc6a |
| institution | Kabale University |
| issn | 2075-4418 |
| language | English |
| publishDate | 2025-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Diagnostics |
| spelling | doaj-art-c68f44c4eed0498dbe4d255a2851dc6a2025-08-20T04:00:50ZengMDPI AGDiagnostics2075-44182025-08-011515196610.3390/diagnostics15151966Assessing ResNeXt and RegNet Models for Diabetic Retinopathy Classification: A Comprehensive Comparative StudySamara Acosta-Jiménez0Valeria Maeda-Gutiérrez1Carlos E. Galván-Tejada2Miguel M. Mendoza-Mendoza3Luis C. Reveles-Gómez4José M. Celaya-Padilla5Jorge I. Galván-Tejada6Antonio García-Domínguez7Unidad Académica de Ingeniería Eléctrica, Universidad Autónoma de Zacatecas, Jardín Juárez 147, Centro, Zacatecas 98000, MexicoUnidad Académica de Ingeniería Eléctrica, Universidad Autónoma de Zacatecas, Jardín Juárez 147, Centro, Zacatecas 98000, MexicoUnidad Académica de Ingeniería Eléctrica, Universidad Autónoma de Zacatecas, Jardín Juárez 147, Centro, Zacatecas 98000, MexicoUnidad Académica de Ingeniería Eléctrica, Universidad Autónoma de Zacatecas, Jardín Juárez 147, Centro, Zacatecas 98000, MexicoUnidad Académica de Ingeniería Eléctrica, Universidad Autónoma de Zacatecas, Jardín Juárez 147, Centro, Zacatecas 98000, MexicoUnidad Académica de Ingeniería Eléctrica, Universidad Autónoma de Zacatecas, Jardín Juárez 147, Centro, Zacatecas 98000, MexicoUnidad Académica de Ingeniería Eléctrica, Universidad Autónoma de Zacatecas, Jardín Juárez 147, Centro, Zacatecas 98000, MexicoUnidad Académica de Ingeniería Eléctrica, Universidad Autónoma de Zacatecas, Jardín Juárez 147, Centro, Zacatecas 98000, Mexico<b>Background/Objectives:</b> Diabetic retinopathy is a leading cause of vision impairment worldwide, and the development of reliable automated classification systems is crucial for early diagnosis and clinical decision-making. This study presents a comprehensive comparative evaluation of two state-of-the-art deep learning families for the task of classifying diabetic retinopathy using retinal fundus images. <b>Methods:</b> The models were trained and tested in both binary and multi-class settings. The experimental design involved partitioning the data into training (70%), validation (20%), and testing (10%) sets. Model performance was assessed using standard metrics, including precision, sensitivity, specificity, F1-score, and the area under the receiver operating characteristic curve. <b>Results:</b> In binary classification, the ResNeXt101-64x4d model and RegNetY32GT model demonstrated outstanding performance, each achieving high sensitivity and precision. For multi-class classification, ResNeXt101-32x8d exhibited strong performance in early stages, while RegNetY16GT showed better balance across all stages, particularly in advanced diabetic retinopathy cases. To enhance transparency, SHapley Additive exPlanations were employed to visualize the pixel-level contributions for each model’s predictions. <b>Conclusions:</b> The findings suggest that while ResNeXt models are effective in detecting early signs, RegNet models offer more consistent performance in distinguishing between multiple stages of diabetic retinopathy severity. This dual approach combining quantitative evaluation and model interpretability supports the development of more robust and clinically trustworthy decision support systems for diabetic retinopathy screening.https://www.mdpi.com/2075-4418/15/15/1966diabetic retinopathydeep learningconvolutional neural networkResNeXtRegNetSHAP |
| spellingShingle | Samara Acosta-Jiménez Valeria Maeda-Gutiérrez Carlos E. Galván-Tejada Miguel M. Mendoza-Mendoza Luis C. Reveles-Gómez José M. Celaya-Padilla Jorge I. Galván-Tejada Antonio García-Domínguez Assessing ResNeXt and RegNet Models for Diabetic Retinopathy Classification: A Comprehensive Comparative Study Diagnostics diabetic retinopathy deep learning convolutional neural network ResNeXt RegNet SHAP |
| title | Assessing ResNeXt and RegNet Models for Diabetic Retinopathy Classification: A Comprehensive Comparative Study |
| title_full | Assessing ResNeXt and RegNet Models for Diabetic Retinopathy Classification: A Comprehensive Comparative Study |
| title_fullStr | Assessing ResNeXt and RegNet Models for Diabetic Retinopathy Classification: A Comprehensive Comparative Study |
| title_full_unstemmed | Assessing ResNeXt and RegNet Models for Diabetic Retinopathy Classification: A Comprehensive Comparative Study |
| title_short | Assessing ResNeXt and RegNet Models for Diabetic Retinopathy Classification: A Comprehensive Comparative Study |
| title_sort | assessing resnext and regnet models for diabetic retinopathy classification a comprehensive comparative study |
| topic | diabetic retinopathy deep learning convolutional neural network ResNeXt RegNet SHAP |
| url | https://www.mdpi.com/2075-4418/15/15/1966 |
| work_keys_str_mv | AT samaraacostajimenez assessingresnextandregnetmodelsfordiabeticretinopathyclassificationacomprehensivecomparativestudy AT valeriamaedagutierrez assessingresnextandregnetmodelsfordiabeticretinopathyclassificationacomprehensivecomparativestudy AT carlosegalvantejada assessingresnextandregnetmodelsfordiabeticretinopathyclassificationacomprehensivecomparativestudy AT miguelmmendozamendoza assessingresnextandregnetmodelsfordiabeticretinopathyclassificationacomprehensivecomparativestudy AT luiscrevelesgomez assessingresnextandregnetmodelsfordiabeticretinopathyclassificationacomprehensivecomparativestudy AT josemcelayapadilla assessingresnextandregnetmodelsfordiabeticretinopathyclassificationacomprehensivecomparativestudy AT jorgeigalvantejada assessingresnextandregnetmodelsfordiabeticretinopathyclassificationacomprehensivecomparativestudy AT antoniogarciadominguez assessingresnextandregnetmodelsfordiabeticretinopathyclassificationacomprehensivecomparativestudy |