MedElevator Войти в исследования
← Поиск публикаций

DOI 10.1177/20552076261423994

Медицинская библиотека · Digital health · 2026

Unveiling the black box: Explainable transfer learning for ocular disorder diagnosis.

Un Nisa Zaib, Jaffar Arfan, Bhatti Sohail Masood, Jaghdam Ines Hilali, Mazhar Tehseen, Amir Khan Muhammad, Hamam Habib

СтатьяПеревод пока не подготовлен

Аннотация

OBJECTIVE

To systematically evaluate transfer learning (TL) models for multiclass ocular disease diagnosis and assess their reliability using explainable artificial intelligence (AI).

METHODS

Eight pretrained convolutional neural network (CNN) models were evaluated on a public dataset covering cataract, diabetic retinopathy, glaucoma, and normal classes under a unified protocol. Performance was measured using accuracy, precision, recall, and F1-score. Grad-CAM, LIME, and SHAP were used for interpretability, and the Friedman test assessed performance consistency.

RESULTS

Several models achieved near-perfect performance for diabetic retinopathy. DenseNet121 and XceptionNet performed best for cataract detection, while glaucoma showed consistently weaker results, indicating the need for segmentation-based approaches. Despite similar accuracy, explainability revealed substantial differences in model attention. EfficientNetB3 produced the most clinically meaningful visual explanations.

CONCLUSIONS

Accuracy alone is insufficient for trustworthy medical AI. Explainable AI is essential for model selection. EfficientNetB3 offers the best balance between performance and interpretability, and glaucoma diagnosis requires more advanced, segmentation-aware pipelines.

Для цитирования: Un Nisa Zaib, Jaffar Arfan, Bhatti Sohail Masood, Jaghdam Ines Hilali, Mazhar Tehseen, Amir Khan Muhammad, Hamam Habib. Unveiling the black box: Explainable transfer learning for ocular disorder diagnosis.. Digital health. 2026. DOI: 10.1177/20552076261423994.
Подготовка и перевод публикации
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…

История · было → стало

Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.

Тип публикации указан по данным источника. Уровень доказательности автоматически не присваивается.