Ata uhi

Diabetic Retinopathy Detection with Uncertainty scores: A Combined Approach Using Transfer Learning and Ensemble Calibration

I tiakina i:
I whakaputaina i:ADCAIJ : Advances in Distributed Computing and Artificial Intelligence Journal vol. 14 (2025), p. e32209-e32235
Kaituhi matua: Verma, Preeti
Ētahi atu kaituhi: Sivasankar Elango, Singh, Kunwar
I whakaputaina:
Ediciones Universidad de Salamanca
Ngā marau:
Accuracy
Calibration
Diabetes
Diagnostic systems
Deep learning
Machine learning
Confidence intervals
Statistical analysis
Diabetic retinopathy
Uncertainty
Artificial neural networks
Neural networks
Urunga tuihono:Citation/Abstract
Full Text - PDF
Ngā Tūtohu: Tāpirihia he Tūtohu
Kāore He Tūtohu, Me noho koe te mea tuatahi ki te tūtohu i tēnei pūkete!
Whakarāpopotonga:The rising prevalence of diabetes has made Diabetic Retinopathy (DR) a major cause of blindness, underscoring the necessity for a computer-aided diagnostic system that can support clinical diagnoses without requiring extensive human effort. Many researchers have turned to deep learning to create automated screening and diagnostic tools for DR. However, for such systems to be truly effective in clinical practice, they must provide highly accurate assessments and well-calibrated estimates of uncertainty. Unfortunately, deep neural networks often tend to be overconfident in their predictions and are not easily amenable to probabilistic approaches. In our study, we introduce a novel approach for evaluating diagnostic uncertainty in DR predictions by employing ensemble-based calibration techniques. What sets our approach apart from cutting-edge convolutional neural network models is our use of the EfficientNet architecture, which offers superior accuracy through transfer learning. We then apply a set of post-calibration techniques to transform the model's probabilistic output into a confidence level. To gauge the uncertainty of our forecasts, we compute the entropy of the calibrated confidence value. This approach greatly assists users in determining whether it is necessary to seek a second opinion. Our model achieves an impressive accuracy score of 96 %, and our ensemble technique exhibits a notable reduction in Expected Calibration Error (ECE), in addition to providing a reassuring uncertainty score.
ISSN:2255-2863
DOI:10.14201/adcaij.32209
Puna:Advanced Technologies & Aerospace Database