Pratinav Seth (Manipal Institute of Technology); Adil Khan (Manipal Institute of Technology) *; Ananya Gupta (Manipal Institute of Technology) *; Saurabh Kumar Mishra (Manipal institute of technology) *; Akshat Bhandari (Manipal Institute of Technology)
- ~ Equal Contribution
Official implementation of https://arxiv.org/pdf/2211.03148v1.pdf paper.
Deep Ensemble Convolutional Neural Networks has become a methodology of choice for analyzing medical images with a diagnostic performance comparable to a physician, including the diagnosis of Diabetic Retinopathy. However, commonly used techniques are deterministic and are therefore unable to provide any estimate of predictive uncertainty. Quantifying model uncertainty is crucial for reducing the risk of misdiagnosis. A reliable architecture should be well-calibrated to avoid overconfident predictions. To address this, we propose a UATTA-ENS: UncertaintyAware Test-Time Augmented Ensemble Technique for 5 Class PIRC Diabetic Retinopathy Classification to produce reliable and well-calibrated predictions.
This paper was accepted at the Medical Imaging meets NeurIPS Workshop at NeurIPS 2022.
Link to pre-trained checkpoints - https://learnermanipal-my.sharepoint.com/:u:/g/personal/pratinav_seth_learner_manipal_edu/ESBb5eoIFB5OjBTQInlEohoBX7J3DRej9lHDiw7DL945Eg?e=lfBCEg