Title | ||
---|---|---|
Feature Representation Learning for Robust Retinal Disease Detection from Optical Coherence Tomography Images |
Abstract | ||
---|---|---|
Ophthalmic images may contain identical-looking pathologies that can cause failure in automated techniques to distinguish different retinal degenerative diseases. Additionally, reliance on large annotated datasets and lack of knowledge distillation can restrict ML-based clinical support systems' deployment in real-world environments. To improve the robustness and transferability of knowledge, an enhanced feature-learning module is required to extract meaningful spatial representations from the retinal subspace. Such a module, if used effectively, can detect unique disease traits and differentiate the severity of such retinal degenerative pathologies. In this work, we propose a robust disease detection architecture with three learning heads, i) A supervised encoder for retinal disease classification, ii) An unsupervised decoder for the reconstruction of disease-specific spatial information, and iii) A novel representation learning module for learning the similarity between encoder-decoder feature and enhancing the accuracy of the model. Our experimental results on two publicly available OCT datasets illustrate that the proposed model outperforms existing state-ofthe-art models in terms of accuracy, interpretability, and robustness for out-of-distribution retinal disease detection. |
Year | DOI | Venue |
---|---|---|
2022 | 10.1007/978-3-031-16525-2_3 | OPHTHALMIC MEDICAL IMAGE ANALYSIS, OMIA 2022 |
Keywords | DocType | Volume |
Retinal degeneration, SD-OCT, Deep learning, Optical coherence tomography, Representation learning | Conference | 13576 |
ISSN | Citations | PageRank |
0302-9743 | 0 | 0.34 |
References | Authors | |
0 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Sharif Amit Kamran | 1 | 0 | 1.01 |
Khondker Fariha Hossain | 2 | 2 | 2.06 |
Alireza Tavakkoli | 3 | 0 | 0.34 |
Stewart Lee Zuckerbrod | 4 | 2 | 1.72 |
Salah A. Baker | 5 | 0 | 0.34 |