Summary of Oct-selfnet: a Self-supervised Framework with Multi-modal Datasets For Generalized and Robust Retinal Disease Detection, by Fatema-e Jannat et al.
OCT-SelfNet: A Self-Supervised Framework with Multi-Modal Datasets for Generalized and Robust Retinal Disease Detection
by Fatema-E Jannat, Sina Gholami, Minhaj Nur Alam, Hamed Tabkhi
First submitted to arxiv on: 22 Jan 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The research proposes a self-supervised machine learning framework, OCT-SelfNet, for detecting eye diseases using optical coherence tomography (OCT) images. The method combines self-supervised pretraining and supervised fine-tuning with a mask autoencoder based on the SwinV2 backbone. This approach aims to bridge the gap in medical AI by enabling widespread generalized learning from multi-modal data. The paper demonstrates the effectiveness of OCT-SelfNet through extensive experiments on three datasets, outperforming the baseline model Resnet-50 in terms of AUC-ROC and AUC-PR metrics. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The research developed a new machine learning method to help doctors use computers to better diagnose eye diseases from special scans. They combined different types of data and used a two-step training process to make their computer program very good at identifying these diseases. The results show that their method is much better than previous methods, which could lead to improved patient care. |
Keywords
* Artificial intelligence * Auc * Autoencoder * Fine tuning * Machine learning * Mask * Multi modal * Pretraining * Resnet * Self supervised * Supervised
