# A self-training framework for glaucoma grading in OCT B-scans

arXiv: https://arxiv.org/abs/2111.11771 · HTML: https://mlsanity.com/paper/2111.11771/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 22 references that are in the map.
- First posted on arXiv 23 Nov 2021.

## Builds on (most cited first, 9 of 9)

- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Unsupervised Representation Learning by Predicting Image Rotations](https://mlsanity.com/paper/1803.07728/) (2018)
- [Self-training with Noisy Student improves ImageNet classification](https://mlsanity.com/paper/1911.04252/) (2019)
- [Self-Supervised Relational Reasoning for Representation Learning](https://mlsanity.com/paper/2006.05849/) (2020)
- [Clinically Verified Hybrid Deep Learning System for Retinal Ganglion Cells Aware Grading of Glaucomatous Progression](https://mlsanity.com/paper/2010.03872/) (2020)
- [Self-learning for weakly supervised Gleason grading of local patterns](https://mlsanity.com/paper/2105.10420/) (2021)
- [A feature agnostic approach for glaucoma detection in OCT volumes](https://mlsanity.com/paper/1807.04855/) (2018)
- [Glaucoma Detection From Raw Circumapillary OCT Images Using Fully Convolutional Neural Networks](https://mlsanity.com/paper/2006.00027/) (2020)
- [Analysis of Hand-Crafted and Automatic-Learned Features for Glaucoma Detection Through Raw Circmpapillary OCT Images](https://mlsanity.com/paper/2009.04190/) (2020)

## Abstract (arXiv)

In this paper, we present a self-training-based framework for glaucoma grading using OCT B-scans under the presence of domain shift. Particularly, the proposed two-step learning methodology resorts to pseudo-labels generated during the first step to augment the training dataset on the target domain, which is then used to train the final target model. This allows transferring knowledge-domain from the unlabeled data. Additionally, we propose a novel glaucoma-specific backbone which introduces residual and attention modules via skip-connections to refine the embedding features of the latent space. By doing this, our model is capable of improving state-of-the-art from a quantitative and interpretability perspective. The reported results demonstrate that the proposed learning strategy can boost the performance of the model on the target dataset without incurring in additional annotation steps, by using only labels from the source examples. Our model consistently outperforms the baseline by 1-3% across different metrics and bridges the gap with respect to training the model on the labeled target data.