# Self-Adaptive Transfer Learning for Multicenter Glaucoma Classification in Fundus Retina Images

arXiv: https://arxiv.org/abs/2105.03068 · HTML: https://mlsanity.com/paper/2105.03068/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 42 references that are in the map.
- First posted on arXiv 7 May 2021.

## Builds on (most cited first, 24 of 24)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning](https://mlsanity.com/paper/1602.07261/) (2016)
- [Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks](https://mlsanity.com/paper/1703.10593/) (2017)
- [Deep Visual Domain Adaptation: A Survey](https://mlsanity.com/paper/1802.03601/) (2018)
- [Domain Generalization via Model-Agnostic Learning of Semantic Features](https://mlsanity.com/paper/1910.13580/) (2019)
- [REFUGE Challenge: A Unified Framework for Evaluating Automated Methods for Glaucoma Assessment from Fundus Photographs](https://mlsanity.com/paper/1910.03667/) (2019)
- [Convolutional Neural Networks for Medical Image Analysis: Full Training or Fine Tuning?](https://mlsanity.com/paper/1706.00712/) (2017)
- [Domain-Specific Batch Normalization for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1906.03950/) (2019)
- [Deep Reconstruction-Classification Networks for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1607.03516/) (2016)
- [Demystifying Neural Style Transfer](https://mlsanity.com/paper/1701.01036/) (2017)
- [Image Generation From Small Datasets via Batch Statistics Adaptation](https://mlsanity.com/paper/1904.01774/) (2019)
- [Beyond Sharing Weights for Deep Domain Adaptation](https://mlsanity.com/paper/1603.06432/) (2016)
- [Attention Based Glaucoma Detection: A Large-scale Database and CNN Model](https://mlsanity.com/paper/1903.10831/) (2019)
- [Unsupervised Domain Adaptation using Feature-Whitening and Consensus Loss](https://mlsanity.com/paper/1903.03215/) (2019)
- [Unsupervised Reverse Domain Adaptation for Synthetic Medical Images via Adversarial Training](https://mlsanity.com/paper/1711.06606/) (2017)
- [Transfer Adaptation Learning: A Decade Survey](https://mlsanity.com/paper/1903.04687/) (2019)
- [A Lifelong Learning Approach to Brain MR Segmentation Across Scanners and Protocols](https://mlsanity.com/paper/1805.10170/) (2018)
- [Patch-based Output Space Adversarial Learning for Joint Optic Disc and Cup Segmentation](https://mlsanity.com/paper/1902.07519/) (2019)
- [Disc-aware Ensemble Network for Glaucoma Screening from Fundus Image](https://mlsanity.com/paper/1805.07549/) (2018)
- [Boundary-weighted Domain Adaptive Neural Network for Prostate MR Image Segmentation](https://mlsanity.com/paper/1902.08128/) (2019)
- [Transfer learning for multi-center classification of chronic obstructive pulmonary disease](https://mlsanity.com/paper/1701.05013/) (2017)

## Abstract (arXiv)

The early diagnosis and screening of glaucoma are important for patients to receive treatment in time and maintain eyesight. Nowadays, deep learning (DL) based models have been successfully used for computer-aided diagnosis (CAD) of glaucoma from retina fundus images. However, a DL model pre-trained using a dataset from one hospital center may have poor performance on a dataset from another new hospital center and therefore its applications in the real scene are limited. In this paper, we propose a self-adaptive transfer learning (SATL) strategy to fill the domain gap between multicenter datasets. Specifically, the encoder of a DL model that is pre-trained on the source domain is used to initialize the encoder of a reconstruction model. Then, the reconstruction model is trained using only unlabeled image data from the target domain, which makes the encoder in the model adapt itself to extract useful high-level features both for target domain images encoding and glaucoma classification, simultaneously. Experimental results demonstrate that the proposed SATL strategy is effective in the domain adaptation task between one private and two public glaucoma diagnosis datasets, i.e. pri-RFG, REFUGE, and LAG. Moreover, the proposed strategy is completely independent of the source domain data, which meets the real scene application and the privacy protection policy.