# SD-LayerNet: Semi-supervised retinal layer segmentation in OCT using disentangled representation with anatomical priors

arXiv: https://arxiv.org/abs/2207.00458 · HTML: https://mlsanity.com/paper/2207.00458/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 17 references that are in the map.
- First posted on arXiv 1 Jul 2022.

## Builds on (most cited first, 8 of 8)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [FiLM: Visual Reasoning with a General Conditioning Layer](https://mlsanity.com/paper/1709.07871/) (2017)
- [Disentangled Representation Learning in Cardiac Image Analysis](https://mlsanity.com/paper/1903.09467/) (2019)
- [ReLayNet: Retinal Layer and Fluid Segmentation of Macular Optical Coherence Tomography using Fully Convolutional Network](https://mlsanity.com/paper/1704.02161/) (2017)
- [Uncertainty guided semi-supervised segmentation of retinal layers in OCT images](https://mlsanity.com/paper/2103.02083/) (2021)
- [Adaptivity without Compromise: A Momentumized, Adaptive, Dual Averaged Gradient Method for Stochastic Optimization](https://mlsanity.com/paper/2101.11075/) (2021)
- [Residual Attention U-Net for Automated Multi-Class Segmentation of COVID-19 Chest CT Images](https://mlsanity.com/paper/2004.05645/) (2020)
- [Joint Segmentation and Uncertainty Visualization of Retinal Layers in Optical Coherence Tomography Images using Bayesian Deep Learning](https://mlsanity.com/paper/1809.04282/) (2018)

## Built on by (most cited first, 7 of 7)

- [SD-RetinaNet: Topologically Constrained Semi-Supervised Retinal Lesion and Layer Segmentation in OCT](https://mlsanity.com/paper/2509.20864/) (2025)
- [Formula-Driven Data Augmentation and Partial Retinal Layer Copying for Retinal Layer Segmentation](https://mlsanity.com/paper/2410.01185/) (2024)
- [Exploiting Intermediate Reconstructions in Optical Coherence Tomography for Test-Time Adaption of Medical Image Segmentation](https://mlsanity.com/paper/2603.05041/) (2026)
- [UOPSL: Unpaired OCT Predilection Sites Learning for Fundus Image Diagnosis Augmentation](https://mlsanity.com/paper/2509.08624/) (2025)
- [Fully Automated High-Precision Segmentation of Retinal Atrophy and Ellipsoid Zone Thickness in OCT: A Reliable Tool for Real-World GA Monitoring](https://mlsanity.com/paper/2606.31502/) (2026)
- [Spatial Normalization for Cross-Domain Retinal Layer Segmentation in Optical Coherence Tomography](https://mlsanity.com/paper/2607.16065/) (2026)
- [PC-Seg: Progressive Cross-View Consistency for 3D OCT Segmentation from Sparse 2D Annotations](https://mlsanity.com/paper/2607.17718/) (2026)

## Abstract (arXiv)

Optical coherence tomography (OCT) is a non-invasive 3D modality widely used in ophthalmology for imaging the retina. Achieving automated, anatomically coherent retinal layer segmentation on OCT is important for the detection and monitoring of different retinal diseases, like Age-related Macular Disease (AMD) or Diabetic Retinopathy. However, the majority of state-of-the-art layer segmentation methods are based on purely supervised deep-learning, requiring a large amount of pixel-level annotated data that is expensive and hard to obtain. With this in mind, we introduce a semi-supervised paradigm into the retinal layer segmentation task that makes use of the information present in large-scale unlabeled datasets as well as anatomical priors. In particular, a novel fully differentiable approach is used for converting surface position regression into a pixel-wise structured segmentation, allowing to use both 1D surface and 2D layer representations in a coupled fashion to train the model. In particular, these 2D segmentations are used as anatomical factors that, together with learned style factors, compose disentangled representations used for reconstructing the input image. In parallel, we propose a set of anatomical priors to improve network training when a limited amount of labeled data is available. We demonstrate on the real-world dataset of scans with intermediate and wet-AMD that our method outperforms state-of-the-art when using our full training set, but more importantly largely exceeds state-of-the-art when it is trained with a fraction of the labeled data.