mlsanityData to 7 Oct 2026

Morph-SSL: Self-Supervision with Longitudinal Morphing to Predict AMD Progression from OCT

arXiv 2304.08439 ↗First posted 17 Apr 2023eess.IV cs.AI cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

The lack of reliable biomarkers makes predicting the conversion from intermediate to neovascular age-related macular degeneration (iAMD, nAMD) a challenging task. We develop a Deep Learning (DL) model to predict the future risk of conversion of an eye from iAMD to nAMD from its current OCT scan. Although eye clinics generate vast amounts of longitudinal OCT scans to monitor AMD progression, only a small subset can be manually labeled for supervised DL. To address this issue, we propose Morph-SSL, a novel Self-supervised Learning (SSL) method for longitudinal data. It uses pairs of unlabelled OCT scans from different visits and involves morphing the scan from the previous visit to the next. The Decoder predicts the transformation for morphing and ensures a smooth feature manifold that can generate intermediate scans between visits through linear interpolation. Next, the Morph-SSL trained features are input to a Classifier which is trained in a supervised manner to model the cumulative probability distribution of the time to conversion with a sigmoidal function. Morph-SSL was trained on unlabelled scans of 399 eyes (3570 visits). The Classifier was evaluated with a five-fold cross-validation on 2418 scans from 343 eyes with clinical labels of the conversion date. The Morph-SSL features achieved an AUC of 0.766 in predicting the conversion to nAMD within the next 6 months, outperforming the same network when trained end-to-end from scratch or pre-trained with popular SSL methods. Automated prediction of the future risk of nAMD onset can enable timely treatment and individualized AMD management.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 23 of its 42 references that are in the map. First posted on arXiv 17 Apr 2023.

Builds on

23 of 42 references.

References · 23

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
  3. 2017Quo Vadis, Action Recognition? A New Model and the Kinetics Datasetcited by 3,259
  4. 2016Xception: Deep Learning with Depthwise Separable Convolutionscited by 2,320
  5. 2016Identity Mappings in Deep Residual Networkscited by 1,960
  6. 2021Barlow Twins: Self-Supervised Learning via Redundancy Reductioncited by 1,818
  7. 2015Spatial Transformer Networkscited by 1,423
  8. 2021VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learningcited by 1,013
  9. 2018VoxelMorph: A Learning Framework for Deformable Medical Image Registrationcited by 657
  10. 2020X3D: Expanding Architectures for Efficient Video Recognitioncited by 635
  11. 2015Cyclical Learning Rates for Training Neural Networkscited by 627
  12. 2021Big Self-Supervised Models Advance Medical Image Classificationcited by 320
11 more
  1. 2016Generating Images with Perceptual Similarity Metrics based on Deep Networkscited by 221
  2. 2017Low Dose CT Image Denoising Using a Generative Adversarial Network with Wasserstein Distance and Perceptual Losscited by 161
  3. 2020Self supervised contrastive learning for digital histopathologycited by 146
  4. 2021Positional Contrastive Learning for Volumetric Medical Image Segmentationcited by 56
  5. 2021Balanced-MixUp for Highly Imbalanced Medical Image Classificationcited by 46
  6. 2020USCL: Pretraining Deep Ultrasound Image Diagnosis Model through Video Contrastive Representation Learningcited by 34
  7. 2018Inverse-Consistent Deep Networks for Unsupervised Deformable Image Registrationcited by 32
  8. 2019Modeling Disease Progression In Retinal OCTs With Longitudinal Self-Supervised Learningcited by 21
  9. 2022Metadata-enhanced contrastive learning from retinal optical coherence tomography imagescited by 14
  10. 2022TINC: Temporally Informed Non-Contrastive Learning for Disease Progression Modeling in Retinal OCT Volumescited by 12
  11. 2020Development and Validation of a Novel Prognostic Model for Predicting AMD Progression Using Longitudinal Fundus Imagescited by 2

Built on by

Not cited yet.