Learning Temporally Equivariance for Degenerative Disease Progression in OCT by Predicting Future Representations

• URL: http://arxiv.org/abs/2405.09404v2
• Date: Mon, 14 Oct 2024 14:17:24 GMT
• Title: Learning Temporally Equivariance for Degenerative Disease Progression in OCT by Predicting Future Representations
• Authors: Taha Emre, Arunava Chakravarty, Dmitrii Lachinov, Antoine Rivail, Ursula Schmidt-Erfurth, Hrvoje Bogunović,
• Abstract summary: We propose a Time-equivariant Contrastive Learning (TC) method for time-induced transformations. Our model clearly outperforms existing equivariant contrastive methods in predicting progression from intermediate age-related macular degeneration (AMD) to advanced wet-AMD within a specified time-window.
• Score: 2.2069666964830845
• License:
• Abstract: Contrastive pretraining provides robust representations by ensuring their invariance to different image transformations while simultaneously preventing representational collapse. Equivariant contrastive learning, on the other hand, provides representations sensitive to specific image transformations while remaining invariant to others. By introducing equivariance to time-induced transformations, such as disease-related anatomical changes in longitudinal imaging, the model can effectively capture such changes in the representation space. In this work, we propose a Time-equivariant Contrastive Learning (TC) method. First, an encoder embeds two unlabeled scans from different time points of the same patient into the representation space. Next, a temporal equivariance module is trained to predict the representation of a later visit based on the representation from one of the previous visits and the corresponding time interval with a novel regularization loss term while preserving the invariance property to irrelevant image transformations. On a large longitudinal dataset, our model clearly outperforms existing equivariant contrastive methods in predicting progression from intermediate age-related macular degeneration (AMD) to advanced wet-AMD within a specified time-window.

Related papers

• Unsupervised Representation Learning from Sparse Transformation Analysis [79.94858534887801]
  We propose to learn representations from sequence data by factorizing the transformations of the latent variables into sparse components. Input data are first encoded as distributions of latent activations and subsequently transformed using a probability flow model.
  arXiv  Detail & Related papers  (2024-10-07T23:53:25Z)
• Robust Multivariate Time Series Forecasting against Intra- and Inter-Series Transitional Shift [40.734564394464556]
  We present a unified Probabilistic Graphical Model to Jointly capturing intra-/inter-series correlations and modeling the time-variant transitional distribution. We validate the effectiveness and efficiency of JointPGM through extensive experiments on six highly non-stationary MTS datasets.
  arXiv  Detail & Related papers  (2024-07-18T06:16:03Z)
• Changen2: Multi-Temporal Remote Sensing Generative Change Foundation Model [62.337749660637755]
  We present change data generators based on generative models which are cheap and automatic. Changen2 is a generative change foundation model that can be trained at scale via self-supervision. The resulting model possesses inherent zero-shot change detection capabilities and excellent transferability.
  arXiv  Detail & Related papers  (2024-06-26T01:03:39Z)
• Imaging with Equivariant Deep Learning [9.333799633608345]
  We review the emerging field of equivariant imaging and show how it can provide improved generalization and new imaging opportunities. We show the interplay between the acquisition physics and group actions and links to iterative reconstruction, blind compressed sensing and self-supervised learning.
  arXiv  Detail & Related papers  (2022-09-05T02:13:57Z)
• Moment evolution equations and moment matching for stochastic image EPDiff [68.97335984455059]
  Models of image deformation allow study of time-continuous effects transforming images by deforming the image domain. Applications include medical image analysis with both population trends and random subject specific variation. We use moment approximations of the corresponding Ito diffusion to construct estimators for statistical inference in the parameters full model.
  arXiv  Detail & Related papers  (2021-10-07T11:08:11Z)
• Topographic VAEs learn Equivariant Capsules [84.33745072274942]
  We introduce the Topographic VAE: a novel method for efficiently training deep generative models with topographically organized latent variables. We show that such a model indeed learns to organize its activations according to salient characteristics such as digit class, width, and style on MNIST. We demonstrate approximate equivariance to complex transformations, expanding upon the capabilities of existing group equivariant neural networks.
  arXiv  Detail & Related papers  (2021-09-03T09:25:57Z)
• Adversarial Semantic Data Augmentation for Human Pose Estimation [96.75411357541438]
  We propose Semantic Data Augmentation (SDA), a method that augments images by pasting segmented body parts with various semantic granularity. We also propose Adversarial Semantic Data Augmentation (ASDA), which exploits a generative network to dynamiclly predict tailored pasting configuration. State-of-the-art results are achieved on challenging benchmarks.
  arXiv  Detail & Related papers  (2020-08-03T07:56:04Z)
• Learning Disentangled Representations with Latent Variation Predictability [102.4163768995288]
  This paper defines the variation predictability of latent disentangled representations. Within an adversarial generation process, we encourage variation predictability by maximizing the mutual information between latent variations and corresponding image pairs. We develop an evaluation metric that does not rely on the ground-truth generative factors to measure the disentanglement of latent representations.
  arXiv  Detail & Related papers  (2020-07-25T08:54:26Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.