Self-Supervised Longitudinal Neighbourhood Embedding

• URL: http://arxiv.org/abs/2103.03840v2
• Date: Tue, 9 Mar 2021 02:44:14 GMT
• Title: Self-Supervised Longitudinal Neighbourhood Embedding
• Authors: Jiahong Ouyang and Qingyu Zhao and Ehsan Adeli and Edith V Sullivan and Adolf Pfefferbaum and Greg Zaharchuk and Kilian M Pohl
• Abstract summary: We propose a self-supervised strategy for representation learning named Longitudinal Neighborhood Embedding. Motivated by concepts in contrastive learning, LNE explicitly models the similarity between trajectory vectors across different subjects. We apply LNE to longitudinal T1w MRIs of two neuroimaging studies: a dataset composed of 274 healthy subjects, and Alzheimer's Disease Neuroimaging Initiative.
• Score: 13.633165258766418
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Longitudinal MRIs are often used to capture the gradual deterioration of brain structure and function caused by aging or neurological diseases. Analyzing this data via machine learning generally requires a large number of ground-truth labels, which are often missing or expensive to obtain. Reducing the need for labels, we propose a self-supervised strategy for representation learning named Longitudinal Neighborhood Embedding (LNE). Motivated by concepts in contrastive learning, LNE explicitly models the similarity between trajectory vectors across different subjects. We do so by building a graph in each training iteration defining neighborhoods in the latent space so that the progression direction of a subject follows the direction of its neighbors. This results in a smooth trajectory field that captures the global morphological change of the brain while maintaining the local continuity. We apply LNE to longitudinal T1w MRIs of two neuroimaging studies: a dataset composed of 274 healthy subjects, and Alzheimer's Disease Neuroimaging Initiative (ADNI, N=632). The visualization of the smooth trajectory vector field and superior performance on downstream tasks demonstrate the strength of the proposed method over existing self-supervised methods in extracting information associated with normal aging and in revealing the impact of neurodegenerative disorders. The code is available at \url{https://github.com/ouyangjiahong/longitudinal-neighbourhood-embedding.git}.

Related papers

• Topology-Aware Graph Augmentation for Predicting Clinical Trajectories in Neurocognitive Disorders [27.280927277680515]
  We propose a topology-aware graph augmentation (TGA) framework, comprising a pretext model to train a generalizable encoder and a task-specific model to perform downstream tasks. Experiments on 1, 688 fMRI scans suggest that TGA outperforms several state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-10-31T19:37:20Z)
• Knowledge-Guided Prompt Learning for Lifespan Brain MR Image Segmentation [53.70131202548981]
  We present a two-step segmentation framework employing Knowledge-Guided Prompt Learning (KGPL) for brain MRI. Specifically, we first pre-train segmentation models on large-scale datasets with sub-optimal labels. The introduction of knowledge-wise prompts captures semantic relationships between anatomical variability and biological processes.
  arXiv  Detail & Related papers  (2024-07-31T04:32:43Z)
• Interpretable Spatio-Temporal Embedding for Brain Structural-Effective Network with Ordinary Differential Equation [56.34634121544929]
  In this study, we first construct the brain-effective network via the dynamic causal model. We then introduce an interpretable graph learning framework termed Spatio-Temporal Embedding ODE (STE-ODE) This framework incorporates specifically designed directed node embedding layers, aiming at capturing the dynamic interplay between structural and effective networks.
  arXiv  Detail & Related papers  (2024-05-21T20:37:07Z)
• LSOR: Longitudinally-Consistent Self-Organized Representation Learning [14.10874160164196]
  Interpretability is a key issue when applying deep learning models to longitudinal brain MRIs. One way to address this issue is by visualizing the high-dimensional latent spaces generated by deep learning via self-organizing maps (SOM) We propose the first self-supervised SOM approach that derives a high-dimensional, interpretable representation stratified by brain age.
  arXiv  Detail & Related papers  (2023-09-30T01:31:24Z)
• Cross-Modal Causal Intervention for Medical Report Generation [109.83549148448469]
  Medical report generation (MRG) is essential for computer-aided diagnosis and medication guidance. Due to the spurious correlations within image-text data induced by visual and linguistic biases, it is challenging to generate accurate reports reliably describing lesion areas. We propose a novel Visual-Linguistic Causal Intervention (VLCI) framework for MRG, which consists of a visual deconfounding module (VDM) and a linguistic deconfounding module (LDM)
  arXiv  Detail & Related papers  (2023-03-16T07:23:55Z)
• DBGDGM: Dynamic Brain Graph Deep Generative Model [63.23390833353625]
  Graphs are a natural representation of brain activity derived from functional magnetic imaging (fMRI) data. It is well known that clusters of anatomical brain regions, known as functional connectivity networks (FCNs), encode temporal relationships which can serve as useful biomarkers for understanding brain function and dysfunction. Previous works, however, ignore the temporal dynamics of the brain and focus on static graphs. We propose a dynamic brain graph deep generative model (DBGDGM) which simultaneously clusters brain regions into temporally evolving communities and learns dynamic unsupervised node embeddings.
  arXiv  Detail & Related papers  (2023-01-26T20:45:30Z)
• fMRI from EEG is only Deep Learning away: the use of interpretable DL to unravel EEG-fMRI relationships [68.8204255655161]
  We present an interpretable domain grounded solution to recover the activity of several subcortical regions from multichannel EEG data. We recover individual spatial and time-frequency patterns of scalp EEG predictive of the hemodynamic signal in the subcortical nuclei.
  arXiv  Detail & Related papers  (2022-10-23T15:11:37Z)
• Reducing Catastrophic Forgetting in Self Organizing Maps with Internally-Induced Generative Replay [67.50637511633212]
  A lifelong learning agent is able to continually learn from potentially infinite streams of pattern sensory data. One major historic difficulty in building agents that adapt is that neural systems struggle to retain previously-acquired knowledge when learning from new samples. This problem is known as catastrophic forgetting (interference) and remains an unsolved problem in the domain of machine learning to this day.
  arXiv  Detail & Related papers  (2021-12-09T07:11:14Z)
• Dynamic Adaptive Spatio-temporal Graph Convolution for fMRI Modelling [0.0]
  We propose a dynamic adaptivetemporal graph convolution (DASTGCN) model to overcome the shortcomings of pre-defined static correlation-based graph structures. The proposed approach allows end-to-end inference of dynamic connections between brain regions via layer-wise graph structure learning module. We evaluate our pipeline on the UKBiobank for age and gender classification tasks from resting-state functional scans.
  arXiv  Detail & Related papers  (2021-09-26T07:19:47Z)
• Longitudinal Self-Supervised Learning [13.094393751939837]
  Ground-truth labels are often missing or expensive to obtain in neuroscience. We propose a new definition of disentanglement by formulating a multivariate mapping between factors associated with an MRI and a latent image representation. We implement this model, named Longitudinal Self-Supervised Learning (LSSL), via a standard autoencoding structure with a cosine loss to disentangle brain age from the image representation.
  arXiv  Detail & Related papers  (2020-06-12T03:35:17Z)
• Longitudinal Pooling & Consistency Regularization to Model Disease Progression from MRIs [11.979581631288832]
  We propose to combine features across visits by coupling feature extraction with a novel longitudinal pooling layer. We evaluate the proposed method on the longitudinal structural MRIs from three datasets: Alzheimer's Disease Neuroimaging Initiative (ADNI), a dataset composed of 274 normal controls and 329 patients with Alcohol Use Disorder (AUD) In all three experiments our method is superior to other widely used approaches for longitudinal classification thus making a unique contribution towards more accurate tracking of the impact of conditions on the brain.
  arXiv  Detail & Related papers  (2020-03-31T05:28:51Z)

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.