Quantifying the Reproducibility of Graph Neural Networks using Multigraph Brain Data

• URL: http://arxiv.org/abs/2109.02248v1
• Date: Mon, 6 Sep 2021 05:31:02 GMT
• Title: Quantifying the Reproducibility of Graph Neural Networks using Multigraph Brain Data
• Authors: Mohammed Amine Gharsallaoui and Islem Rekik
• Abstract summary: Graph neural networks (GNNs) have witnessed an unprecedented proliferation in tackling several problems in computer vision, computer-aided diagnosis, and related fields. While prior studies have focused on boosting the model accuracy, quantifying the most discriminative features identified by GNNs is still an intact problem that yields concerns about their reliability in clinical applications in particular. We propose for the first time, a framework for GNN assessment via the most discriminative features (i.e., biomarkers) shared between different models. To ascertain the soundness of our framework, the assessment embraces variations of different factors such as training strategies and
• Score: 0.0
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Graph neural networks (GNNs) have witnessed an unprecedented proliferation in tackling several problems in computer vision, computer-aided diagnosis, and related fields. While prior studies have focused on boosting the model accuracy, quantifying the reproducibility of the most discriminative features identified by GNNs is still an intact problem that yields concerns about their reliability in clinical applications in particular. Specifically, the reproducibility of biological markers across clinical datasets and distribution shifts across classes (e.g., healthy and disordered brains) is of paramount importance in revealing the underpinning mechanisms of diseases as well as propelling the development of personalized treatment. Motivated by these issues, we propose, for the first time, reproducibility-based GNN selection (RG-Select), a framework for GNN reproducibility assessment via the quantification of the most discriminative features (i.e., biomarkers) shared between different models. To ascertain the soundness of our framework, the reproducibility assessment embraces variations of different factors such as training strategies and data perturbations. Despite these challenges, our framework successfully yielded replicable conclusions across different training strategies and various clinical datasets. Our findings could thus pave the way for the development of biomarker trustworthiness and reliability assessment methods for computer-aided diagnosis and prognosis tasks. RG-Select code is available on GitHub at https://github.com/basiralab/RG-Select.

Related papers

• Benchmarking Reliability of Deep Learning Models for Pathological Gait Classification [2.1548132286330453]
  Researchers have recently sought to leverage advances in machine learning algorithms to detect symptoms of altered gait. This paper analyzes existing approaches to identify gaps inhibiting translation. We propose our strong baseline called Asynchronous Multi-Stream Graph Convolutional Network (AMS-GCN) that can reliably differentiate multiple categories of pathological gaits.
  arXiv  Detail & Related papers  (2024-09-20T16:47:45Z)
• Discovering robust biomarkers of neurological disorders from functional MRI using graph neural networks: A Review [4.799269666410891]
  We provide an overview of how GNN and model explainability techniques have been applied on fMRI datasets for disorder prediction tasks. We find that while most studies have performant models, salient features highlighted in these studies vary greatly across studies on the same disorder. We suggest establishing new standards that are based on objective evaluation metrics to determine the robustness of these potential biomarkers.
  arXiv  Detail & Related papers  (2024-05-01T15:29:55Z)
• Highly Accurate Disease Diagnosis and Highly Reproducible Biomarker Identification with PathFormer [32.26944736442376]
  Graph neural networks (GNNs) have been the dominant deep learning model for analyzing graph-structured data. The root of the challenges is the unique graph structure of biological signaling pathways. We present a novel GNN model architecture, named PathFormer, which integrates signaling network, priori knowledge and omics data to rank biomarkers and predict disease diagnosis.
  arXiv  Detail & Related papers  (2024-02-11T18:23:54Z)
• Genetic InfoMax: Exploring Mutual Information Maximization in High-Dimensional Imaging Genetics Studies [50.11449968854487]
  Genome-wide association studies (GWAS) are used to identify relationships between genetic variations and specific traits. Representation learning for imaging genetics is largely under-explored due to the unique challenges posed by GWAS. We introduce a trans-modal learning framework Genetic InfoMax (GIM) to address the specific challenges of GWAS.
  arXiv  Detail & Related papers  (2023-09-26T03:59:21Z)
• A Comparative Study of Graph Neural Networks for Shape Classification in Neuroimaging [17.775145204666874]
  We present an overview of the current state-of-the-art in geometric deep learning for shape classification in neuroimaging. We find that using FPFH as node features substantially improves GNN performance and generalisation to out-of-distribution data. We then confirm these results hold for a clinically relevant task, using the classification of Alzheimer's disease.
  arXiv  Detail & Related papers  (2022-10-29T19:03:01Z)
• Investigating the Predictive Reproducibility of Federated Graph Neural Networks using Medical Datasets [0.0]
  We present the first work investigating the application of federated GNN models with application to classifying medical imaging and brain connectivity datasets. We showed that federated learning boosts both the accuracy and accuracy of GNN models in such medical learning tasks.
  arXiv  Detail & Related papers  (2022-09-13T14:32:03Z)
• Domain Invariant Model with Graph Convolutional Network for Mammogram Classification [49.691629817104925]
  We propose a novel framework, namely Domain Invariant Model with Graph Convolutional Network (DIM-GCN) We first propose a Bayesian network, which explicitly decomposes the latent variables into disease-related and other disease-irrelevant parts that are provable to be disentangled from each other. To better capture the macroscopic features, we leverage the observed clinical attributes as a goal for reconstruction, via Graph Convolutional Network (GCN)
  arXiv  Detail & Related papers  (2022-04-21T08:23:44Z)
• Many-to-One Distribution Learning and K-Nearest Neighbor Smoothing for Thoracic Disease Identification [83.6017225363714]
  deep learning has become the most powerful computer-aided diagnosis technology for improving disease identification performance. For chest X-ray imaging, annotating large-scale data requires professional domain knowledge and is time-consuming. In this paper, we propose many-to-one distribution learning (MODL) and K-nearest neighbor smoothing (KNNS) methods to improve a single model's disease identification performance.
  arXiv  Detail & Related papers  (2021-02-26T02:29:30Z)
• G-MIND: An End-to-End Multimodal Imaging-Genetics Framework for Biomarker Identification and Disease Classification [49.53651166356737]
  We propose a novel deep neural network architecture to integrate imaging and genetics data, as guided by diagnosis, that provides interpretable biomarkers. We have evaluated our model on a population study of schizophrenia that includes two functional MRI (fMRI) paradigms and Single Nucleotide Polymorphism (SNP) data.
  arXiv  Detail & Related papers  (2021-01-27T19:28:04Z)
• Neuro-symbolic Neurodegenerative Disease Modeling as Probabilistic Programmed Deep Kernels [93.58854458951431]
  We present a probabilistic programmed deep kernel learning approach to personalized, predictive modeling of neurodegenerative diseases. Our analysis considers a spectrum of neural and symbolic machine learning approaches. We run evaluations on the problem of Alzheimer's disease prediction, yielding results that surpass deep learning.
  arXiv  Detail & Related papers  (2020-09-16T15:16:03Z)
• Select-ProtoNet: Learning to Select for Few-Shot Disease Subtype Prediction [55.94378672172967]
  We focus on few-shot disease subtype prediction problem, identifying subgroups of similar patients. We introduce meta learning techniques to develop a new model, which can extract the common experience or knowledge from interrelated clinical tasks. Our new model is built upon a carefully designed meta-learner, called Prototypical Network, that is a simple yet effective meta learning machine for few-shot image classification.
  arXiv  Detail & Related papers  (2020-09-02T02:50:30Z)

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.