PIPNet3D: Interpretable Detection of Alzheimer in MRI Scans

• URL: http://arxiv.org/abs/2403.18328v3
• Date: Mon, 22 Jul 2024 15:04:33 GMT
• Title: PIPNet3D: Interpretable Detection of Alzheimer in MRI Scans
• Authors: Lisa Anita De Santi, Jörg Schlötterer, Michael Scheschenja, Joel Wessendorf, Meike Nauta, Vincenzo Positano, Christin Seifert,
• Abstract summary: Part-prototype neural networks (PP-NN) are an alternative to standard blackbox models. We present PIPNet3D, a prototypical PP-NN for volumetric images. We apply PIPNet3D to the clinical diagnosis of Alzheimer's Disease from structural Magnetic Resonance Imaging (sMRI)
• Score: 2.8254815749464544
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Information from neuroimaging examinations is increasingly used to support diagnoses of dementia, e.g., Alzheimer's disease. While current clinical practice is mainly based on visual inspection and feature engineering, Deep Learning approaches can be used to automate the analysis and to discover new image-biomarkers. Part-prototype neural networks (PP-NN) are an alternative to standard blackbox models, and have shown promising results in general computer vision. PP-NN's base their reasoning on prototypical image regions that are learned fully unsupervised, and combined with a simple-to-understand decision layer. We present PIPNet3D, a PP-NN for volumetric images. We apply PIPNet3D to the clinical diagnosis of Alzheimer's Disease from structural Magnetic Resonance Imaging (sMRI). We assess the quality of prototypes under a systematic evaluation framework, propose new functionally grounded metrics to evaluate brain prototypes and develop an evaluation scheme to assess their coherency with domain experts. Our results show that PIPNet3D is an interpretable, compact model for Alzheimer's diagnosis with its reasoning well aligned to medical domain knowledge. Notably, PIPNet3D achieves the same accuracy as its blackbox counterpart; and removing the remaining clinically irrelevant prototypes from its decision process does not decrease predictive performance.

Related papers

• Patch-based Intuitive Multimodal Prototypes Network (PIMPNet) for Alzheimer's Disease classification [3.144057505325736]
  Part-prototype neural networks integrate the computational advantages of Deep Learning (DL) in an interpretable-by-design architecture. We present PIMPNet, the first interpretable multimodal model for 3D images and demographics applied to the binary classification of Alzheimer's Disease (AD) from 3D sMRI and patient's age.
  arXiv  Detail & Related papers  (2024-07-19T12:58:18Z)
• Brain3D: Generating 3D Objects from fMRI [76.41771117405973]
  We design a novel 3D object representation learning method, Brain3D, that takes as input the fMRI data of a subject. We show that our model captures the distinct functionalities of each region of human vision system. Preliminary evaluations indicate that Brain3D can successfully identify the disordered brain regions in simulated scenarios.
  arXiv  Detail & Related papers  (2024-05-24T06:06:11Z)
• Attention-based Efficient Classification for 3D MRI Image of Alzheimer's Disease [2.6793044027881865]
  This study proposes a novel Alzheimer's disease detection model based on Convolutional Neural Networks. The experimental results indicate that the employed 2D fusion algorithm effectively improves the model's training expense.
  arXiv  Detail & Related papers  (2024-01-25T12:18:46Z)
• Leveraging Brain Modularity Prior for Interpretable Representation Learning of fMRI [38.236414924531196]
  Resting-state functional magnetic resonance imaging (rs-fMRI) can reflect spontaneous neural activities in brain. Previous studies propose to extract fMRI representations through diverse machine/deep learning methods for subsequent analysis. This paper proposes a Brain Modularity-constrained dynamic Representation learning (BMR) framework for interpretable fMRI analysis.
  arXiv  Detail & Related papers  (2023-06-24T23:45:47Z)
• Don't PANIC: Prototypical Additive Neural Network for Interpretable Classification of Alzheimer's Disease [2.4469484645516837]
  We propose PANIC, a prototypical additive neural network for interpretable Alzheimer's disease (AD) classification. We show that PANIC achieves state-of-the-art performance in AD classification, while directly providing local and global explanations.
  arXiv  Detail & Related papers  (2023-03-13T13:56:20Z)
• Behavior Score-Embedded Brain Encoder Network for Improved Classification of Alzheimer Disease Using Resting State fMRI [36.40726715739385]
  We propose a behavior score-embedded encoder network (BSEN) that integrates regularly adminstrated psychological tests information into the encoding procedure of representing subject's restingstate fMRI data. BSEN is based on a 3D convolutional autoencoder structure with contrastive loss jointly optimized using behavior scores from MiniMental State Examination (MMSE) and Clinical Dementia Rating (CDR) Our proposed classification framework of using BSEN achieved an overall recognition accuracy of 59.44% (3-class classification: AD, MCI and Healthy Control) and we further extracted the most discriminative regions between healthy control (HC) and
  arXiv  Detail & Related papers  (2022-11-04T09:58:45Z)
• Attentive Symmetric Autoencoder for Brain MRI Segmentation [56.02577247523737]
  We propose a novel Attentive Symmetric Auto-encoder based on Vision Transformer (ViT) for 3D brain MRI segmentation tasks. In the pre-training stage, the proposed auto-encoder pays more attention to reconstruct the informative patches according to the gradient metrics. Experimental results show that our proposed attentive symmetric auto-encoder outperforms the state-of-the-art self-supervised learning methods and medical image segmentation models.
  arXiv  Detail & Related papers  (2022-09-19T09:43:19Z)
• BrainIB: Interpretable Brain Network-based Psychiatric Diagnosis with Graph Information Bottleneck [38.281423869037575]
  We propose BrainIB, a new graph neural network (GNN) framework to analyze functional magnetic resonance images (fMRI) BrainIB is able to identify the most informative edges in the brain (i.e., subgraph) and generalizes well to unseen data.
  arXiv  Detail & Related papers  (2022-05-07T09:35:23Z)
• Probabilistic 3D surface reconstruction from sparse MRI information [58.14653650521129]
  We present a novel probabilistic deep learning approach for concurrent 3D surface reconstruction from sparse 2D MR image data and aleatoric uncertainty prediction. Our method is capable of reconstructing large surface meshes from three quasi-orthogonal MR imaging slices from limited training sets.
  arXiv  Detail & Related papers  (2020-10-05T14:18:52Z)
• Learning Shape Features and Abstractions in 3D Convolutional Neural Networks for Detecting Alzheimer's Disease [0.0]
  In this thesis, learned shape features and abstractions by 3D ConvNets for detecting Alzheimer's disease were investigated. LRP relevance map of different models revealed which parts of the brain were more relevant for the classification decision. Finally, transfer learning from a convolutional autoencoder was implemented to check whether increasing the number of training samples with patches of input improves learned features and the model performance.
  arXiv  Detail & Related papers  (2020-09-10T17:41:03Z)
• An Explainable 3D Residual Self-Attention Deep Neural Network FOR Joint Atrophy Localization and Alzheimer's Disease Diagnosis using Structural MRI [22.34325971680329]
  We have proposed a novel computer-aided approach for early diagnosis of Alzheimer's disease by introducing an explainable 3D Residual Attention Deep Neural Network (3D ResAttNet) for end-to-end learning from sMRI scans. The experimental results show that the proposed approach has a competitive advantage over the state-of-the-art models in terms of accuracy performance and generalizability.
  arXiv  Detail & Related papers  (2020-08-10T11:08:55Z)

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.