NeuroAPS-Net: Neuro-Anatomically Aware Point Cloud Representation for Efficient Alzheimer's Disease Classification

• URL: http://arxiv.org/abs/2604.22883v1
• Date: Fri, 24 Apr 2026 07:09:07 GMT
• Title: NeuroAPS-Net: Neuro-Anatomically Aware Point Cloud Representation for Efficient Alzheimer's Disease Classification
• Abstract summary: Alzheimer's disease (AD) is a progressive neurodegenerative disorder and a major cause of dementia.<n>Most deep learning methods rely on computationally expensive 3D convolutional neural networks (CNNs)<n>We present NeuroAPS-Net, a lightweight geometric deep learning model that incorporates anatomical priors via region-aware feature encoding and ROI token aggregation.
• Score: 3.896010209171511
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Alzheimer's disease (AD) is a progressive neurodegenerative disorder and a major cause of dementia. Structural MRI is widely used to analyze AD-related brain atrophy; however, most deep learning methods rely on computationally expensive 3D convolutional neural networks (CNNs), limiting deployment in resource-constrained settings. This work introduces two main contributions. First, we propose a pipeline that converts T1-weighted MRI into anatomically informed 2D point clouds using Anatomical Priority Sampling (APS), producing ADNI-2DPC, the first neuroanatomically labeled MRI-derived point cloud dataset. Second, we present NeuroAPS-Net, a lightweight geometric deep learning model that incorporates anatomical priors via region-aware feature encoding and ROI token aggregation. Experiments on ADNI-2DPC demonstrate that NeuroAPS-Net achieves competitive classification accuracy while significantly reducing inference latency and GPU memory compared to state-of-the-art point cloud methods. These results highlight the potential of anatomically guided point cloud learning as an efficient and interpretable alternative to voxel-based CNNs for AD classification.

Related papers

• A Gradient-based yet Spike-Timing-Dependent Solution to the Feedback Learning Problem in Neural Microcircuits [43.880352532823956]
  How neural microcircuits (NMCs) solve temporal credit assignment using local spike timing remains a fundamental open question.<n>Here, we reformulate temporal credit assignment as a state separation problem.<n>This enables an online feedback learning framework for NMCs through a tunneling gradient (GT) algorithm and the lead-lag expansion technique.<n> Experimentally, GT-trained NMCs excel at long-timescale evidence integration and noise-robust memory retention.
  arXiv  Detail & Related papers  (2026-09-08T00:27:18Z)
• Robust PnP on a Neuromorphic Processor for Object Pose Estimation [12.523102333406166]
  This paper proposes a novel neuromorphic deployable formulation for robust object estimation on a neuromorphic processor.<n>We use a spiking neural network (SNN) to predict 2D landmarks from event data, where the main layers of the SNN were designed according to the principles of neurons.
  arXiv  Detail & Related papers  (2026-07-18T14:13:29Z)
• Disentangling Neurodegeneration with Brain Age Gap Prediction Models: A Graph Signal Processing Perspective [89.99666725996975]
  The brain age gap prediction (BAGP) models estimate the difference between a person's predicted brain age from data and their chronological age.<n>This tutorial article provides an overview of BAGP and introduces a principled framework for this application based on recent advancements in graph signal processing (GSP)<n>VNNs offer strong theoretical grounding and operational interpretability, enabling robust estimation of brain age gap predictions.
  arXiv  Detail & Related papers  (2025-10-14T17:44:45Z)
• GL-ICNN: An End-To-End Interpretable Convolutional Neural Network for the Diagnosis and Prediction of Alzheimer's Disease [0.9910295091178368]
  We propose a novel model that combines CNNs and EBMs for the diagnosis and prediction of Alzheimer's disease (AD) dementia.<n>The model takes imaging data as input and provides both predictions and interpretable feature importance measures.
  arXiv  Detail & Related papers  (2025-01-20T19:55:50Z)
• AD-Lite Net: A Lightweight and Concatenated CNN Model for Alzheimer's Detection from MRI Images [1.8749305679160366]
  Alzheimer's Disease (AD) is a non-curable progressive neurodegenerative disorder that affects the human brain, leading to a decline in memory, cognitive abilities, and eventually, the ability to carry out daily tasks. There is a need for an automatic Computer Assisted Diagnosis (CAD) system, which can detect Alzheimer's disease at early stages with higher accuracy. We have proposed a novel AD-Lite Net model (trained from scratch), that could alleviate the aforementioned problem.
  arXiv  Detail & Related papers  (2024-09-12T16:00:51Z)
• SNeurodCNN: Structure-focused Neurodegeneration Convolutional Neural Network for Modelling and Classification of Alzheimer's Disease [0.0]
  Alzheimer's disease (AD), the predominant form of dementia, is a growing global challenge. Current clinical diagnoses rely on radiologist expert interpretation, which is prone to human error. This paper proposes a deep learning framework that includes a novel structure-focused neurodegeneration CNN architecture named SNeurodCNN.
  arXiv  Detail & Related papers  (2024-01-08T14:33:57Z)
• Spatial-Temporal DAG Convolutional Networks for End-to-End Joint Effective Connectivity Learning and Resting-State fMRI Classification [42.82118108887965]
  Building comprehensive brain connectomes has proved to be fundamental importance in resting-state fMRI (rs-fMRI) analysis. We model the brain network as a directed acyclic graph (DAG) to discover direct causal connections between brain regions. We propose Spatial-Temporal DAG Convolutional Network (ST-DAGCN) to jointly infer effective connectivity and classify rs-fMRI time series.
  arXiv  Detail & Related papers  (2023-12-16T04:31:51Z)
• PTGB: Pre-Train Graph Neural Networks for Brain Network Analysis [39.16619345610152]
  We propose PTGB, a GNN pre-training framework that captures intrinsic brain network structures, regardless of clinical outcomes, and is easily adaptable to various downstream tasks. PTGB comprises two key components: (1) an unsupervised pre-training technique designed specifically for brain networks, which enables learning from large-scale datasets without task-specific labels; (2) a data-driven parcellation atlas mapping pipeline that facilitates knowledge transfer across datasets with different ROI systems.
  arXiv  Detail & Related papers  (2023-05-20T21:07:47Z)
• Transferability of coVariance Neural Networks and Application to Interpretable Brain Age Prediction using Anatomical Features [119.45320143101381]
  Graph convolutional networks (GCN) leverage topology-driven graph convolutional operations to combine information across the graph for inference tasks. We have studied GCNs with covariance matrices as graphs in the form of coVariance neural networks (VNNs) VNNs inherit the scale-free data processing architecture from GCNs and here, we show that VNNs exhibit transferability of performance over datasets whose covariance matrices converge to a limit object.
  arXiv  Detail & Related papers  (2023-05-02T22:15:54Z)
• Hierarchical Graph Convolutional Network Built by Multiscale Atlases for Brain Disorder Diagnosis Using Functional Connectivity [48.75665245214903]
  We propose a novel framework to perform multiscale FCN analysis for brain disorder diagnosis. We first use a set of well-defined multiscale atlases to compute multiscale FCNs. Then, we utilize biologically meaningful brain hierarchical relationships among the regions in multiscale atlases to perform nodal pooling.
  arXiv  Detail & Related papers  (2022-09-22T04:17:57Z)
• Towards better Interpretable and Generalizable AD detection using Collective Artificial Intelligence [0.0]
  Deep learning methods have been proposed to automate diagnosis and prognosis of Alzheimer's disease. These methods often suffer from a lack of interpretability and generalization. We propose a novel deep framework designed to overcome these limitations.
  arXiv  Detail & Related papers  (2022-06-07T13:02:53Z)
• Deep Convolutional Neural Network based Classification of Alzheimer's Disease using MRI data [8.609787905151563]
  Alzheimer's disease (AD) is a progressive and incurable neurodegenerative disease which destroys brain cells and causes loss to patient's memory. In this paper, we have proposed a smart and accurate way of diagnosing AD based on a two-dimensional deep convolutional neural network (2D-DCNN) using imbalanced three-dimensional MRI dataset. The model classifies MRI into three categories: AD, mild cognitive impairment, and normal control: and has achieved 99.89% classification accuracy with imbalanced classes.
  arXiv  Detail & Related papers  (2021-01-08T06:51:08Z)

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.