ReBA-Pred-Net: Weakly-Supervised Regional Brain Age Prediction on MRI
- URL: http://arxiv.org/abs/2602.12751v1
- Date: Fri, 13 Feb 2026 09:31:09 GMT
- Title: ReBA-Pred-Net: Weakly-Supervised Regional Brain Age Prediction on MRI
- Authors: Shuai Shao, Yan Wang, Shu Jiang, Shiyuan Zhao, Xinzhe Luo, Di Yang, Jiangtao Wang, Yutong Bai, Jianguo Zhang,
- Abstract summary: Regional brain age (ReBA) estimation is critical, yet a widely generalizable model has yet to be established.<n>We propose the Regional Brain Age Prediction Network (ReBA-Pred-Net), a Teacher-Student framework for fine-grained brain age estimation.
- Score: 20.74655155594933
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Brain age has become a prominent biomarker of brain health. Yet most prior work targets whole brain age (WBA), a coarse paradigm that struggles to support tasks such as disease characterization and research on development and aging patterns, because relevant changes are typically region-selective rather than brain-wide. Therefore, robust regional brain age (ReBA) estimation is critical, yet a widely generalizable model has yet to be established. In this paper, we propose the Regional Brain Age Prediction Network (ReBA-Pred-Net), a Teacher-Student framework designed for fine-grained brain age estimation. The Teacher produces soft ReBA to guide the Student to yield reliable ReBA estimates with a clinical-prior consistency constraint (regions within the same function should change similarly). For rigorous evaluation, we introduce two indirect metrics: Healthy Control Similarity (HCS), which assesses statistical consistency by testing whether regional brain-age-gap (ReBA minus chronological age) distributions align between training and unseen HC; and Neuro Disease Correlation (NDC), which assesses factual consistency by checking whether clinically confirmed patients show elevated brain-age-gap in disease-associated regions. Experiments across multiple backbones demonstrate the statistical and factual validity of our method.
Related papers
- SurfAge-Net: A Hierarchical Surface-Based Network for Interpretable Fine-Grained Brain Age Prediction [9.571325956619743]
We propose a novel surface-based brain age prediction network (SurfAge-Net) to capture region-specific developmental patterns.<n>SurfAge-Net establishes a new modeling paradigm by incorporating the connectomic principles of cortical organization.<n>It provides spatially precise and biologically interpretable maps of cortical maturation, effectively identifying heterogeneous delays and regional-specific abnormalities.
arXiv Detail & Related papers (2026-01-28T07:01:57Z) - 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) - Explainable Brain Age Gap Prediction in Neurodegenerative Conditions using coVariance Neural Networks [94.06526659234756]
Black-box machine learning approaches to brain age gap prediction have limited practical utility.<n>We apply the VNN-based approach to study brain age gap using cortical thickness features for various prevalent neurodegenerative conditions.<n>Our results reveal distinct anatomic patterns for brain age gap in Alzheimer's disease, frontotemporal dementia, and atypical Parkinsonian disorders.
arXiv Detail & Related papers (2025-01-02T19:37:09Z) - A voxel-level approach to brain age prediction: A method to assess regional brain aging [35.506876461932855]
Voxel-level predictions can provide localized brain age estimates that can provide granular insights into the regional aging processes.
Deep learning-based multitask model is proposed for voxel-level brain age prediction from T1-weighted magnetic resonance images.
arXiv Detail & Related papers (2023-10-17T16:32:38Z) - Robust Brain Age Estimation via Regression Models and MRI-derived
Features [2.028990630951476]
We present a novel brain age estimation framework using the Open Big Healthy Brain (OpenBHB) dataset.
Our approach integrates three different MRI-derived region-wise features and different regression models, resulting in a highly accurate brain age estimation.
arXiv Detail & Related papers (2023-06-08T19:07:22Z) - Explainable Brain Age Prediction using coVariance Neural Networks [94.81523881951397]
We propose an explanation-driven and anatomically interpretable framework for brain age prediction using cortical thickness features.
Specifically, our brain age prediction framework extends beyond the coarse metric of brain age gap in Alzheimer's disease (AD)
We make two important observations: VNNs can assign anatomical interpretability to elevated brain age gap in AD by identifying contributing brain regions.
arXiv Detail & Related papers (2023-05-27T22:28:25Z) - Brain Structural Saliency Over The Ages [0.41998444721319217]
We trained a ResNet model as a BA regressor on T1 structural MRI volumes from a small cross-sectional cohort of 524 individuals.
We show the change in attribution of relevance to different brain regions through the course of ageing.
Some regions increase in relevance with age; some decrease in relevance with age; and others are consistently relevant across ages.
arXiv Detail & Related papers (2022-01-12T09:50:29Z) - Voxel-level Importance Maps for Interpretable Brain Age Estimation [70.5330922395729]
We focus on the task of brain age regression from 3D brain Magnetic Resonance (MR) images using a Convolutional Neural Network, termed prediction model.
We implement a noise model which aims to add as much noise as possible to the input without harming the performance of the prediction model.
We test our method on 13,750 3D brain MR images from the UK Biobank, and our findings are consistent with the existing neuropathology literature.
arXiv Detail & Related papers (2021-08-11T18:08:09Z) - Brain Age Estimation From MRI Using Cascade Networks with Ranking Loss [75.03117866578913]
A novel 3D convolutional network, called two-stage-age-network (TSAN), is proposed to estimate brain age from T1-weighted MRI data.
Experiments with $6586$ MRIs showed that TSAN could provide accurate brain age estimation.
arXiv Detail & Related papers (2021-06-06T07:11:25Z) - Patch-based Brain Age Estimation from MR Images [64.66978138243083]
Brain age estimation from Magnetic Resonance Images (MRI) derives the difference between a subject's biological brain age and their chronological age.
Early detection of neurodegeneration manifesting as a higher brain age can potentially facilitate better medical care and planning for affected individuals.
We develop a new deep learning approach that uses 3D patches of the brain as well as convolutional neural networks (CNNs) to develop a localised brain age estimator.
arXiv Detail & Related papers (2020-08-29T11:50:37Z)
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.