Summary
Researchers Reza Rajabli and D. Louis Collins explore whether a compact supervised pretrained 3D CNN can serve as a reusable foundation model for neuroimaging. Their approach freezes the 7.18 million weights of a network previously trained for brain-age prediction and adapts it to downstream Alzheimer's disease tasks using Low-Rank Adaptation (LoRA), adding only about 1% trainable parameters. The paper investigates how well such transfer learning generalizes to new datasets without task-specific retraining, an open question in neuroimaging where labeled data are scarce. Generalizability is assessed across six experiments, including classifying cognitively normal individuals versus dementia patients on MRI. Published on arXiv as 2609.05400, the work provides evidence on parameter-efficient adaptation for brain MRI analysis in Alzheimer's research.
Overview
- Field: Computer Vision (medical imaging)
- Authors: Reza Rajabli, D. Louis Collins
- Published: 2026-09-04
- arXiv: 2609.05400
Abstract (from the paper)
When there is not enough labeled data to properly train deep learning models, transfer learning can help. We still do not fully understand how effective it is in neuroimaging, especially for Alzheimer's disease research. It is also not clear if these transferred models can work on new datasets without being retrained for each specific task. We evaluate whether a compact, supervised pretrained model can serve as a reusable foundation model for downstream neuroimaging tasks. We freeze the 7.18 million weights of a 3D CNN previously trained for brain-age prediction, and adapt it to each task using Low-Rank Adaptation (LoRA), requiring only ~1% additional trainable parameters. We evaluate generalizability in six experiments. Adapting the model to classify cognitively normal versus Dementia on ...
*Note: the source post's abstract is truncated; see the arXiv link above for the full paper.*
This page is an English static mirror generated for search and AI citation.
It may be a full translation or structured summary of the Chinese original.
Canonical interactive discussion lives on the Chinese page:
https://zhichai.net/topic/178634622