Lost in Distortion: Uncovering the Domain Gap Between Computer Vision and Brain Imaging -- A Study on Pretraining for Age Prediction

TL;DR

This paper investigates how data quality in neuroimaging affects pretraining for brain age prediction, highlighting the importance of domain-aware data curation to improve model generalization and trustworthiness.

Contribution

It systematically analyzes the impact of neuroimaging data quality on pretraining effectiveness and emphasizes the need for domain-specific data curation practices.

Findings

High-quality scans lead to better pretraining performance.

Low-quality or distorted scans can hinder model learning.

Domain-aware curation improves model generalization.

Abstract

Large-scale brain imaging datasets provide unprecedented opportunities for developing domain foundation models through pretraining. However, unlike natural image datasets in computer vision, these neuroimaging data often exhibit high heterogeneity in quality, ranging from well-structured scans to severely distorted or incomplete brain volumes. This raises a fundamental question: can noise or low-quality scans contribute meaningfully to pretraining, or do they instead hinder model learning? In this study, we systematically explore the role of data quality level in pretraining and its impact on downstream tasks. Specifically, we perform pretraining on datasets with different quality levels and perform fine-tuning for brain age prediction on external cohorts. Our results show significant performance differences across quality levels, revealing both opportunities and limitations. We further discuss the gap between computer vision practices and clinical neuroimaging standards, emphasizing the necessity of domain-aware curation to ensure trusted and generalizable domain-specific foundation models.