BRIQA: Balanced Reweighting in Image Quality Assessment of Pediatric Brain MRI

TL;DR

BRIQA introduces a novel method for automated pediatric brain MRI artifact severity assessment that addresses class imbalance using gradient-based reweighting and rotating batching, improving classification performance across artifact types.

Contribution

The paper presents BRIQA, a new approach combining gradient-based loss reweighting and rotating batching to enhance artifact severity classification in pediatric brain MRI.

Findings

Improved macro F1 score from 0.659 to 0.706.

Significant gains in Noise, Zipper, and Positioning artifact classification.

Rotating batching enhances model performance across artifact types.

Abstract

Assessing the severity of artifacts in pediatric brain Magnetic Resonance Imaging (MRI) is critical for diagnostic accuracy, especially in low-field systems where the signal-to-noise ratio is reduced. Manual quality assessment is time-consuming and subjective, motivating the need for robust automated solutions. In this work, we propose BRIQA (Balanced Reweighting in Image Quality Assessment), which addresses class imbalance in artifact severity levels. BRIQA uses gradient-based loss reweighting to dynamically adjust per-class contributions and employs a rotating batching scheme to ensure consistent exposure to underrepresented classes. Through experiments, no single architecture performs best across all artifact types, emphasizing the importance of architectural diversity. The rotating batching configuration improves performance across metrics by promoting balanced learning when combined with cross-entropy loss. BRIQA improves average macro F1 score from 0.659 to 0.706, with notable gains in Noise (0.430), Zipper (0.098), Positioning (0.097), Contrast (0.217), Motion (0.022), and Banding (0.012) artifact severity classification. The code is available at https://github.com/BioMedIA-MBZUAI/BRIQA.