解决儿科脑MRI伪影评估中的类别不平衡问题，提升自动质量判断准确率。
BRIQA: Balanced Reweighting in Image Quality Assessment of Pediatric Brain MRI
- 基于梯度的动态损失重加权，调节不同伪影类别的贡献度。
- 旋转批量训练使少数类伪影样本充分学习，平均宏F1提升至0.706。
- 特别改善噪声、条带、定位等常见伪影分类，适合医学影像质检场景。
评估儿科脑MRI中伪影的严重程度对诊断准确性至关重要，尤其在低场系统中信号噪声比降低。人工评估耗时且主观，亟需鲁棒的自动化方案。本文提出BRIQA（Balanced Reweighting in Image Quality Assessment），针对伪影严重程度类别不平衡问题，采用基于梯度的损失重加权动态调整每类贡献，并引入旋转批量策略确保欠代表类别持续暴露。实验表明，单一架构无法在所有伪影类型上表现最优，凸显架构多样性的重要性。旋转批量配置结合交叉熵损失，显著提升多指标性能。BRIQA将平均宏F1分数从0.659提升至0.706，其中噪声（0.430）、条带（0.098）、定位（0.097）、对比度（0.217）、运动（0.022）和波纹（0.012）等伪影分类均有明显改进。代码已开源：https://github.com/BioMedIA-MBZUAI/BRIQA。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。