用域随机化提升低场脑部影像分割精度，助力婴幼儿神经发育障碍早期筛查。
Segmenting infant brains across magnetic fields: Domain randomization and annotation curation in ultra-low field MRI
- 通过域随机化增强模型对低场磁共振图像的适应能力
- 在LISA挑战赛中实现对海马和基底节的高精度分割
- 适合关注儿科影像分析与低资源医疗场景的研究者
早期识别神经发育障碍依赖于婴儿脑结构的精确分割，但受快速脑发育、组织对比度差及运动伪影影响，该任务极具挑战。超低场（ULF，0.064~T）MRI虽图像质量较低，却具备低成本、便携、无需镇静等优势，适用于资源匮乏地区。本文针对LISA挑战赛中的海马与基底节分割任务，提出一种域随机化（DR）框架，以弥合高场（HF）与ULF MRI之间的域差异。结果表明，在全脑HF分割数据上预训练并结合DR，可显著提升模型在ULF数据上的泛化能力；进一步通过剔除错误配准的HF到ULF标注，优化训练标签质量，性能再次提升。采用多数投票融合多个模型预测，达到竞争力表现。实验验证了鲁棒增强与标注质量控制相结合，可实现对ULF数据的准确分割。代码已公开于https://github.com/Medical-Image-Analysis-Laboratory/lisasegm。
原文摘要 · Abstract (English)
Early identification of neurodevelopmental disorders relies on accurate segmentation of brain structures in infancy, a task complicated by rapid brain growth, poor tissue contrast, and motion artifacts in pediatric MRI. These challenges are further exacerbated in ultra-low-field (ULF, 0.064~T) MRI, which, despite its lower image quality, offers an affordable, portable, and sedation-free alternative for use in low-resource settings. In this work, we propose a domain randomization (DR) framework to bridge the domain gap between high-field (HF) and ULF MRI in the context of the hippocampi and basal ganglia segmentation in the LISA challenge. We show that pre-training on whole-brain HF segmentations using DR significantly improves generalization to ULF data, and that careful curation of training labels, by removing misregistered HF-to-ULF annotations from training, further boosts performance. By fusing the predictions of several models through majority voting, we are able to achieve competitive performance. Our results demonstrate that combining robust augmentation with annotation quality control can enable accurate segmentation in ULF data. Our code is available at https://github.com/Medical-Image-Analysis-Laboratory/lisasegm
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。