发表机构
Vanderbilt University Institute of Imaging Science（范德堡大学影像科学研究所）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对超低频场新生儿脑部MRI伪影分级问题，该研究提出提炼式领域内骨干网络LoFi RADIO，通过将基础模型教师提炼为ViT-S学生模型，实现了更优的伪影分级性能且部署成本更低。
AI 中文摘要
超低频场（ULF）MRI使新生儿脑部成像可在资源匮乏环境中部署，但其信噪比（SNR）低、缺乏屏蔽且扫描时间长，极易产生采集伪影，因此亟需自动化质量控制。我们解决LISA 2026任务1a挑战：对ULF T2加权体积的7种常见图像伪影进行多标签严重度分级（0/1/2级）。我们发现，多种骨干网络可与分类MLP成功配对，但无单一骨干网络在所有伪影上均表现最优。为提升性能，我们评估了通过每个伪影的门控路由互补基础模型教师，以及在未标记的低场MRI语料库上将教师提炼为单一领域内ViT-S学生模型（LoFi RADIO）的方案。两种策略均提升了加权综合指标，提炼后的骨干网络性能与门控方案相当或更优，且具有无需在推理时部署多个大型基础模型的额外优势。
英文摘要
Ultra-low-field MRI makes neonatal brain imaging deploy- able in low-resource settings, but its low SNR, lack of shielding, and long scan duration make it especially prone to acquisition artifacts, motivating automated quality control. We address the LISA 2026 Task 1a challenge: multi-label severity grading (0/1/2) of seven common image artifacts on ULF T2 weighted volumes. We identify that a number of backbones may be successfully paired with a classification MLP, but that no single backbone is uniformly best across artifacts. To improve performance, we evaluate routing complementary foundation model teachers through a per-artifact gate, as well as distilling the teachers into a single in-domain ViT-S student (LoFi RADIO) over an unlabeled low-field MRI corpus. Both of these strategies improve the weighted composite. The distilled backbone matches or exceeds the gate and has the added advantage of not requiring deployment of multiple large foundation models at infer- ence.
Comments11 pages, 2 figures, MICCAI 2026 satellite
