发表机构
Unité de Recherche en Systèmes Intelligents Avancés (URSIA), Institut Supérieur du Numérique (SupNum); University of Basel（高级智能系统研究单位（URSIA），数字高等学院（SupNum）; 巴塞尔大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
AlignUS通过跨模态知识蒸馏将MRI解剖知识迁移至舌部超声分类器，在推理时仅需超声，实现ALS分类平衡准确率0.958，显著提升低资源场景下的评估性能。
AI 中文摘要
肌萎缩侧索硬化（ALS）是一种进行性神经退行性疾病，其早期评估仍具挑战性，尤其是在MRI通常不可用的低资源环境中。舌部高分辨率超声（HRUS）为评估延髓受累提供了一种便携且低成本的替代方案，但学习可靠的诊断模型受到小数据集以及仅从超声中提取稳健表示的难度的限制。我们提出AlignUS，一种跨模态知识蒸馏框架，将解剖学知识从MRI迁移到基于HRUS的分类器，同时在推理时仅需HRUS。该模型结合了分类损失、监督对比学习和特征级蒸馏，以将HRUS表示与MRI嵌入对齐。AlignUS在四个患者级交叉验证折上汇总实现了患者级平衡准确率0.958、宏F1分数0.963和ROC-AUC 0.990，且相对于HRUS基线和跨模态替代方案具有一致的改进。这些结果表明，MRI衍生的监督可以显著改善基于超声的ALS评估，同时保持低成本且在推理时独立于MRI。
英文摘要
Amyotrophic lateral sclerosis (ALS) is a progressive neurodegenerative disease in which early assessment remains challenging, particularly in low-resource settings where MRI is often unavailable. High-resolution ultrasound (HRUS) of the tongue offers a portable and low-cost alternative for evaluating bulbar involvement, but learning reliable diagnostic models is limited by small datasets and the difficulty of extracting robust representations from ultrasound alone. We propose AlignUS, a cross-modal knowledge distillation framework that transfers anatomical knowledge from MRI to a HRUS-based classifier while requiring only HRUS at inference time. The model combines classification loss, supervised contrastive learning, and feature-level distillation to align HRUS representations with MRI embeddings. AlignUS achieves a patient-level balanced accuracy of 0.958, macro-F1 of 0.963, and ROC-AUC of 0.990, aggregated across four patient-level cross-validation folds, with consistent improvements over HRUS baselines and cross-modal alternatives. These results demonstrate that MRI-derived supervision can substantially improve ultrasound-based ALS assessment while preserving low-cost, inference-time independence from MRI.
