用7特斯拉MRI训练新模型，精准识别多发性硬化小病灶。
Automated Detection of Multiple Sclerosis Lesions on 7-tesla MRI Using U-net and Transformer-based Segmentation
- 基于U-Net和Transformer的3D模型，直接在7T原始分辨率上训练。
- 在小病灶检测上优于传统工具，体积级Dice达0.61，病灶级达0.20。
- 适合高场强多发性硬化影像研究者，可直接使用开源模型。
超高场7特斯拉（7T）MRI能更清晰显示多发性硬化白质病变（WML），但其对比度与伪影特征与1.5-3特斯拉成像差异显著，导致现有自动分割工具难以直接迁移。本研究分析7T FLAIR扫描，以Lesion Segmentation Tool（LST）输出为基础，经专家手动修正生成参考病灶掩码。作为外部对比，采用原为低场数据开发的LST-LPA和最新LST-AI集成方法。随后在7T FLAIR数据上，于多个分辨率（0.5×0.5×0.5³、1.0×1.0×1.0³、1.5×1.5×2.0³）训练3D UNETR与SegFormer等基于Transformer的模型，并在BraTS 2023框架下采用体素级与病灶级指标评估。在原生0.5×0.5×0.5³分辨率的独立测试集上，7T训练的Transformer模型在重叠度上媲美LST-AI，同时发现更多小病灶，但边界略有波动且偶有伪影误报。在独立7T测试集上，最佳模型SegFormer实现体素级Dice 0.61，病灶级Dice 0.20，显著优于经典方法LST-LPA（体素级Dice 0.39，病灶级Dice 0.02）。在降采样图像上训练的模型性能下降，凸显原始7T分辨率对小病灶检测的重要性。通过开源7T训练模型，旨在为超高场多发性硬化研究提供可复现、即用型的自动化病灶量化资源（https://github.com/maynord/7T-MS-lesion-segmentation）。
原文摘要 · Abstract (English)
Ultra-high field 7-tesla (7T) MRI improves visualization of multiple sclerosis (MS) white matter lesions (WML) but differs sufficiently in contrast and artifacts from 1.5-3T imaging - suggesting that widely used automated segmentation tools may not translate directly. We analyzed 7T FLAIR scans and generated reference WML masks from Lesion Segmentation Tool (LST) outputs followed by expert manual revision. As external comparators, we applied LST-LPA and the more recent LST-AI ensemble, both originally developed on lower-field data. We then trained 3D UNETR and SegFormer transformer-based models on 7T FLAIR at multiple resolutions (0.5x0.5x0.5^3, 1.0x1.0x1.0^3, and 1.5x1.5x2.0^3) and evaluated all methods using voxel-wise and lesion-wise metrics from the BraTS 2023 framework. On the held-out test set at native 0.5x0.5x0.5^3 resolution, 7T-trained transformers achieved competitive overlap with LST-AI while recovering additional small lesions that were missed by classical methods, at the cost of some boundary variability and occasional artifact-related false positives. On a held-out 7 T test set, our best transformer model (SegFormer) achieved a voxel-wise Dice of 0.61 and lesion-wise Dice of 0.20, improving on the classical LST-LPA tool (Dice 0.39, lesion-wise Dice 0.02). Performance decreased for models trained on downsampled images, underscoring the value of native 7T resolution for small-lesion detection. By releasing our 7T-trained models, we aim to provide a reproducible, ready-to-use resource for automated lesion quantification in ultra-high field MS research (https://github.com/maynord/7T-MS-lesion-segmentation).
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。