用小块采样提升脑膜斑分割精度，计算量降99%。
Efficient Transformer-Based Localized Patch Sampling for Choroid Plexus Segmentation in Multiple Sclerosis
- 基于SwinUNETR的局部小块采样，精准定位脑室周围区域。
- 多模态输入下平均骰子系数达0.868，显著优于对比模型。
- 计算量仅22,080 GFLOPs，适合临床大规模应用。
侧脑室脉络丛（LVCP）是多发性硬化症相关躯体残疾和神经炎症的重要影像生物标志物。然而手动分割耗时费力，限制其在大规模临床试验和纵向评估中的应用。本研究提出一种基于SwinUNETR的自动分割流程，通过针对性地对脑室内外小块区域进行采样，实现从单模态与多模态MRI中对多发性硬化患者LVCP的自动分割。回顾性分析来自两个独立多发性硬化队列的3T MRI数据（数据集1：n=177；数据集2：n=177；扩展测试集：n=388）。方法采用在32×32×32体素小块上训练的SwinUNETR架构，与3D UXNET模型对比。主要评估指标为骰子相似系数（DSC），辅以计算量（GFLOPs）和95百分位豪斯多夫距离（HD95）。在扩展测试集上，融合MPRAGE与FLAIR的SwinUNETR模型平均DSC为0.868（95% CI: 0.863–0.872），显著优于UXNET（DSC: 0.858 [95% CI: 0.853–0.862]，p<0.0001）。仅使用FLAIR序列时，该方法仍保持高精度DSC为0.863，而UXNET的空间定位性能显著下降（HD95: 1.86 vs. 3.00 mm）。此外，所提框架将计算负载降低99%（91.8 vs. 22,080 GFLOPs）。结合局部化小块采样与SwinUNETR架构，该方法在精度、鲁棒性和计算效率方面均优于现有主流模型，具有广泛临床与科研推广潜力。
原文摘要 · Abstract (English)
Background: The lateral ventricle choroid plexus (LVCP) is gaining recognition as a key imaging biomarker for multiple sclerosis (MS) related to physical disability and neuroinflammation. Yet, manual segmentation of the LVCP is highly tedious, restricting its use in broad clinical trials and longitudinal assessments. This research aims to develop a SwinUNETR-driven pipeline that leverages targeted intra- and peri-ventricular small patch sampling to automatically segment the LVCP in MS from both standalone and multi-modal MRI inputs. Methods: We retrospectively assessed 3T MRI scans across three sets of data stemming from two separate MS-dominant cohorts (Dataset 1: n=177; Dataset 2: n=177; expanded test set: n=388). Our method employed a SwinUNETR architecture trained on 32x32x32 voxel patches, benchmarking it against the 3D UXNET model. The primary metric for evaluation was the Dice Similarity Coefficient (DSC), supplemented by computational demand (GFLOPs) and the 95th percentile Hausdorff Distance (HD95). Results: On the extended test set, the SwinUNETR model secured a mean DSC of 0.868 (95% CI: 0.863-0.872) with MPRAGE and FLAIR combined, showing a statistically significant gain over UXNET (DSC: 0.858 [95% CI: 0.853-0.862], p<0.0001). When restricted to standalone FLAIR inputs, the transformer-based approach sustained a high DSC of 0.863, while the spatial localization of UXNET worsened considerably (HD95: 1.86 vs. 3.00 mm). Importantly, the proposed framework lowered computational load by 99% (91.8 vs. 22,080 GFLOPs). By integrating localized patch sampling with a SwinUNETR architecture, this methodology offers an accurate, robust, and statistically superior alternative to current leading models for LVCP segmentation. Its vast reduction in computational cost makes it ideal for widespread implementation in clinical and research environments.
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。