对比多种损失函数，提升新生儿缺氧缺血性脑病病变分割精度
Multimodal HIE Lesion Segmentation in Neonates: A Comparative Study of Loss Functions
- 采用复合损失函数融合区域与边界信息，优化分割效果
- Tversky-HausdorffDT Loss在Dice和表面相似度上表现最优
- 适用于小样本、多灶性病变的医学图像分割任务
新生儿缺氧缺血性脑病（HIE）病变在MRI中的分割是一项关键但具有挑战性的任务，因病变弥散且多灶性，体积差异大，且标注数据稀缺。基于BONBID-HIE数据集，我们采用3D U-Net并结合优化的预处理、增强与训练策略以应对数据限制。本研究旨在识别最适合HIE病变分割的损失函数。评估了Dice、Dice-Focal、Tversky、Hausdorff Distance（HausdorffDT）损失及两种新提出的复合损失——Dice-Focal-HausdorffDT与Tversky-HausdorffDT。结果表明，不同损失函数生成的分割掩膜存在差异，复合损失优于单一损失。其中，Tversky-HausdorffDT Loss在Dice分数与归一化表面Dice上最高，Dice-Focal-HausdorffDT Loss最小化平均表面距离。研究强调了针对任务定制损失函数的重要性，证明结合区域与边界感知损失可显著提升分割精度，即使在有限数据条件下亦然。
原文摘要 · Abstract (English)
Segmentation of Hypoxic-Ischemic Encephalopathy (HIE) lesions in neonatal MRI is a crucial but challenging task due to diffuse multifocal lesions with varying volumes and the limited availability of annotated HIE lesion datasets. Using the BONBID-HIE dataset, we implemented a 3D U-Net with optimized preprocessing, augmentation, and training strategies to overcome data constraints. The goal of this study is to identify the optimal loss function specifically for the HIE lesion segmentation task. To this end, we evaluated various loss functions, including Dice, Dice-Focal, Tversky, Hausdorff Distance (HausdorffDT) Loss, and two proposed compound losses -- Dice-Focal-HausdorffDT and Tversky-HausdorffDT -- to enhance segmentation performance. The results show that different loss functions predict distinct segmentation masks, with compound losses outperforming standalone losses. Tversky-HausdorffDT Loss achieves the highest Dice and Normalized Surface Dice scores, while Dice-Focal-HausdorffDT Loss minimizes Mean Surface Distance. This work underscores the significance of task-specific loss function optimization, demonstrating that combining region-based and boundary-aware losses leads to more accurate HIE lesion segmentation, even with limited training data.
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。