在FLAIR MRI中利用银标准掩码进行侧脑室分割的域适应
Domain Adaptation using Silver Standard Masks for Lateral Ventricle Segmentation in FLAIR MRI
AI总结：
提出面向FLAIR MRI侧脑室分割的域适应方法，用传统算法生成目标域银标准掩码并结合源域金标准微调，显著提升跨数据集鲁棒性。
摘要：
侧脑室体积（LVV）是临床研究中的重要生物标志物。我们提出了首个基于迁移学习的液体衰减反转恢复（FLAIR）MRI的LVV分割方法。为缓解源域与目标域之间的协变量偏移，本工作提出了一种域适应方法，该方法在三个目标数据集上优化性能。研究使用一种新颖的传统图像处理脑室分割算法，从目标域生成银标准（SS）掩码，并将其用于补充来自源域Canadian Atherosclerosis Imaging Network（CAIN）的金标准（GS）数据。在四个数据集的留出测试集上测试了四个模型：1）SS+GS：在目标SS掩码上训练，并在源GS掩码上微调；2）GS+SS：在源GS掩码上训练，并在目标SS掩码上微调；3）在源GS上训练（仅GS CAIN）；4）在目标SS掩码上训练（仅SS）。SS+GS模型具有最佳且最一致的性能（平均DSC=0.89，CoV=0.05），并且在三个目标域上相比仅使用GS的模型表现出显著更高的DSC（p<0.05）。结果表明，使用来自目标域的噪声标签进行预训练可使模型适应数据集特有的特征，并提供稳健的参数初始化，而使用GS掩码进行微调则使模型能够学习详细特征。该方法可广泛应用于标注数据稀缺的其他医学影像问题，并可作为逐数据集校准方法，以加速大规模采用。
英文摘要：
Lateral ventricular volume (LVV) is an important biomarker for clinical investigation. We present the first transfer learning-based LVV segmentation method for fluid-attenuated inversion recovery (FLAIR) MRI. To mitigate covariate shifts between source and target domains, this work proposes an domain adaptation method that optimizes performance on three target datasets. Silver standard (SS) masks were generated from the target domain using a novel conventional image processing ventricular segmentation algorithm and used to supplement the gold standard (GS) data from the source domain, Canadian Atherosclerosis Imaging Network (CAIN). Four models were tested on held-out test sets from four datasets: 1) SS+GS: trained on target SS masks and fine-tuned on source GS masks, 2) GS+SS: trained on source GS masks and fine-tuned on target SS masks, 3) trained on source GS (GS CAIN Only) and 4) trained on target SS masks (SS Only). The SS+GS model had the best and most consistent performance (mean DSC = 0.89, CoV = 0.05) and showed significantly (p < 0.05) higher DSC compared to the GS-only model on three target domains. Results suggest pre-training with noisy labels from the target domain allows the model to adapt to the dataset-specific characteristics and provides robust parameter initialization while fine-tuning with GS masks allows the model to learn detailed features. This method has wide application to other medical imaging problems where labeled data is scarce, and can be used as a per-dataset calibration method to accelerate wide-scale adoption.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
