面向儿童脑肿瘤分割的无监督域适应
Unsupervised Domain Adaptation for Pediatric Brain Tumor Segmentation
AI总结：
针对成人胶质瘤分割模型迁移到儿童胶质瘤时的域偏移问题，提出带梯度反转层的DA-nnUNet无监督域适应方法，在儿童肿瘤核心区域分割性能大幅提升，接近有监督上限水平。
摘要：
当前针对成人胶质瘤的精准自动分割模型已取得显著进展，但由于成像特征与临床特征存在差异（域偏移），这类模型应用于儿童胶质瘤时性能往往会下降。儿童胶质瘤属于罕见病，通常难以获取充足的标注数据，且人工标注稀缺、成本高昂。\n本研究提出域适应nnU-Net（DA-nnUNet），用于实现从成人胶质瘤（源域）到儿童胶质瘤（目标域）的无监督域适应。具体而言，我们在骨干网络nnU-Net上添加了一个与梯度反转层（GRL）相连的域分类器。当分类器达到极高准确率后，GRL被激活，目标是将分类器学习到的域不变特征迁移到分割模型中，同时保留模型在源域上的分割精度，随后分类器的准确率会逐渐下降至随机猜测水平。整个过程未使用目标域的任何标注数据。\n我们使用BraTS-Adult胶质瘤数据集（样本量N=1251）和BraTS-PED胶质瘤数据集（样本量N=99），将该方法与8种不同的监督模型进行对比。结果显示，与仅使用成人数据训练的模型相比，所提方法在肿瘤核心（TC）区域的性能提升显著：Dice系数提升约32%，95%分位数豪斯多夫距离降低约20。此外，我们的无监督方法在TC区域的表现，与同时使用两个数据集人工标注的实际上限模型相比，无统计学意义上的显著差异。代码已公开于https://github.com/Fjr9516/DA_nnUNet。
英文摘要：
Significant advances have been made toward building accurate automatic segmentation models for adult gliomas. However, the performance of these models often degrades when applied to pediatric glioma due to their imaging and clinical differences (domain shift). Obtaining sufficient annotated data for pediatric glioma is typically difficult because of its rare nature. Also, manual annotations are scarce and expensive. In this work, we propose Domain-Adapted nnU-Net (DA-nnUNet) to perform unsupervised domain adaptation from adult glioma (source domain) to pediatric glioma (target domain). Specifically, we add a domain classifier connected with a gradient reversal layer (GRL) to a backbone nnU-Net. Once the classifier reaches a very high accuracy, the GRL is activated with the goal of transferring domain-invariant features from the classifier to the segmentation model while preserving segmentation accuracy on the source domain. The accuracy of the classifier slowly degrades to chance levels. No annotations are used in the target domain. The method is compared to 8 different supervised models using BraTS-Adult glioma (N=1251) and BraTS-PED glioma data (N=99). The proposed method shows notable performance enhancements in the tumor core (TC) region compared to the model that only uses adult data: ~32% better Dice scores and ~20 better 95th percentile Hausdorff distances. Moreover, our unsupervised approach shows no statistically significant difference compared to the practical upper bound model using manual annotations from both datasets in TC region. The code is shared at https://github.com/Fjr9516/DA_nnUNet.
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。
