使用放射学信息驱动的深度学习级联方法进行儿童脑肿瘤分割
Segmentation of Pediatric Brain Tumors using a Radiologically informed, Deep Learning Cascade
AI总结：
本研究提出一种基于放射学指南的两阶段级联nnU-Net方法，通过从粗到细分割儿童脑肿瘤亚结构，在BraTS-PEDs 2024挑战赛中取得优于基线nnU-Net的分割性能。
摘要：
对儿童患者弥漫性内生性脑桥胶质瘤（DIPG）和弥漫性中线胶质瘤（DMG）脑肿瘤的监测是评估治疗反应的关键。儿童神经肿瘤学反应评估（RAPNO）指南建议使用MRI对这些肿瘤进行体积测量。诸如脑肿瘤分割（BraTS）挑战赛等分割挑战促进了可复现、可泛化且准确的自动化方法的发展，以辅助这些任务。本研究提出了一种对现有nnU-Net方法的新颖改编，用于儿童脑肿瘤分割，并提交至BraTS-PEDs 2024挑战赛。我们将带有层次级联的改编版nnU-Net应用于BraTS-PEDs 2024挑战赛的分割任务。作为基线模型的nnU-Net残差编码器变体已经能够提供高质量的分割结果。我们对nnU-Net的实现进行了多处修改，并设计了一种新颖的两阶段级联nnU-Net，以从粗到细地分割脑肿瘤的亚结构。利用nnU-Net残差编码器的输出（该编码器经过训练，可从T1w、T1w-CE、T2w和T2-FLAIR MRI中分割CC、ED、ET和NET肿瘤标签），将这些输出传递给两个额外的模型：一个用于分类ET与NET，另一个使用级联学习分类CC与ED。我们使用放射学指南来指导在这些级联模型中使用哪种多参数MRI（mpMRI）。与默认nnU-Net和集成nnU-Net作为基线方法相比，我们的新方法为BraTS-PEDs 2024挑战赛提供了稳健的分割结果，在ET、NET、CC和ED上分别取得了0.657、0.904、0.703和0.967的平均Dice分数，以及76.2、10.1、111.0和12.3的HD95值。
英文摘要：
Monitoring of Diffuse Intrinsic Pontine Glioma (DIPG) and Diffuse Midline Glioma (DMG) brain tumors in pediatric patients is key for assessment of treatment response. Response Assessment in Pediatric Neuro-Oncology (RAPNO) guidelines recommend the volumetric measurement of these tumors using MRI. Segmentation challenges, such as the Brain Tumor Segmentation (BraTS) Challenge, promote development of automated approaches which are replicable, generalizable and accurate, to aid in these tasks. The current study presents a novel adaptation of existing nnU-Net approaches for pediatric brain tumor segmentation, submitted to the BraTS-PEDs 2024 challenge. We apply an adapted nnU-Net with hierarchical cascades to the segmentation task of the BraTS-PEDs 2024 challenge. The residual encoder variant of nnU-Net, used as our baseline model, already provides high quality segmentations. We incorporate multiple changes to the implementation of nnU-Net and devise a novel two-stage cascaded nnU-Net to segment the substructures of brain tumors from coarse to fine. Using outputs from the nnU-Net Residual Encoder (trained to segment CC, ED, ET and NET tumor labels from T1w, T1w-CE, T2w and T2-FLAIR MRI), these are passed to two additional models one classifying ET versus NET and a second classifying CC vs ED using cascade learning. We use radiological guidelines to steer which multi parametric MRI (mpMRI) to use in these cascading models. Compared to a default nnU-Net and an ensembled nnU-net as baseline approaches, our novel method provides robust segmentations for the BraTS-PEDs 2024 challenge, achieving mean Dice scores of 0.657, 0.904, 0.703, and 0.967, and HD95 of 76.2, 10.1, 111.0, and 12.3 for the ET, NET, CC and ED, respectively.
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。
