nnU-Net与DeepMedic方法在儿童脑肿瘤自动分割中的训练与比较
本研究利用339例儿童脑肿瘤患者的多参数MR图像训练并比较了两种深度学习3D分割模型DeepMedic与nnU-Net。nnU-Net在全肿瘤及各亚区分割的Dice评分均显著高于DeepMedic(P≤.01),且在外部BraTS-PEDs 2023数据集上展现出高泛化能力。
要点
- nnU-Net在全肿瘤分割上内部测试集平均Dice为0.9,DeepMedic为0.82。
- nnU-Net对增强肿瘤、非增强肿瘤、囊性成分及瘤周水肿的Dice均显著高于DeepMedic。
- nnU-Net外部验证全肿瘤平均Dice为0.87,肿瘤核心为0.83,增强肿瘤为0.48。
核心结论
- 基于儿童特异性数据训练的nnU-Net模型在全肿瘤及亚区分割上优于DeepMedic。
研究设计与样本
- 回顾性比较研究,纳入339例儿童脑肿瘤患者(内部293例,外部46例),使用多参数术前MR图像,手动分割为4个肿瘤亚区作为参考标准,训练并比较DeepMedic与nnU-Net两种深度学习3D分割模型。
关键影像表现/征象
- nnU-Net内部测试集全肿瘤平均Dice为0.9(SD 0.07,中位数0.94),DeepMedic为0.82(SD 0.16)。
- nnU-Net对增强肿瘤、非增强肿瘤、囊性成分、瘤周水肿的平均Dice分别为0.77(SD 0.29)、0.66(SD 0.32)、0.71(SD 0.33)、0.71(SD 0.40)。
- DeepMedic对增强肿瘤、非增强肿瘤、囊性成分、瘤周水肿的平均Dice分别为0.66(SD 0.32)、0.48(SD 0.27)、0.48(SD 0.36)、0.19(SD 0.33)。
- nnU-Net外部验证全肿瘤、肿瘤核心、增强肿瘤的平均Dice分别为0.87(SD 0.13,中位数0.91)、0.83(SD 0.18,中位数0.89)、0.48(SD 0.38,中位数0.58)。
诊断标准与关键数值
- 分割性能以Dice评分评估,nnU-Net各亚区Dice评分均显著高于DeepMedic(P≤.01)。
- 亚区体积占全肿瘤百分比的一致性:内部测试集增强肿瘤相关系数nnU-Net 0.98 vs DeepMedic 0.91,非增强肿瘤0.97 vs 0.75,囊性成分0.98 vs 0.80,瘤周水肿0.95 vs 0.33。
- Bland-Altman分析显示nnU-Net较DeepMedic一致性更好。
临床应用与阅片要点
- 原文未据此给出临床推荐。
局限性
- 原文未报告局限性。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
英文原文(摘要)· 点击展开
BACKGROUND AND PURPOSE: Tumor segmentation is essential in surgical and treatment planning and response assessment and monitoring in pediatric brain tumors, the leading cause of cancer-related death among children. However, manual segmentation is time-consuming and has high interoperator variability, underscoring the need for more efficient methods. After training, we compared 2 deep-learning-based 3D segmentation models, DeepMedic and nnU-Net, with pediatric-specific multi-institutional brain tumor data based on multiparametric MR images.
MATERIALS AND METHODS: Multiparametric preoperative MR imaging scans of 339 pediatric patients (n = 293 internal and n = 46 external cohorts) with a variety of tumor subtypes were preprocessed and manually segmented into 4 tumor subregions, ie, enhancing tumor, nonenhancing tumor, cystic components, and peritumoral edema. After training, performances of the 2 models on internal and external test sets were evaluated with reference to ground truth manual segmentations. Additionally, concordance was assessed by comparing the volume of the subregions as a percentage of the whole tumor between model predictions and ground truth segmentations using the Pearson or Spearman correlation coefficients and the Bland-Altman method.
RESULTS: The mean Dice score for nnU-Net internal test set was 0.9 (SD, 0.07) (median, 0.94) for whole tumor; 0.77 (SD, 0.29) for enhancing tumor; 0.66 (SD, 0.32) for nonenhancing tumor; 0.71 (SD, 0.33) for cystic components, and 0.71 (SD, 0.40) for peritumoral edema, respectively. For DeepMedic, the mean Dice scores were 0.82 (SD, 0.16) for whole tumor; 0.66 (SD, 0.32) for enhancing tumor; 0.48 (SD, 0.27) for nonenhancing tumor; 0.48 (SD, 0.36) for cystic components, and 0.19 (SD, 0.33) for peritumoral edema, respectively. Dice scores were significantly higher for nnU-Net (P ≤ .01). Correlation coefficients for tumor subregion percentage volumes were higher (0.98 versus 0.91 for enhancing tumor, 0.97 versus 0.75 for nonenhancing tumor, 0.98 versus 0.80 for cystic components, 0.95 versus 0.33 for peritumoral edema in the internal test set). Bland-Altman plots were better for nnU-Net compared with DeepMedic. External validation of the trained nnU-Net model on the multi-institutional Brain Tumor Segmentation Challenge in Pediatrics (BraTS-PEDs) 2023 data set revealed high generalization capability in the segmentation of whole tumor, tumor core (a combination of enhancing tumor, nonenhancing tumor, and cystic components), and enhancing tumor with mean Dice scores of 0.87 (SD, 0.13) (median, 0.91), 0.83 (SD, 0.18) (median, 0.89), and 0.48 (SD, 0.38) (median, 0.58), respectively.
CONCLUSIONS: The pediatric-specific data-trained nnU-Net model is superior to DeepMedic for whole tumor and subregion segmentation of pediatric brain tumors.
引用
- Vossough A, Khalili N, Familiar AM, et al. Training and Comparison of nnU-Net and DeepMedic Methods for Autosegmentation of Pediatric Brain Tumors. AJNR Am J Neuroradiol. 2024. PMID: 38724204. doi:10.3174/ajnr.A8293
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。