文献速递神经肿瘤

利用多任务深度学习对胶质瘤进行分子亚型分型、分级和分割

Combined molecular subtyping, grading, and segmentation of glioma using multi-task deep learning.
PubMed 文献 · Neuro Oncol · 2023-01-01

研究开发单一多任务卷积神经网络,利用术前3D结构MRI同时预测胶质瘤的IDH突变状态、1p/19q共缺失状态和分级,并分割肿瘤;在来自13个研究所的240例独立测试集上,IDH-AUC为0.90,1p/19q共缺失AUC为0.85,分级AUC为0.81,全肿瘤Dice均值为0.84。

要点

  • 多任务深度学习可同时预测胶质瘤分子分型、分级并分割肿瘤。
  • 独立测试集IDH-AUC 0.90,1p/19q共缺失AUC 0.85,分级AUC 0.81。
  • 全肿瘤分割Dice均值0.84,方法在更广泛临床人群中泛化良好。

核心结论

  • 该方法非侵入性预测胶质瘤多个临床相关特征,在独立数据集中表现出高性能并泛化良好。

研究设计与样本

  • 开发单一多任务卷积神经网络,使用完整3D结构术前MRI扫描预测IDH突变状态、1p/19q共缺失状态和肿瘤分级,同时分割肿瘤。
  • 训练队列包含来自16个研究所的1508例胶质瘤患者,独立测试集为来自13个不同研究所的240例患者。

主要发现

  • 独立测试集中IDH-AUC为0.90,1p/19q共缺失AUC为0.85,分级AUC为0.81(II/III/IV级)。
  • 肿瘤分割的全肿瘤Dice均值0.84。

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)。

原文

BACKGROUND: Accurate characterization of glioma is crucial for clinical decision making. A delineation of the tumor is also desirable in the initial decision stages but is time-consuming. Previously, deep learning methods have been developed that can either non-invasively predict the genetic or histological features of glioma, or that can automatically delineate the tumor, but not both tasks at the same time. Here, we present our method that can predict the molecular subtype and grade, while simultaneously providing a delineation of the tumor. METHODS: We developed a single multi-task convolutional neural network that uses the full 3D, structural, preoperative MRI scans to predict the IDH mutation status, the 1p/19q co-deletion status, and the grade of a tumor, while simultaneously segmenting the tumor. We trained our method using a patient cohort containing 1508 glioma patients from 16 institutes. We tested our method on an independent dataset of 240 patients from 13 different institutes. RESULTS: In the independent test set, we achieved an IDH-AUC of 0.90, an 1p/19q co-deletion AUC of 0.85, and a grade AUC of 0.81 (grade II/III/IV). For the tumor delineation, we achieved a mean whole tumor Dice score of 0.84. CONCLUSIONS: We developed a method that non-invasively predicts multiple, clinically relevant features of glioma. Evaluation in an independent dataset shows that the method achieves a high performance and that it generalizes well to the broader clinical population. This first-of-its-kind method opens the door to more generalizable, instead of hyper-specialized, AI methods.

来源:Neuro Oncol,查看原文。版权归原作者所有。

引用

  1. van der Voort SR, Incekara F, Wijnenga MMJ, et al. Combined molecular subtyping, grading, and segmentation of glioma using multi-task deep learning. Neuro Oncol. 2023. PMID: 35788352. doi:10.1093/neuonc/noac166

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。