Cepeda Santiago, Romero Roberto, Luque Lidia, García-Pérez Daniel, Blasco Guillermo, Luppino Luigi Tommaso, Kuttner Samuel, Esteban-Sinovas Olga, Arrese Ignacio, Solheim Ole, Eikenes Live, Karlberg Anna, Pérez-Núñez Ángel, Zanier Olivier, Serra Carlo, Staartjes Victor E, Bianconi Andrea, Rossi Luca Francesco, Garbossa Diego, Escudero Trinidad, Hornero Roberto, Sarabia Rosario
Department of Neurosurgery, Río Hortega University Hospital, Valladolid, Spain.
Center for Biomedical Research in Network of Bioengineering, Biomaterials and Nanomedicine (CIBER-BBN), Valladolid, Spain.
Neurooncol Adv. 2024 Nov 16;6(1):vdae199. doi: 10.1093/noajnl/vdae199. eCollection 2024 Jan-Dec.
The pursuit of automated methods to assess the extent of resection (EOR) in glioblastomas is challenging, requiring precise measurement of residual tumor volume. Many algorithms focus on preoperative scans, making them unsuitable for postoperative studies. Our objective was to develop a deep learning-based model for postoperative segmentation using magnetic resonance imaging (MRI). We also compared our model's performance with other available algorithms.
To develop the segmentation model, a training cohort from 3 research institutions and 3 public databases was used. Multiparametric MRI scans with ground truth labels for contrast-enhancing tumor (ET), edema, and surgical cavity, served as training data. The models were trained using MONAI and nnU-Net frameworks. Comparisons were made with currently available segmentation models using an external cohort from a research institution and a public database. Additionally, the model's ability to classify EOR was evaluated using the RANO-Resect classification system. To further validate our best-trained model, an additional independent cohort was used.
The study included 586 scans: 395 for model training, 52 for model comparison, and 139 scans for independent validation. The nnU-Net framework produced the best model with median Dice scores of 0.81 for contrast ET, 0.77 for edema, and 0.81 for surgical cavities. Our best-trained model classified patients into maximal and submaximal resection categories with 96% accuracy in the model comparison dataset and 84% in the independent validation cohort.
Our nnU-Net-based model outperformed other algorithms in both segmentation and EOR classification tasks, providing a freely accessible tool with promising clinical applicability.
寻求用于评估胶质母细胞瘤切除范围（EOR）的自动化方法具有挑战性，需要精确测量残余肿瘤体积。许多算法专注于术前扫描，使其不适用于术后研究。我们的目标是开发一种基于深度学习的模型，用于使用磁共振成像（MRI）进行术后分割。我们还将我们模型的性能与其他可用算法进行了比较。
为了开发分割模型，使用了来自3个研究机构和3个公共数据库的训练队列。具有用于增强对比肿瘤（ET）、水肿和手术腔的真实标签的多参数MRI扫描用作训练数据。使用MONAI和nnU-Net框架对模型进行训练。使用来自一个研究机构和一个公共数据库的外部队列与当前可用的分割模型进行比较。此外，使用RANO-Resect分类系统评估模型对EOR进行分类的能力。为了进一步验证我们训练最佳的模型，使用了一个额外的独立队列。
该研究包括586次扫描：395次用于模型训练，52次用于模型比较，139次扫描用于独立验证。nnU-Net框架产生了最佳模型，对比ET的中位骰子分数为0.81，水肿为0.77，手术腔为0.81。我们训练最佳的模型在模型比较数据集中将患者分类为最大切除和次最大切除类别，准确率为96%，在独立验证队列中为84%。
我们基于nnU-Net的模型在分割和EOR分类任务中均优于其他算法，提供了一个具有良好临床适用性的免费可用工具。
