Buser Myrthe A D, van der Steeg Alida F W, Wijnen Marc H W A, Fitski Matthijs, van Tinteren Harm, van den Heuvel-Eibrink Marry M, Littooij Annemieke S, van der Velden Bas H M
Princess Máxima Center for Pediatric Oncology, 3584 CS Utrecht, The Netherlands.
Wilhelmina Children's Hospital, University Medical Center Utrecht, 3584 EA Utrecht, The Netherlands.
Cancers (Basel). 2023 Apr 1;15(7):2115. doi: 10.3390/cancers15072115.
Wilms tumor is a common pediatric solid tumor. To evaluate tumor response to chemotherapy and decide whether nephron-sparing surgery is possible, tumor volume measurements based on magnetic resonance imaging (MRI) are important. Currently, radiological volume measurements are based on measuring tumor dimensions in three directions. Manual segmentation-based volume measurements might be more accurate, but this process is time-consuming and user-dependent. The aim of this study was to investigate whether manual segmentation-based volume measurements are more accurate and to explore whether these segmentations can be automated using deep learning. We included the MRI images of 45 Wilms tumor patients (age 0-18 years). First, we compared radiological tumor volumes with manual segmentation-based tumor volume measurements. Next, we created an automated segmentation method by training a nnU-Net in a five-fold cross-validation. Segmentation quality was validated by comparing the automated segmentation with the manually created ground truth segmentations, using Dice scores and the 95th percentile of the Hausdorff distances (HD95). On average, manual tumor segmentations result in larger tumor volumes. For automated segmentation, the median dice was 0.90. The median HD95 was 7.2 mm. We showed that radiological volume measurements underestimated tumor volume by about 10% when compared to manual segmentation-based volume measurements. Deep learning can potentially be used to replace manual segmentation to benefit from accurate volume measurements without time and observer constraints.
肾母细胞瘤是一种常见的儿科实体瘤。为了评估肿瘤对化疗的反应并决定是否可行保留肾单位手术，基于磁共振成像（MRI）的肿瘤体积测量很重要。目前，放射学体积测量是基于在三个方向上测量肿瘤尺寸。基于手动分割的体积测量可能更准确，但这个过程既耗时又依赖用户。本研究的目的是调查基于手动分割的体积测量是否更准确，并探索这些分割能否使用深度学习实现自动化。我们纳入了45例肾母细胞瘤患者（年龄0至18岁）的MRI图像。首先，我们将放射学肿瘤体积与基于手动分割的肿瘤体积测量进行比较。接下来，我们通过在五折交叉验证中训练nnU-Net创建了一种自动分割方法。通过使用Dice分数和豪斯多夫距离的第95百分位数（HD95）将自动分割与手动创建的真实分割进行比较，来验证分割质量。平均而言，手动肿瘤分割得出的肿瘤体积更大。对于自动分割，中位Dice为0.90。中位HD95为7.2毫米。我们表明，与基于手动分割的体积测量相比，放射学体积测量低估肿瘤体积约10%。深度学习有可能用于取代手动分割，从而在不受时间和观察者限制的情况下受益于准确的体积测量。
