Radiologic versus Segmentation Measurements to Quantify Wilms Tumor Volume on MRI in Pediatric Patients
by
, , , , ,
Myrthe A. D. Buser
1
,
Alida F. W. van der Steeg
1,*,
Marc H. W. A. Wijnen
1,
Matthijs Fitski
1,
Harm van Tinteren
1,
Marry M. van den Heuvel-Eibrink
1,2
,
Annemieke S. Littooij
1,2 and
Bas H. M. van der Velden
3 1
Princess Máxima Center for Pediatric Oncology, 3584 CS Utrecht, The Netherlands
2
Wilhelmina Children’s Hospital, University Medical Center Utrecht, 3584 EA Utrecht, The Netherlands
3
Image Sciences Institute, University Medical Center Utrecht, Utrecht University, 3584 CX Utrecht, The Netherlands
*
Author to whom correspondence should be addressed.
Cancers 2023, 15(7), 2115; https://doi.org/10.3390/cancers15072115
Submission received: 22 February 2023
/
Revised: 28 March 2023
/
Accepted: 30 March 2023
/
Published: 1 April 2023
(This article belongs to the Topic Artificial Intelligence in Medical Imaging and Image Processing)
Simple Summary
Volume measurements are important in tumor evaluations of children with a Wilms tumor. Current volume measurements might not be accurate. Our study had two aims. Our first aim was to assess whether manual segmentation of MRI can accurately quantify the volume of Wilms tumors. Our second aim was to show if manual segmentation can be automated using deep learning. We compared radiological-based and manual segmentation-based measurements. Next, we developed an automated segmentation method. Radiological measurements underestimate the actual tumor volume by about 10% irrespective of tumor size. Deep learning can potentially be used to replace manual segmentations in volume measurements.
Abstract
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.
Keywords:
Wilms tumor; pediatric oncology; volume measurements; MRI; deep learning
