Publications by authors named "M B van Herk"
Background: High-resolution (HR) 3D MR images provide detailed soft-tissue information that is useful in assessing long-term side-effects after treatment in childhood cancer survivors, such as morphological changes in brain structures. However, these images require long acquisition times, so routinely acquired follow-up images after treatment often consist of 2D low-resolution (LR) images (with thick slices in multiple planes).
Purpose: In this work, we present a super-resolution convolutional neural network, based on previous single-image MRI super-resolution work, that can reconstruct a HR image from 2D LR slices in multiple planes in order to facilitate the extraction of structural biomarkers from routine scans.
Increasing radiotherapy dose to select cardiac structures is associated with cardiac events and premature death. Previous studies have found a dose-response relationship for structures at the base of the heart. We have defined a new cardiac anatomical region at risk for radiotherapy by consensus opinion, based on image-based data-mining studies.
View Article and Find Full Text PDFArticle Synopsis
- IBDM for breast radiotherapy needs better spatial normalisation due to differences in treatment positioning and breast characteristics, prompting an optimization study.
- Data from 996 patients were analyzed using various deformable image registration methods to improve the accuracy of spatial normalisation during treatment.
- The B-spline algorithm with normalised mutual information was identified as the most effective method, with supine registrations achieving the highest accuracy, while arm positioning did not significantly affect outcomes.