Adrian Thummerer, Erik van der Bijl, Arthur Jr Galapon et al.
Purpose: Medical imaging has become increasingly important in diagnosing and treating oncological patients, particularly in radiotherapy. Recent advances in synthetic computed tomography (sCT) generation have increased interest in public challenges to provide data and evaluation metrics for comparing different approaches openly. This paper describes a dataset of brain and pelvis computed tomography (CT) images with rigidly registered CBCT and MRI images to facilitate the development and evaluation of sCT generation for radiotherapy planning. Acquisition and validation methods: The dataset consists of CT, CBCT, and MRI of 540 brains and 540 pelvic radiotherapy patients from three Dutch university medical centers. Subjects' ages ranged from 3 to 93 years, with a mean age of 60. Various scanner models and acquisition settings were used across patients from the three data-providing centers. Details are available in CSV files provided with the datasets. Data format and usage notes: The data is available on Zenodo (https://doi.org/10.5281/zenodo.7260705) under the SynthRAD2023 collection. The images for each subject are available in nifti format. Potential applications: This dataset will enable the evaluation and development of image synthesis algorithms for radiotherapy purposes on a realistic multi-center dataset with varying acquisition protocols. Synthetic CT generation has numerous applications in radiation therapy, including diagnosis, treatment planning, treatment monitoring, and surgical planning.
Wouter A. C. van Amsterdam, Pim A. de Jong, Joost J. C. Verhoeff et al.
In cancer research there is much interest in building and validating outcome predicting outcomes to support treatment decisions. However, because most outcome prediction models are developed and validated without regard to the causal aspects of treatment decision making, many published outcome prediction models may cause harm when used for decision making, despite being found accurate in validation studies. Guidelines on prediction model validation and the checklist for risk model endorsement by the American Joint Committee on Cancer do not protect against prediction models that are accurate during development and validation but harmful when used for decision making. We explain why this is the case and how to build and validate models that are useful for decision making.
Background: Synthetic computed tomography (sCT) has been proposed and increasingly clinically adopted to enable magnetic resonance imaging (MRI)-based radiotherapy. Deep learning (DL) has recently demonstrated the ability to generate accurate sCT from fixed MRI acquisitions. However, MRI protocols may change over time or differ between centres resulting in low-quality sCT due to poor model generalisation. Purpose: investigating domain randomisation (DR) to increase the generalisation of a DL model for brain sCT generation. Methods: CT and corresponding T1-weighted MRI with/without contrast, T2-weighted, and FLAIR MRI from 95 patients undergoing RT were collected, considering FLAIR the unseen sequence where to investigate generalisation. A ``Baseline'' generative adversarial network was trained with/without the FLAIR sequence to test how a model performs without DR. Image similarity and accuracy of sCT-based dose plans were assessed against CT to select the best-performing DR approach against the Baseline. Results: The Baseline model had the poorest performance on FLAIR, with mean absolute error (MAE)=106$\pm$20.7 HU (mean$\pmσ$). Performance on FLAIR significantly improved for the DR model with MAE=99.0$\pm$14.9 HU, but still inferior to the performance of the Baseline+FLAIR model (MAE=72.6$\pm$10.1 HU). Similarly, an improvement in $γ$-pass rate was obtained for DR vs Baseline. Conclusions: DR improved image similarity and dose accuracy on the unseen sequence compared to training only on acquired MRI. DR makes the model more robust, reducing the need for re-training when applying a model on sequences unseen and unavailable for retraining.
Selena Huisman, Matteo Maspero, Marielle Philippens et al.
Manual segmentation of medical images is labor intensive and especially challenging for images with poor contrast or resolution. The presence of disease exacerbates this further, increasing the need for an automated solution. To this extent, SynthSeg is a robust deep learning model designed for automatic brain segmentation across various contrasts and resolutions. This study validates the SynthSeg robust brain segmentation model on computed tomography (CT), using a multi-center dataset. An open access dataset of 260 paired CT and magnetic resonance imaging (MRI) from radiotherapy patients treated in 5 centers was collected. Brain segmentations from CT and MRI were obtained with SynthSeg model, a component of the Freesurfer imaging suite. These segmentations were compared and evaluated using Dice scores and Hausdorff 95 distance (HD95), treating MRI-based segmentations as the ground truth. Brain regions that failed to meet performance criteria were excluded based on automated quality control (QC) scores. Dice scores indicate a median overlap of 0.76 (IQR: 0.65-0.83). The median HD95 is 2.95 mm (IQR: 1.73-5.39). QC score based thresholding improves median dice by 0.1 and median HD95 by 0.05mm. Morphological differences related to sex and age, as detected by MRI, were also replicated with CT, with an approximate 17% difference between the CT and MRI results for sex and 10% difference between the results for age. SynthSeg can be utilized for CT-based automatic brain segmentation, but only in applications where precision is not essential. CT performance is lower than MRI based on the integrated QC scores, but low-quality segmentations can be excluded with QC-based thresholding. Additionally, performing CT-based neuroanatomical studies is encouraged, as the results show correlations in sex- and age-based analyses similar to those found with MRI.
Louis D. van Harten, Jelmer M. Wolterink, Joost J. C. Verhoeff et al.
Accurate MR-to-CT synthesis is a requirement for MR-only workflows in radiotherapy (RT) treatment planning. In recent years, deep learning-based approaches have shown impressive results in this field. However, to prevent downstream errors in RT treatment planning, it is important that deep learning models are only applied to data for which they are trained and that generated synthetic CT (sCT) images do not contain severe errors. For this, a mechanism for online quality control should be in place. In this work, we use an ensemble of sCT generators and assess their disagreement as a measure of uncertainty of the results. We show that this uncertainty measure can be used for two kinds of online quality control. First, to detect input images that are outside the expected distribution of MR images. Second, to identify sCT images that were generated from suitable MR images but potentially contain errors. Such automatic online quality control for sCT generation is likely to become an integral part of MR-only RT workflows.
Louis D. van Harten, Jelmer M. Wolterink, Joost J. C. Verhoeff et al.
Convolutional neural networks (CNNs) have been widely and successfully used for medical image segmentation. However, CNNs are typically considered to require large numbers of dedicated expert-segmented training volumes, which may be limiting in practice. This work investigates whether clinically obtained segmentations which are readily available in picture archiving and communication systems (PACS) could provide a possible source of data to train a CNN for segmentation of organs-at-risk (OARs) in radiotherapy treatment planning. In such data, delineations of structures deemed irrelevant to the target clinical use may be lacking. To overcome this issue, we use multi-label instead of multi-class segmentation. We empirically assess how many clinical delineations would be sufficient to train a CNN for the segmentation of OARs and find that increasing the training set size beyond a limited number of images leads to sharply diminishing returns. Moreover, we find that by using multi-label segmentation, missing structures in the reference standard do not have a negative effect on overall segmentation accuracy. These results indicate that segmentations obtained in a clinical workflow can be used to train an accurate OAR segmentation model.