Deep learning-based brain segmentation model performance validation with clinical radiotherapy CT

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.

Generalizable synthetic MRI with physics-informed convolutional networks

In this study, we develop a physics-informed deep learning-based method to synthesize multiple brain magnetic resonance imaging (MRI) contrasts from a single five-minute acquisition and investigate its ability to generalize to arbitrary contrasts to accelerate neuroimaging protocols. A dataset of fifty-five subjects acquired with a standard MRI protocol and a five-minute transient-state sequence was used to develop a physics-informed deep learning-based method. The model, based on a generative adversarial network, maps data acquired from the five-minute scan to "effective" quantitative parameter maps, here named q*-maps, by using its generated PD, T1, and T2 values in a signal model to synthesize four standard contrasts (proton density-weighted, T1-weighted, T2-weighted, and T2-weighted fluid-attenuated inversion recovery), from which losses are computed. The q*-maps are compared to literature values and the synthetic contrasts are compared to an end-to-end deep learning-based method proposed by literature. The generalizability of the proposed method is investigated for five volunteers by synthesizing three non-standard contrasts unseen during training and comparing these to respective ground truth acquisitions via contrast-to-noise ratio and quantitative assessment. The physics-informed method was able to match the high-quality synthMRI of the end-to-end method for the four standard contrasts, with mean \pm standard deviation structural similarity metrics above 0.75 \pm 0.08 and peak signal-to-noise ratios above 22.4 \pm 1.9 and 22.6 \pm 2.1. Additionally, the physics-informed method provided retrospective contrast adjustment, with visually similar signal contrast and comparable contrast-to-noise ratios to the ground truth acquisitions for three sequences unused for model training, demonstrating its generalizability and potential application to accelerate neuroimaging protocols.

SynthRAD2023 Grand Challenge dataset: generating synthetic CT for radiotherapy

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.

Exploring contrast generalisation in deep learning-based brain MRI-to-CT synthesis

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$20.7 HU (mean$\pm\sigma$). Performance on FLAIR significantly improved for the DR model with MAE=99.0$\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 $\gamma$-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.

Accelerated respiratory-resolved 4D-MRI with separable spatio-temporal neural networks

Purpose: To quickly obtain high-quality respiratory-resolved four-dimensional magnetic resonance imaging (4D-MRI), enabling accurate motion quantification for MRI-guided radiotherapy. Methods: A small convolutional neural network called MODEST is proposed to reconstruct 4D-MRI by performing a spatial and temporal decomposition, omitting the need for 4D convolutions to use all the spatio-temporal information present in 4D-MRI. This network is trained on undersampled 4D-MRI after respiratory binning to reconstruct high-quality 4D-MRI obtained by compressed sensing reconstruction. The network is trained, validated, and tested on 4D-MRI of 28 lung cancer patients acquired with a T1-weighted golden-angle radial stack-of-stars sequence. The 4D-MRI of 18, 5, and 5 patients were used for training, validation, and testing. Network performances are evaluated on image quality measured by the structural similarity index (SSIM) and motion consistency by comparing the position of the lung-liver interface on undersampled 4D-MRI before and after respiratory binning. The network is compared to conventional architectures such as a U-Net, which has 30 times more trainable parameters. Results: MODEST can reconstruct high-quality 4D-MRI with higher image quality than a U-Net, despite a thirty-fold reduction in trainable parameters. High-quality 4D-MRI can be obtained using MODEST in approximately 2.5 minutes, including acquisition, processing, and reconstruction. Conclusion: High-quality accelerated 4D-MRI can be obtained using MODEST, which is particularly interesting for MRI-guided radiotherapy.

Deep learning-based synthetic-CT generation in radiotherapy and PET: a review

Recently, deep learning (DL)-based methods for the generation of synthetic computed tomography (sCT) have received significant research attention as an alternative to classical ones. We present here a systematic review of these methods by grouping them into three categories, according to their clinical applications: I) to replace CT in magnetic resonance (MR)-based treatment planning, II) facilitate cone-beam computed tomography (CBCT)-based image-guided adaptive radiotherapy, and III) derive attenuation maps for the correction of Positron Emission Tomography (PET). Appropriate database searching was performed on journal articles published between January 2014 and December 2020. The DL methods' key characteristics were extracted from each eligible study, and a comprehensive comparison among network architectures and metrics was reported. A detailed review of each category was given, highlighting essential contributions, identifying specific challenges, and summarising the achievements. Lastly, the statistics of all the cited works from various aspects were analysed, revealing the popularity and future trends, and the potential of DL-based sCT generation. The current status of DL-based sCT generation was evaluated, assessing the clinical readiness of the presented methods.

CBCT-to-CT synthesis with a single neural network for head-and-neck, lung and breast cancer adaptive radiotherapy

Purpose: CBCT-based adaptive radiotherapy requires daily images for accurate dose calculations. This study investigates the feasibility of applying a single convolutional network to facilitate CBCT-to-CT synthesis for head-and-neck, lung, and breast cancer patients. Methods: Ninety-nine patients diagnosed with head-and-neck, lung or breast cancer undergoing radiotherapy with CBCT-based position verification were included in this study. CBCTs were registered to planning CTs according to clinical procedures. Three cycle-consistent generative adversarial networks (cycle-GANs) were trained in an unpaired manner on 15 patients per anatomical site generating synthetic-CTs (sCTs). Another network was trained with all the anatomical sites together. Performances of all four networks were compared and evaluated for image similarity against rescan CT (rCT). Clinical plans were recalculated on CT and sCT and analysed through voxel-based dose differences and {\gamma}-analysis. Results: A sCT was generated in 10 seconds. Image similarity was comparable between models trained on different anatomical sites and a single model for all sites. Mean dose differences < 0.5% were obtained in high-dose regions. Mean gamma (2%,2mm) pass-rates > 95% were achieved for all sites. Conclusions: Cycle-GAN reduced CBCT artefacts and increased HU similarity to CT, enabling sCT-based dose calculations. The speed of the network can facilitate on-line adaptive radiotherapy using a single network for head-and-neck, lung and breast cancer patients.