Rectified flow-based prediction of post-treatment brain MRI from pre-radiotherapy priors for patients with glioma

Purpose/Objective: Brain tumors result in 20 years of lost life on average. Standard therapies induce complex structural changes in the brain that are monitored through MRI. Recent developments in artificial intelligence (AI) enable conditional multimodal image generation from clinical data. In this study, we investigate AI-driven generation of follow-up MRI in patients with in- tracranial tumors through conditional image generation. This approach enables realistic modeling of post-radiotherapy changes, allowing for treatment optimization. Material/Methods: The public SAILOR dataset of 25 patients was used to create a 2D rectified flow model conditioned on axial slices of pre-treatment MRI and RT dose maps. Cross-attention conditioning was used to incorporate temporal and chemotherapy data. The resulting images were validated with structural similarity index measure (SSIM), peak signal-to-noise ratio (PSNR), Dice scores and Jacobian determinants. Results: The resulting model generates realistic follow-up MRI for any time point, while integrating treatment information. Comparing real versus predicted images, SSIM is 0.88, and PSNR is 22.82. Tissue segmentations from real versus predicted MRI result in a mean Dice-Sørensen coefficient (DSC) of 0.91. The rectified flow (RF) model enables up to 250x faster inference than Denoising Diffusion Probabilistic Models (DDPM). Conclusion: The proposed model generates realistic follow-up MRI in real-time, preserving both semantic and visual fidelity as confirmed by image quality metrics and tissue segmentations. Conditional generation allows counterfactual simulations by varying treatment parameters, producing predicted morphological changes. This capability has potential to support adaptive treatment dose planning and personalized outcome prediction for patients with intracranial tumors.

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.

Real-time myocardial landmark tracking for MRI-guided cardiac radio-ablation using Gaussian Processes

The high speed of cardiorespiratory motion introduces a unique challenge for cardiac stereotactic radio-ablation (STAR) treatments with the MR-linac. Such treatments require tracking myocardial landmarks with a maximum latency of 100 ms, which includes the acquisition of the required data. The aim of this study is to present a new method that allows to track myocardial landmarks from few readouts of MRI data, thereby achieving a latency sufficient for STAR treatments. We present a tracking framework that requires only few readouts of k-space data as input, which can be acquired at least an order of magnitude faster than MR-images. Combined with the real-time tracking speed of a probabilistic machine learning framework called Gaussian Processes, this allows to track myocardial landmarks with a sufficiently low latency for cardiac STAR guidance, including both the acquisition of required data, and the tracking inference. The framework is demonstrated in 2D on a motion phantom, and in vivo on volunteers and a ventricular tachycardia (arrhythmia) patient. Moreover, the feasibility of an extension to 3D was demonstrated by in silico 3D experiments with a digital motion phantom. The framework was compared with template matching - a reference, image-based, method - and linear regression methods. Results indicate an order of magnitude lower total latency (<10 ms) for the proposed framework in comparison with alternative methods. The root-mean-square-distances and mean end-point-distance with the reference tracking method was less than 0.8 mm for all experiments, showing excellent (sub-voxel) agreement. The high accuracy in combination with a total latency of less than 10 ms - including data acquisition and processing - make the proposed method a suitable candidate for tracking during STAR treatments.

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.