Artificial intelligence for treatment delivery: image-guided radiotherapy.

Radiation therapy (RT) is a highly digitized field relying heavily on computational methods and, as such, has a high affinity for the automation potential afforded by modern artificial intelligence (AI). This is particularly relevant where imaging is concerned and is especially so during image-guided RT (IGRT). With the advent of online adaptive RT (ART) workflows at magnetic resonance (MR) linear accelerators (linacs) and at cone-beam computed tomography (CBCT) linacs, the need for automation is further increased. AI as applied to modern IGRT is thus one area of RT where we can expect important developments in the near future. In this review article, after outlining modern IGRT and online ART workflows, we cover the role of AI in CBCT and MRI correction for dose calculation, auto-segmentation on IGRT imaging, motion management, and response assessment based on in-room imaging.

Evaluation of magnetic resonance thermometry performance during MR-guided hyperthermia treatment of soft-tissue sarcomas in the lower extremities and pelvis.

INTRODUCTION: This study evaluated the performance of magnetic resonance thermometry (MRT) during deep-regional hyperthermia (HT) in pelvic and lower-extremity soft-tissue sarcomas. MATERIALS AND METHODS: 17 pelvic (45 treatments) and 16 lower-extremity (42 treatments) patients underwent standard regional HT and chemotherapy. Pairs of double-echo gradient-echo scans were acquired during the MR protocol 1.4 s apart. For each pair, precision was quantified using phase data from both echoes ('dual-echo') or only one ('single-echo') in- or excluding body fat pixels in the field drift correction region of interest. The precision of each method was compared to that of the MRT approach using a built-in clinical software tool (SigmaVision). Accuracy was assessed in three lower-extremity patients (six treatments) using interstitial temperature probes. The Jaccard coefficient quantified pretreatment motion; receiver operating characteristic analysis assessed its predictability for acceptable precision (<1 °C) during HT. RESULTS: Compared to the built-in dual-echo approach, single-echo thermometry improved the mean temporal precision from 1.32 ± 0.40 °C to 1.07 ± 0.34 °C (pelvis) and from 0.99 ± 0.28 °C to 0.76 ± 0.23 °C (lower extremities). With body fat-based field drift correction, single-echo mean accuracy improved from 1.4 °C to 1.0 °C. Pretreatment bulk motion provided excellent precision prediction with an area under the curve of 0.80-0.86 (pelvis) and 0.81-0.83 (lower extremities), compared to gastrointestinal air motion (0.52-0.58). CONCLUSION: Single-echo MRT exhibited better precision than dual-echo MRT. Body fat-based field-drift correction significantly improved MRT accuracy. Pretreatment bulk motion showed improved prediction of acceptable MRT temporal precision over gastrointestinal air motion.

Assessment of intrafractional prostate motion and its dosimetric impact in MRI-guided online adaptive radiotherapy with gating.

PURPOSE: This study aimed to evaluate the intrafractional prostate motion captured during gated magnetic resonance imaging (MRI)-guided online adaptive radiotherapy for prostate cancer and analyze its impact on the delivered dose as well as the effect of gating. METHODS: Sagittal 2D cine-MRI scans were acquired at 4 Hz during treatment at a ViewRay MRIdian (ViewRay Inc., Oakwood Village, OH, USA) MR linac. Prostate shifts in anterior-posterior (AP) and superior-inferior (SI) directions were extracted separately. Using the static dose cloud approximation, the planned fractional dose was shifted according to the 2D gated motion (residual motion in gating window) to estimate the delivered dose by superimposing and averaging the shifted dose volumes. The dose of a hypothetical non-gated delivery was reconstructed similarly using the non-gated motion. For the clinical target volume (CTV), rectum, and bladder, dose-volume histogram parameters of the planned and reconstructed doses were compared. RESULTS: In total, 174 fractions (15.7 h of cine-MRI) from 10 patients were evaluated. The average (±1 σ) non-gated prostate motion was 0.6 ± 1.0 mm in the AP and 0.0 ± 0.6 mm in the SI direction with respect to the centroid position of the gating boundary. 95% of the shifts were within [-3.5, 2.7] mm in the AP and [-2.9, 3.2] mm in the SI direction. For the gated treatment and averaged over all fractions, CTV D98% decreased by less than 2% for all patients. The rectum and the bladder D2% increased by less than 3% and 0.5%, respectively. Doses reconstructed for gated and non-gated delivery were similar for most fractions. CONCLUSION: A pipeline for extraction of prostate motion during gated MRI-guided radiotherapy based on 2D cine-MRI was implemented. The 2D motion data enabled an approximate estimation of the delivered dose. For the majority of fractions, the benefit of gating was negligible, and clinical dosimetric constraints were met, indicating safety of the currently adopted gated MRI-guided treatment workflow.

ExacTrac Dynamic workflow evaluation: Combined surface optical/thermal imaging and X-ray positioning.

In modern radiotherapy (RT), especially for stereotactic radiotherapy or stereotactic radiosurgery treatments, image guidance is essential. Recently, the ExacTrac Dynamic (EXTD) system, a new combined surface-guided RT and image-guided RT (IGRT) system for patient positioning, monitoring, and tumor targeting, was introduced in clinical practice. The purpose of this study was to provide more information about the geometric accuracy of EXTD and its workflow in a clinical environment. The surface optical/thermal- and the stereoscopic X-ray imaging positioning systems of EXTD was evaluated and compared to cone-beam computed tomography (CBCT). Additionally, the congruence with the radiation isocenter was tested. A Winston Lutz test was executed several times over 1 year, and repeated end-to-end positioning tests were performed. The magnitude of the displacements between all systems, CBCT, stereoscopic X-ray, optical-surface imaging, and MV portal imaging was within the submillimeter range, suggesting that the image guidance provided by EXTD is accurate at any couch angle. Additionally, results from the evaluation of 14 patients with intracranial tumors treated with open-face masks are reported, and limited differences with a maximum of 0.02 mm between optical/thermal- and stereoscopic X-ray imaging were found. As the optical/thermal positioning system showed a comparable accuracy to other IGRT systems, and due to its constant monitoring capability, it can be an efficient tool for detecting intra-fractional motion and for real-time tracking of the surface position during RT.

Business exit during the COVID-19 pandemic: Non-traditional measures in historical context.

Lags in official data releases have forced economists and policymakers to leverage "alternative" or "non-traditional" data to measure business exit resulting from the COVID-19 pandemic. We first review official data on business exit in recent decades to place the alternative measures of exit within historical context. For the U.S., business exit is fairly common, with about 7.5 percent of firms exiting annually in recent years. The high level of exit is driven by very small firms and establishments. We then explore a range of alternative measures of business exit, including novel measures based on paycheck issuance and phone-tracking data, which indicate exit was elevated in certain sectors during the first year of the pandemic. That said, we find many industries have likely seen lower-than-usual exit rates, and exiting businesses do not appear to represent a large share of U.S. employment. As a result, exit appears lower than widespread expectations from early in the pandemic.

Evaluation of proton and photon dose distributions recalculated on 2D and 3D Unet-generated pseudoCTs from T1-weighted MR head scans.

Introduction: The recent developments of magnetic resonance (MR) based adaptive strategies for photon and, potentially for proton therapy, require a fast and reliable conversion of MR images to X-ray computed tomography (CT) values. CT values are needed for photon and proton dose calculation. The improvement of conversion results employing a 3D deep learning approach is evaluated. Material and methods: A database of 89 T1-weighted MR head scans with about 100 slices each, including rigidly registered CTs, was created. Twenty-eight validation patients were randomly sampled, and four patients were selected for application. The remaining patients were used to train a 2D and a 3D U-shaped convolutional neural network (Unet). A stack size of 32 slices was used for 3D training. For all application cases, volumetric modulated arc therapy photon and single-field uniform dose pencil-beam scanning proton plans at four different gantry angles were optimized for a generic target on the CT and recalculated on 2D and 3D Unet-based pseudoCTs. Mean (absolute) error (MAE/ME) and a gradient sharpness estimate were used to quantify the image quality. Three-dimensional gamma and dose difference analyses were performed for photon (gamma criteria: 1%, 1 mm) and proton dose distributions (gamma criteria: 2%, 2 mm). Range (80% fall off) differences for beam's eye view profiles were evaluated for protons. Results: Training 36 h for 1000 epochs in 3D (6 h for 200 epochs in 2D) yielded a maximum MAE of 147 HU (135 HU) for the application patients. Except for one patient gamma pass rates for photon and proton dose distributions were above 96% for both Unets. Slice discontinuities were reduced for 3D training at the cost of sharpness. Conclusions: Image analysis revealed a slight advantage of 2D Unets compared to 3D Unets. Similar dose calculation performance was reached for the 2D and 3D network.

Usability of American Sign Language Videos for Presenting Mathematics Assessment Content.

There is considerable interest in determining whether high-quality American Sign Language videos can be used as an accommodation in tests of mathematics at both K-12 and postsecondary levels; and in learning more about the usability (e.g., comprehensibility) of ASL videos with two different types of signers - avatar (animated figure) and human. The researchers describe the results of administering each of nine pre-college mathematics items in both avatar and human versions to each of 31 Deaf participants with high school and post-high school backgrounds. This study differed from earlier studies by obliging the participants to rely on the ASL videos to answer the items. While participants preferred the human version over the avatar version (apparently due largely to the better expressiveness and fluency of the human), there was no discernible relationship between mathematics performance and signed version.

Development of American Sign Language Guidelines for K-12 Academic Assessments.

The U.S. federal Every Student Succeeds Act (ESSA) was enacted with goals of closing achievement gaps and providing all students with access to equitable and high-quality instruction. One requirement of ESSA is annual statewide testing of students in grades 3-8 and once in high school. Some students, including many deaf or hard-of-hearing (D/HH) students, are eligible to use test supports, in the form of accommodations and accessibility tools, during state testing. Although technology allows accommodations and accessibility tools to be embedded within a digital assessment system, the success of this approach depends on the ability of test developers to appropriately represent content in accommodated forms. The Guidelines for Accessible Assessment Project (GAAP) sought to develop evidence- and consensus-based guidelines for representing test content in American Sign Language. In this article, we present an overview of GAAP, review of the literature, rationale, qualitative and quantitative research findings, and lessons learned.

Comparing cone-beam CT intensity correction methods for dose recalculation in adaptive intensity-modulated photon and proton therapy for head and neck cancer.

BACKGROUND: Adaptive intensity-modulated photon and proton radiotherapy (IMRT and IMPT) of head and neck (H&N) cancer requires frequent three-dimensional (3D) dose calculation. We compared two approaches for dose recalculation on the basis of intensity-corrected cone-beam (CB) x-ray computed tomography (CT) images. MATERIAL AND METHODS: For nine H&N tumor patients, virtual CTs (vCT) were generated by deformable image registration of the planning CT (pCT) to the CBCT. The second intensity correction approach used population-based lookup tables for scaling CBCT intensities to the pCT HU range (CBCTLUT). IMRT and IMPT plans were generated with a commercial treatment planning system. Dose recalculations on vCT and CBCTLUT were analyzed using a (3%, 3 mm) gamma-index analysis and comparison of normal tissue and tumor dose/volume parameters. A replanning CT (rpCT) acquired within three days of the CBCT served as reference. Single field uniform dose (SFUD) proton plans were created and recalculated on vCT and CBCTLUT for proton range comparison. RESULTS: Dose/volume parameters showed minor differences between rpCT, vCT and CBCTLUT in IMRT, but clinically relevant deviations between CBCTLUT and rpCT in the spinal cord for IMPT. Gamma-index pass-rates were found increased for vCT with respect to CBCTLUT in IMPT (by up to 21 percentage points) and IMRT (by up to 9 percentage points) for most cases. The SFUD-based proton range assessment showed improved agreement of vCT and rpCT, with 88-99% of the depth dose profiles in beam's eye view agreeing within 3 mm. For CBCTLUT, only 80-94% of the profiles fulfilled this criterion. CONCLUSION: vCT and CBCTLUT are suitable options for dose recalculation in adaptive IMRT. In the scope of IMPT, the vCT approach is preferable.

Intra-frame motion deterioration effects and deep-learning-based compensation in MR-guided radiotherapy.

BACKGROUND: Current commercially available hybrid magnetic resonance linear accelerators (MR-Linac) use 2D+t cine MR imaging to provide intra-fractional motion monitoring. However, given the limited temporal resolution of cine MR imaging, target intra-frame motion deterioration effects, resulting in effective time latency and motion artifacts in the image domain, can be appreciable, especially in the case of fast breathing. PURPOSE: The aim of this work is to investigate intra-frame motion deterioration effects in MR-guided radiotherapy (MRgRT) by simulating the motion-corrupted image acquisition, and to explore the feasibility of deep-learning-based compensation approaches, relying on the intra-frame motion information which is spatially and temporally encoded in the raw data (k-space). METHODS: An intra-frame motion model was defined to simulate motion-corrupted MR images, with 4D anthropomorphic digital phantoms being exploited to provide ground truth 2D+t cine MR sequences. A total number of 10 digital phantoms were generated for lung cancer patients, with randomly selected eight patients for training or validation and the remaining two for testing. The simulation code served as the data generator, and a dedicated motion pattern perturbation scheme was proposed to build the intra-frame motion database, where three degrees of freedom were designed to guarantee the diversity of intra-frame motion trajectories, enabling a thorough exploration in the domain of the potential anatomical structure positions. U-Nets with three types of loss functions: L1 or L2 loss defined in image or Fourier domain, referred to as NNImgLoss-L1 , NNFloss-L1 and NNL2-Loss were trained to extract information from the motion-corrupted image and used to estimate the ground truth final-position image, corresponding to the end of the acquisition. Images before and after compensation were evaluated in terms of (i) image mean-squared error (MSE) and mean absolute error (MAE), and (ii) accuracy of gross tumor volume (GTV) contouring, based on optical-flow image registration. RESULTS: Image degradation caused by intra-frame motion was observed: for a linearly and fully acquired Cartesian readout k-space trajectory, intra-frame motion resulted in an imaging latency of approximately 50% of the acquisition time; in comparison, the motion artifacts exhibited only a negligible contribution to the overall geometric errors. All three compensation models led to a decrease in image MSE/MAE and GTV position offset compared to the motion-corrupted image. In the investigated testing dataset for GTV contouring, the average dice similarity coefficients (DSC) improved from 88% to 96%, and the 95th percentile Hausdorff distance (HD95 ) dropped from 4.8 mm to 2.1 mm. Different models showed slight performance variations across different intra-frame motion amplitude categories: NNImgLoss-L1 excelled for small/medium amplitudes, whereas NNFloss-L1 demonstrated higher DSC median values at larger amplitudes. The saliency maps of the motion-corrupted image highlighted the major contribution of the later acquired k-space data, as well as the edges of the moving anatomical structures at their final positions, during the model inference stage. CONCLUSIONS: Our results demonstrate the deep-learning-based approaches have the potential to compensate for intra-frame motion by utilizing the later acquired data to drive the convergence of the earlier acquired k-space components.

Repeatability quantification of brain diffusion-weighted imaging for future clinical implementation at a low-field MR-linac.

BACKGROUND: Longitudinal assessments of apparent diffusion coefficients (ADCs) derived from diffusion-weighted imaging (DWI) during intracranial radiotherapy at magnetic resonance imaging-guided linear accelerators (MR-linacs) could enable early response assessment by tracking tumor diffusivity changes. However, DWI pulse sequences are currently unavailable in clinical practice at low-field MR-linacs. Quantifying the in vivo repeatability of ADC measurements is a crucial step towards clinical implementation of DWI sequences but has not yet been reported on for low-field MR-linacs. This study assessed ADC measurement repeatability in a phantom and in vivo at a 0.35 T MR-linac. METHODS: Eleven volunteers and a diffusion phantom were imaged on a 0.35 T MR-linac. Two echo-planar imaging DWI sequence variants, emphasizing high spatial resolution ("highRes") and signal-to-noise ratio ("highSNR"), were investigated. A test-retest study with an intermediate outside-scanner-break was performed to assess repeatability in the phantom and volunteers' brains. Mean ADCs within phantom vials, cerebrospinal fluid (CSF), and four brain tissue regions were compared to literature values. Absolute relative differences of mean ADCs in pre- and post-break scans were calculated for the diffusion phantom, and repeatability coefficients (RC) and relative RC (relRC) with 95% confidence intervals were determined for each region-of-interest (ROI) in volunteers. RESULTS: Both DWI sequence variants demonstrated high repeatability, with absolute relative deviations below 1% for water, dimethyl sulfoxide, and polyethylene glycol in the diffusion phantom. RelRCs were 7% [5%, 12%] (CSF; highRes), 12% [9%, 22%] (CSF; highSNR), 9% [8%, 12%] (brain tissue ROIs; highRes), and 6% [5%, 7%] (brain tissue ROIs; highSNR), respectively. ADCs measured with the highSNR variant were consistent with literature values for volunteers, while smaller mean values were measured for the diffusion phantom. Conversely, the highRes variant underestimated ADCs compared to literature values, indicating systematic deviations. CONCLUSIONS: High repeatability of ADC measurements in a diffusion phantom and volunteers' brains were measured at a low-field MR-linac. The highSNR variant outperformed the highRes variant in accuracy and repeatability, at the expense of an approximately doubled voxel volume. The observed high in vivo repeatability confirms the potential utility of DWI at low-field MR-linacs for early treatment response assessment.

Simultaneous object detection and segmentation for patient-specific markerless lung tumor tracking in simulated radiographs with deep learning.

BACKGROUND: Real-time tumor tracking is one motion management method to address motion-induced uncertainty. To date, fiducial markers are often required to reliably track lung tumors with X-ray imaging, which carries risks of complications and leads to prolonged treatment time. A markerless tracking approach is thus desirable. Deep learning-based approaches have shown promise for markerless tracking, but systematic evaluation and procedures to investigate applicability in individual cases are missing. Moreover, few efforts have been made to provide bounding box prediction and mask segmentation simultaneously, which could allow either rigid or deformable multi-leaf collimator tracking. PURPOSE: The purpose of this study was to implement a deep learning-based markerless lung tumor tracking model exploiting patient-specific training which outputs both a bounding box and a mask segmentation simultaneously. We also aimed to compare the two kinds of predictions and to implement a specific procedure to understand the feasibility of markerless tracking on individual cases. METHODS: We first trained a Retina U-Net baseline model on digitally reconstructed radiographs (DRRs) generated from a public dataset containing 875 CT scans and corresponding lung nodule annotations. Afterwards, we used an independent cohort of 97 lung patients to develop a patient-specific refinement procedure. In order to determine the optimal hyperparameters for automatic patient-specific training, we selected 13 patients for validation where the baseline model predicted a bounding box on planning CT (PCT)-DRR with intersection over union (IoU) with the ground-truth higher than 0.7. The final test set contained the remaining 84 patients with varying PCT-DRR IoU. For each testing patient, the baseline model was refined on the PCT-DRR to generate a patient-specific model, which was then tested on a separate 10-phase 4DCT-DRR to mimic the intrafraction motion during treatment. A template matching algorithm served as benchmark model. The testing results were evaluated by four metrics: the center of mass (COM) error and the Dice similarity coefficient (DSC) for segmentation masks, and the center of box (COB) error and the DSC for bounding box detections. Performance was compared to the benchmark model including statistical testing for significance. RESULTS: A PCT-DRR IoU value of 0.2 was shown to be the threshold dividing inconsistent (68%) and consistent (100%) success (defined as mean bounding box DSC > 0.6) of PS models on 4DCT-DRRs. Thirty-seven out of the eighty-four testing cases had a PCT-DRR IoU above 0.2. For these 37 cases, the mean COM error was 2.6 mm, the mean segmentation DSC was 0.78, the mean COB error was 2.7 mm, and the mean box DSC was 0.83. Including the validation cases, the model was applicable to 50 out of 97 patients when using the PCT-DRR IoU threshold of 0.2. The inference time per frame was 170 ms. The model outperformed the benchmark model on all metrics, and the comparison was significant (p < 0.001) over the 37 PCT-DRR IoU > 0.2 cases, but not over the undifferentiated 84 testing cases. CONCLUSIONS: The implemented patient-specific refinement approach based on a pre-trained baseline model was shown to be applicable to markerless tumor tracking in simulated radiographs for lung cases.

Proton dose calculation with LSTM networks in presence of a magnetic field.

OBJECTIVE: To present a long short-term memory (LSTM) network-based dose calculation method for magnetic resonance (MR)-guided proton therapy. APPROACH: 35 planning computed tomography (CT) images of prostate cancer patients were collected for Monte Carlo (MC) dose calculation under a perpendicular 1.5 T magnetic field. Proton pencil beams (PB) at three energies (150, 175, and 200 MeV) were simulated (7560 PBs at each energy). A 3D relative stopping power (RSP) cuboid covering the extent of the PB dose was extracted and given as input to the LSTM model, yielding a 3D predicted PB dose. Three single-energy (SE) LSTM models were trained separately on the corresponding 150/175/200 MeV datasets and a multi-energy (ME) LSTM model with an energy embedding layer was trained on either the combined dataset with three energies or a continuous energy (CE) dataset with 1 MeV steps ranging from 125 to 200 MeV. For each model, training and validation involved 25 patients and 10 patients were for testing. Two single field uniform dose prostate treatment plans were optimized and recalculated with MC and the CE model. RESULTS: Test results of all PBs from the three SE models showed a mean gamma passing rate (2%/2mm, 10% dose cutoff) above 99.9% with an average center-of-mass (COM) discrepancy below 0.4 mm between predicted and simulated trajectories. The ME model showed a mean gamma passing rate exceeding 99.8% and a COM discrepancy of less than 0.5 mm at the three energies. Treatment plan recalculation by the CE model yielded gamma passing rates of 99.6% and 97.9%. The inference time of the models was 9-10 ms per PB. SIGNIFICANCE: LSTM models for proton dose calculation in a magnetic field were developed and showed promising accuracy and efficiency for prostate cancer patients.

MRI-based ventilation and perfusion imaging to predict radiation-induced pneumonitis in lung tumor patients at a 0.35T MR-Linac.

BACKGROUND AND PURPOSE: Radiation-induced pneumonitis (RP), diagnosed 6-12 weeks after treatment, is a complication of lung tumor radiotherapy. So far, clinical and dosimetric parameters have not been reliable in predicting RP. We propose using non-contrast enhanced magnetic resonance imaging (MRI) based functional parameters acquired over the treatment course for patient stratification for improved follow-up. MATERIALS AND METHODS: 23 lung tumor patients received MR-guided hypofractionated stereotactic body radiation therapy at a 0.35T MR-Linac. Ventilation- and perfusion-maps were generated from 2D-cine MRI-scans acquired after the first and last treatment fraction (Fx) using non-uniform Fourier decomposition. The relative differences in ventilation and perfusion between last and first Fx in three regions (planning target volume (PTV), lung volume receiving more than 20Gy (V20) excluding PTV, whole tumor-bearing lung excluding PTV) and three dosimetric parameters (mean lung dose, V20, mean dose to the gross tumor volume) were investigated. Univariate receiver operating characteristic curve - area under the curve (ROC-AUC) analysis was performed (endpoint RP grade≥1) using 5000 bootstrapping samples. Differences between RP and non-RP patients were tested for statistical significance with the non-parametric Mann-Whitney U test (α=0.05). RESULTS: 14/23 patients developed RP of grade≥1 within 3 months. The dosimetric parameters showed no significant differences between RP and non-RP patients. In contrast, the functional parameters, especially the relative ventilation difference in the PTV, achieved a p-value<0.05 and an AUC value of 0.84. CONCLUSION: MRI-based functional parameters extracted from 2D-cine MRI-scans were found to be predictive of RP development in lung tumor patients.

Comparison of deep learning networks for fully automated head and neck tumor delineation on multi-centric PET/CT images.

OBJECTIVES: Deep learning-based auto-segmentation of head and neck cancer (HNC) tumors is expected to have better reproducibility than manual delineation. Positron emission tomography (PET) and computed tomography (CT) are commonly used in tumor segmentation. However, current methods still face challenges in handling whole-body scans where a manual selection of a bounding box may be required. Moreover, different institutions might still apply different guidelines for tumor delineation. This study aimed at exploring the auto-localization and segmentation of HNC tumors from entire PET/CT scans and investigating the transferability of trained baseline models to external real world cohorts. METHODS: We employed 2D Retina Unet to find HNC tumors from whole-body PET/CT and utilized a regular Unet to segment the union of the tumor and involved lymph nodes. In comparison, 2D/3D Retina Unets were also implemented to localize and segment the same target in an end-to-end manner. The segmentation performance was evaluated via Dice similarity coefficient (DSC) and Hausdorff distance 95th percentile (HD95). Delineated PET/CT scans from the HECKTOR challenge were used to train the baseline models by 5-fold cross-validation. Another 271 delineated PET/CTs from three different institutions (MAASTRO, CRO, BERLIN) were used for external testing. Finally, facility-specific transfer learning was applied to investigate the improvement of segmentation performance against baseline models. RESULTS: Encouraging localization results were observed, achieving a maximum omnidirectional tumor center difference lower than 6.8 cm for external testing. The three baseline models yielded similar averaged cross-validation (CV) results with a DSC in a range of 0.71-0.75, while the averaged CV HD95 was 8.6, 10.7 and 9.8 mm for the regular Unet, 2D and 3D Retina Unets, respectively. More than a 10% drop in DSC and a 40% increase in HD95 were observed if the baseline models were tested on the three external cohorts directly. After the facility-specific training, an improvement in external testing was observed for all models. The regular Unet had the best DSC (0.70) for the MAASTRO cohort, and the best HD95 (7.8 and 7.9 mm) in the MAASTRO and CRO cohorts. The 2D Retina Unet had the best DSC (0.76 and 0.67) for the CRO and BERLIN cohorts, and the best HD95 (12.4 mm) for the BERLIN cohort. CONCLUSION: The regular Unet outperformed the other two baseline models in CV and most external testing cohorts. Facility-specific transfer learning can potentially improve HNC segmentation performance for individual institutions, where the 2D Retina Unets could achieve comparable or even better results than the regular Unet.

Impact of daily plan adaptation on accumulated doses in ultra-hypofractionated magnetic resonance-guided radiation therapy of prostate cancer.

Background and purpose: Ultra-hypofractionated online adaptive magnetic resonance-guided radiotherapy (MRgRT) is promising for prostate cancer. However, the impact of online adaptation on target coverage and organ-at-risk (OAR) sparing at the level of accumulated dose has not yet been reported. Using deformable image registration (DIR)-based accumulation, we compared the delivered adapted dose with the simulated non-adapted dose. Materials and methods: Twenty-three prostate cancer patients treated at two clinics with 0.35 T magnetic resonance-guided linear accelerator (MR-linac) following the same treatment protocol (5 × 7.5 Gy with urethral sparing and daily adaptation) were included. The fraction MR images were deformably registered to the planning MR image. Both non-adapted and adapted fraction doses were accumulated with the corresponding vector fields. Two DIR approaches were implemented. PTV* (planning target volume minus urethra+2mm) D95%, CTV* (clinical target volume minus urethra) D98%, and OARs (urethra+2mm, bladder, and rectum) D0.2cc, were evaluated. Statistical significance was inferred from a two-tailed Wilcoxon signed-rank test (p < 0.05). Results: Normalized to the baseline, the accumulated PTV* D95% increased significantly by 2.7 % ([1.5, 4.3]%) through adaptation, and the CTV* D98% by 1.2 % ([0.1, 1.7]%). For the OARs after adaptation, accumulated bladder D0.2cc decreased by 0.4 % ([-1.2, 0.4]%), urethra+2mmD0.2cc by 0.8 % ([-1.6, -0.1]%), while rectum D0.2cc increased by 2.6 % ([1.2, 4.9]%). For all patients, rectum D0.2cc was still below the clinical constraint. Results of both DIR approaches differed on average by less than 0.2 %. Conclusions: Online adaptation in MRgRT improved target coverage and OARs sparing at the level of accumulated dose.

Reduction of cone-beam CT artifacts in a robotic CBCT device using saddle trajectories with integrated infrared tracking.

BACKGROUND: Cone beam computed tomography (CBCT) is widely used in many medical fields. However, conventional CBCT circular scans suffer from cone beam (CB) artifacts that limit the quality and reliability of the reconstructed images due to incomplete data. PURPOSE: Saddle trajectories in theory might be able to improve the CBCT image quality by providing a larger region with complete data. Therefore, we investigated the feasibility and performance of saddle trajectory CBCT scans and compared them to circular trajectory scans. METHODS: We performed circular and saddle trajectory scans using a novel robotic CBCT scanner (Mobile ImagingRing (IRm); medPhoton, Salzburg, Austria). For the saddle trajectory, the gantry executed yaw motion up to ± 10 ∘ $\pm 10^{\circ }$ using motorized wheels driving on the floor. An infrared (IR) tracking device with reflective markers was used for online geometric calibration correction (mainly floor unevenness). All images were reconstructed using penalized least-squares minimization with the conjugate gradient algorithm from RTK with 0.5 × 0.5 × 0.5 mm 3 $0.5 \times 0.5\times 0.5 \text{ mm}^3$ voxel size. A disk phantom and an Alderson phantom were scanned to assess the image quality. Results were correlated with the local incompleteness value represented by tan ( ψ ) $\tan (\psi)$ , which was calculated at each voxel as a function of the source trajectory and the voxel's 3D coordinates. We assessed the magnitude of CB artifacts using the full width half maximum (FWHM) of each disk profile in the axial center of the reconstructed images. Spatial resolution was also quantified by the modulation transfer function at 10% (MTF10). RESULTS: When using the saddle trajectory, the region without CB artifacts was increased from 43 to 190 mm in the SI direction compared to the circular trajectory. This region coincided with low values for tan ( ψ ) $\tan (\psi)$ . When tan ( ψ ) $\tan (\psi)$ was larger than 0.02, we found there was a linear relationship between the FWHM and tan ( ψ ) $\tan (\psi)$ . For the saddle, IR tracking allowed the increase of MTF10 from 0.37 to 0.98 lp/mm. CONCLUSIONS: We achieved saddle trajectory CBCT scans with a novel CBCT system combined with IR tracking. The results show that the saddle trajectory provides a larger region with reliable reconstruction compared to the circular trajectory. The proposed method can be used to evaluate other non-circular trajectories.

Real-time motion management in MRI-guided radiotherapy: Current status and AI-enabled prospects.

MRI-guided radiotherapy (MRIgRT) is a highly complex treatment modality, allowing adaptation to anatomical changes occurring from one treatment day to the other (inter-fractional), but also to motion occurring during a treatment fraction (intra-fractional). In this vision paper, we describe the different steps of intra-fractional motion management during MRIgRT, from imaging to beam adaptation, and the solutions currently available both clinically and at a research level. Furthermore, considering the latest developments in the literature, a workflow is foreseen in which motion-induced over- and/or under-dosage is compensated in 3D, with minimal impact to the radiotherapy treatment time. Considering the time constraints of real-time adaptation, a particular focus is put on artificial intelligence (AI) solutions as a fast and accurate alternative to conventional algorithms.

Impact of bias field correction on 0.35 T pelvic MR images: evaluation on generative adversarial network-based OARs' auto-segmentation and visual grading assessment.

Purpose: Magnetic resonance imaging (MRI)-guided radiotherapy enables adaptive treatment plans based on daily anatomical changes and accurate organ visualization. However, the bias field artifact can compromise image quality, affecting diagnostic accuracy and quantitative analyses. This study aims to assess the impact of bias field correction on 0.35 T pelvis MRIs by evaluating clinical anatomy visualization and generative adversarial network (GAN) auto-segmentation performance. Materials and methods: 3D simulation MRIs from 60 prostate cancer patients treated on MR-Linac (0.35 T) were collected and preprocessed with the N4ITK algorithm for bias field correction. A 3D GAN architecture was trained, validated, and tested on 40, 10, and 10 patients, respectively, to auto-segment the organs at risk (OARs) rectum and bladder. The GAN was trained and evaluated either with the original or the bias-corrected MRIs. The Dice similarity coefficient (DSC) and 95th percentile Hausdorff distance (HD95th) were computed for the segmented volumes of each patient. The Wilcoxon signed-rank test assessed the statistical difference of the metrics within OARs, both with and without bias field correction. Five radiation oncologists blindly scored 22 randomly chosen patients in terms of overall image quality and visibility of boundaries (prostate, rectum, bladder, seminal vesicles) of the original and bias-corrected MRIs. Bennett's S score and Fleiss' kappa were used to assess the pairwise interrater agreement and the interrater agreement among all the observers, respectively. Results: In the test set, the GAN trained and evaluated on original and bias-corrected MRIs showed DSC/HD95th of 0.92/5.63 mm and 0.92/5.91 mm for the bladder and 0.84/10.61 mm and 0.83/9.71 mm for the rectum. No statistical differences in the distribution of the evaluation metrics were found neither for the bladder (DSC: p = 0.07; HD95th: p = 0.35) nor for the rectum (DSC: p = 0.32; HD95th: p = 0.63). From the clinical visual grading assessment, the bias-corrected MRI resulted mostly in either no change or an improvement of the image quality and visualization of the organs' boundaries compared with the original MRI. Conclusion: The bias field correction did not improve the anatomy visualization from a clinical point of view and the OARs' auto-segmentation outputs generated by the GAN.

Auto-segmentation of pelvic organs at risk on 0.35T MRI using 2D and 3D Generative Adversarial Network models.

PURPOSE: Manual recontouring of targets and Organs At Risk (OARs) is a time-consuming and operator-dependent task. We explored the potential of Generative Adversarial Networks (GAN) to auto-segment the rectum, bladder and femoral heads on 0.35T MRIs to accelerate the online MRI-guided-Radiotherapy (MRIgRT) workflow. METHODS: 3D planning MRIs from 60 prostate cancer patients treated with 0.35T MR-Linac were collected. A 3D GAN architecture and its equivalent 2D version were trained, validated and tested on 40, 10 and 10 patients respectively. The volumetric Dice Similarity Coefficient (DSC) and 95th percentile Hausdorff Distance (HD95th) were computed against expert drawn ground-truth delineations. The networks were also validated on an independent external dataset of 16 patients. RESULTS: In the internal test set, the 3D and 2D GANs showed DSC/HD95th of 0.83/9.72 mm and 0.81/10.65 mm for the rectum, 0.92/5.91 mm and 0.85/15.72 mm for the bladder, and 0.94/3.62 mm and 0.90/9.49 mm for the femoral heads. In the external test set, the performance was 0.74/31.13 mm and 0.72/25.07 mm for the rectum, 0.92/9.46 mm and 0.88/11.28 mm for the bladder, and 0.89/7.00 mm and 0.88/10.06 mm for the femoral heads. The 3D and 2D GANs required on average 1.44 s and 6.59 s respectively to generate the OARs' volumetric segmentation for a single patient. CONCLUSIONS: The proposed 3D GAN auto-segments pelvic OARs with high accuracy on 0.35T, in both the internal and the external test sets, outperforming its 2D equivalent in both segmentation robustness and volume generation time.