Intrafractional motion detection for spine SBRT via X-ray imaging using ExacTrac Dynamic

Purpose

Due to its close vicinity to critical structures, especially the spinal cord, standards for safety for spine stereotactic body radiotherapy (SBRT) should be high. This study was conducted, to evaluate intrafractional motion during spine SBRT for patients without individualized immobilization (e.g., vacuum cushions) using high accuracy patient monitoring via orthogonal X-ray imaging.

Methods

Intrafractional X-ray data were collected from 29 patients receiving 79 fractions of spine SBRT. No individualized immobilization devices were used during the treatment. Intrafractional motion was monitored using the ExacTrac Dynamic (ETD) System (Brainlab AG, Munich, Germany). Deviations were detected in six degrees of freedom (6 DOF). Tolerances for repositioning were 0.7 mm for translational and 0.5° for rotational deviations. Patients were repositioned when the tolerance levels were exceeded.

Results

Out of the 925 pairs of stereoscopic X-ray images examined, 138 (15 %) showed at least one deviation exceeding the predefined tolerance values. In all 6 DOF together, a total of 191 deviations out of tolerance were recorded. The frequency of deviations exceeding the tolerance levels varied among patients but occurred in all but one patient. Deviations out of tolerance could be seen in all 6 DOF. Maximum translational deviations were 2.6 mm, 2.3 mm and 2.8 mm in the lateral, longitudinal and vertical direction. Maximum rotational deviations were 1.8°, 2.6° and 1.6° for pitch, roll and yaw, respectively. Translational deviations were more frequent than rotational ones, and frequency and magnitude of deviations showed an inverse correlation.

Conclusion

Intrafractional motion detection and patient repositioning during spine SBRT using X-ray imaging via the ETD System can lead to improved safety during the application of high BED in critical locations. When using intrafractional imaging with low thresholds for re-positioning individualized immobilization devices (e.g. vacuum cushions) may be omitted.

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.

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.

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 with0.5 × 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 bytan ( 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 fortan ( ψ ) $\tan (\psi)$ . Whentan ( ψ ) $\tan (\psi)$ was larger than 0.02, we found there was a linear relationship between the FWHM andtan ( 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.

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.

The role of online MR-guided multi-fraction stereotactic ablative radiotherapy in lung tumours

Background

The aim of this prospective observational study was to evaluate the dosimetry benefits, changes in pulmonary function, and clinical outcome of online adaptive MR-guided SBRT.

Methods

From 11/2020-07/2022, 45 consecutive patients with 59 lesions underwent multi-fraction SBRT (3-8 fractions) at our institution. Patients were eligible if they had biopsy-proven NSCLC or lung cancer/metastases diagnosed via clinical imaging. Endpoints were local control (LC) and overall survival (OS). We evaluated PTV/GTV dose coverage, organs at risk exposure, and changes in pulmonary function (PF). Acute toxicity was classified per the National Cancer Institute-Common Terminology Criteria for Adverse Events version 5.0.

Results

The median PTV was 14.4 cm3 (range: 3.4 - 96.5 cm3). In total 195/215 (91%) plans were reoptimised. In the reoptimised vs. predicted plans, PTV coverage by the prescribed dose increased in 94.6% of all fractions with a median increase in PTV VPD of 5.6% (range: -1.8 - 44.6%, p < 0.001), increasing the number of fractions with PTV VPD ≥ 95% from 33% to 98%. The PTV D95% and D98% (BED10) increased in 93% and 95% of all fractions with a median increase of 7.7% (p < 0.001) and 10.6% (p < 0.001). The PTV D95% (BED10) increased by a mean of 9.6 Gy (SD: 10.3 Gy, p < 0.001). At a median follow-up of 21.4 months (95% CI: 12.3-27.0 months), 1- and 2-year LC rates were 94.8% (95% CI: 87.6 - 100.0%) and 91.1% (95% CI: 81.3 - 100%); 1- and 2-year OS rates were 85.6% (95% CI: 75.0 - 96.3%) and 67.1 % (95% CI: 50.3 - 83.8%). One grade ≥ 3 toxicity and no significant reduction in short-term PF parameters were recorded.

Conclusions

Online adaptive MR-guided SBRT is an effective, safe and generally well tolerated treatment option for lung tumours achieving encouraging local control rates with significantly improved target volume coverage.

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.

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.

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.

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.

Continuous time-resolved estimated synthetic 4D-CTs for dose reconstruction of lung tumor treatments at a 0.35 T MR-linac

Objective.To experimentally validate a method to create continuous time-resolved estimated synthetic 4D-computed tomography datasets (tresCTs) based on orthogonal cine MRI data for lung cancer treatments at a magnetic resonance imaging (MRI) guided linear accelerator (MR-linac).Approach.A breathing porcine lung phantom was scanned at a CT scanner and 0.35 T MR-linac. Orthogonal cine MRI series (sagittal/coronal orientation) at 7.3 Hz, intersecting tumor-mimicking gelatin nodules, were deformably registered to mid-exhale 3D-CT and 3D-MRI datasets. The time-resolved deformation vector fields were extrapolated to 3D and applied to a reference synthetic 3D-CT image (sCTref), while accounting for breathing phase-dependent lung density variations, to create 82 s long tresCTs at 3.65 Hz. Ten tresCTs were created for ten tracked nodules with different motion patterns in two lungs. For each dataset, a treatment plan was created on the mid-exhale phase of a measured ground truth (GT) respiratory-correlated 4D-CT dataset with the tracked nodule as gross tumor volume (GTV). Each plan was recalculated on the GT 4D-CT, randomly sampled tresCT, and static sCTrefimages. Dose distributions for corresponding breathing phases were compared in gamma (2%/2 mm) and dose-volume histogram (DVH) parameter analyses.Main results.The mean gamma pass rate between all tresCT and GT 4D-CT dose distributions was 98.6%. The mean absolute relative deviations of the tresCT with respect to GT DVH parameters were 1.9%, 1.0%, and 1.4% for the GTVD98%,D50%, andD2%, respectively, 1.0% for the remaining nodulesD50%, and 1.5% for the lungV20Gy. The gamma pass rate for the tresCTs was significantly larger (p< 0.01), and the GTVD50%deviations with respect to the GT were significantly smaller (p< 0.01) than for the sCTref.Significance.The results suggest that tresCTs could be valuable for time-resolved reconstruction and intrafractional accumulation of the dose to the GTV for lung cancer patients treated at MR-linacs in the future.

Experimental comparison of linear regression and LSTM motion prediction models for MLC-tracking on an MRI-linac

BACKGROUND

Magnetic resonance imaging (MRI)-guided radiotherapy with multileaf collimator (MLC)-tracking is a promising technique for intra-fractional motion management, achieving high dose conformality without prolonging treatment times. To improve beam-target alignment, the geometric error due to system latency should be reduced by using temporal prediction.

PURPOSE

To experimentally compare linear regression (LR) and long-short-term memory (LSTM) motion prediction models for MLC-tracking on an MRI-linac using multiple patient-derived traces with different complexities.

METHODS

Experiments were performed on a prototype 1.0 T MRI-linac capable of MLC-tracking. A motion phantom was programmed to move a target in superior-inferior (SI) direction according to eight lung cancer patient respiratory motion traces. Target centroid positions were localized from sagittal 2D cine MRIs acquired at 4 Hz using a template matching algorithm. The centroid positions were input to one of four motion prediction models. We used (1) a LSTM network which had been optimized in a previous study on patient data from another cohort (offline LSTM). We also used (2) the same LSTM model as a starting point for continuous re-optimization of its weights during the experiment based on recent motion (offline+online LSTM). Furthermore, we implemented (3) a continuously updated LR model, which was solely based on recent motion (online LR). Finally, we used (4) the last available target centroid without any changes as a baseline (no-predictor). The predictions of the models were used to shift the MLC aperture in real-time. An electronic portal imaging device (EPID) was used to visualize the target and MLC aperture during the experiments. Based on the EPID frames, the root-mean-square error (RMSE) between the target and the MLC aperture positions was used to assess the performance of the different motion predictors. Each combination of motion trace and prediction model was repeated twice to test stability, for a total of 64 experiments.

RESULTS

The end-to-end latency of the system was measured to be (389 ± 15) ms and was successfully mitigated by both LR and LSTM models. The offline+online LSTM was found to outperform the other models for all investigated motion traces. It obtained a median RMSE over all traces of (2.8 ± 1.3) mm, compared to the (3.2 ± 1.9) mm of the offline LSTM, the (3.3 ± 1.4) mm of the online LR and the (4.4 ± 2.4) mm when using the no-predictor. According to statistical tests, differences were significant (p-value <0.05) among all models in a pair-wise comparison, but for the offline LSTM and online LR pair. The offline+online LSTM was found to be more reproducible than the offline LSTM and the online LR with a maximum deviation in RMSE between two measurements of 10%.

CONCLUSIONS

This study represents the first experimental comparison of different prediction models for MRI-guided MLC-tracking using several patient-derived respiratory motion traces. We have shown that among the investigated models, continuously re-optimized LSTM networks are the most promising to account for the end-to-end system latency in MRI-guided radiotherapy with MLC-tracking.

The role of artificial intelligence in radiotherapy clinical practice

This review article visits the current state of artificial intelligence (AI) in radiotherapy clinical practice. We will discuss how AI has a place in the modern radiotherapy workflow at the level of automatic segmentation and planning, two applications which have seen real-work implementation. A special emphasis will be placed on the role AI can play in online adaptive radiotherapy, such as performed at MR-linacs, where online plan adaptation is a procedure which could benefit from automation to reduce on-couch time for patients. Pseudo-CT generation and AI for motion tracking will be introduced in the scope of online adaptive radiotherapy as well. We further discuss the use of AI for decision-making and response assessment, for example for personalized prescription and treatment selection, risk stratification for outcomes and toxicities, and AI for quantitative imaging and response assessment. Finally, the challenges of generalizability and ethical aspects will be covered. With this, we provide a comprehensive overview of the current and future applications of AI in radiotherapy.

Prior knowledge based deep learning auto-segmentation in magnetic resonance imaging-guided radiotherapy of prostate cancer

Background and purpose

Automation is desirable for organ segmentation in radiotherapy. This study compared deep learning methods for auto-segmentation of organs-at-risk (OARs) and clinical target volume (CTV) in prostate cancer patients undergoing fractionated magnetic resonance (MR)-guided adaptive radiation therapy. Models predicting dense displacement fields (DDFMs) between planning and fraction images were compared to patient-specific (PSM) and baseline (BM) segmentation models.

Materials and methods

A dataset of 92 patients with planning and fraction MR images (MRIs) from two institutions were used. DDFMs were trained to predict dense displacement fields (DDFs) between the planning and fraction images, which were subsequently used to propagate the planning contours of the bladder, rectum, and CTV to the daily MRI. The training was performed either with true planning-fraction image pairs or with planning images and their counterparts deformed by known DDFs. The BMs were trained on 53 planning images, while to generate PSMs, the BMs were fine-tuned using the planning image of a given single patient. The evaluation included Dice similarity coefficient (DSC), the average (HDavg) and the 95th percentile (HD95) Hausdorff distance (HD).

Results

The DDFMs with DSCs for bladder/rectum of 0.76/0.76 performed worse than PSMs (0.91/0.90) and BMs (0.89/0.88). The same trend was observed for HDs. For CTV, DDFM and PSM performed similarly yielding DSCs of 0.87 and 0.84, respectively.

Conclusions

DDFMs were found suitable for CTV delineation after rigid alignment. However, for OARs they were outperformed by PSMs, as they predicted only limited deformations even in the presence of substantial anatomical changes.

Validation of an MR-based multimodal method for molecular composition and proton stopping power ratio determination using ex vivo animal tissues and tissue-mimicking phantoms

Objective. Range uncertainty in proton therapy is an important factor limiting clinical effectiveness. Magnetic resonance imaging (MRI) can measure voxel-wise molecular composition and, when combined with kilovoltage CT (kVCT), accurately determine mean ionization potential (Im), electron density, and stopping power ratio (SPR). We aimed to develop a novel MR-based multimodal method to accurately determine SPR and molecular compositions. This method was evaluated in tissue-mimicking andex vivoporcine phantoms, and in a brain radiotherapy patient.Approach. Four tissue-mimicking phantoms with known compositions, two porcine tissue phantoms, and a brain cancer patient were imaged with kVCT and MRI. Three imaging-based values were determined: SPRCM(CT-based Multimodal), SPRMM(MR-based Multimodal), and SPRstoich(stoichiometric calibration). MRI was used to determine two tissue-specific quantities of the Bethe Bloch equation (Im, electron density) to compute SPRCMand SPRMM. Imaging-based SPRs were compared to measurements for phantoms in a proton beam using a multilayer ionization chamber (SPRMLIC).Main results. Root mean square errors relative to SPRMLICwere 0.0104(0.86%), 0.0046(0.45%), and 0.0142(1.31%) for SPRCM, SPRMM, and SPRstoich, respectively. The largest errors were in bony phantoms, while soft tissue and porcine tissue phantoms had <1% errors across all SPR values. Relative to known physical molecular compositions, imaging-determined compositions differed by approximately ≤10%. In the brain case, the largest differences between SPRstoichand SPRMMwere in bone and high lipids/fat tissue. The magnitudes and trends of these differences matched phantom results.Significance. Our MR-based multimodal method determined molecular compositions and SPR in various tissue-mimicking phantoms with high accuracy, as confirmed with proton beam measurements. This method also revealed significant SPR differences compared to stoichiometric kVCT-only calculation in a clinical case, with the largest differences in bone. These findings support that including MRI in proton therapy treatment planning can improve the accuracy of calculated SPR values and reduce range uncertainties.

Planning CT Identifies Patients at Risk of High Prostate Intrafraction Motion

Prostate motion (standard deviation, range of motion, and diffusion coefficient) was calculated from 4D ultrasound data of 1791 fractions of radiation therapy in N = 100 patients. The inner diameter of the lesser pelvis was obtained from transversal slices through the pubic symphysis in planning CTs. On the lateral and craniocaudal axes, motility increases significantly (t-test, p < 0.005) with the inner diameter of the lesser pelvis. A diameter of >106 mm (ca. 6th decile) is a good predictor for high prostate intrafraction motion (ca. 9th decile). The corresponding area under the receiver operator curve (AUROC) is 80% in the lateral direction, 68% to 80% in the craniocaudal direction, and 62% to 70% in the vertical direction. On the lateral x-axis, the proposed test is 100% sensitive and has a 100% negative predictive value for all three characteristics (standard deviation, range of motion, and diffusion coefficient). On the craniocaudal z-axis, the proposed test is 79% to 100% sensitive and reaches 95% to 100% negative predictive value. On the vertical axis, the proposed test still delivers 98% negative predictive value but is not particularly sensitive. Overall, the proposed predictor is able to help identify patients at risk of high prostate motion based on a single planning CT.

Deep learning based automatic segmentation of organs-at-risk for 0.35 T MRgRT of lung tumors

BACKGROUND AND PURPOSE

Magnetic resonance imaging guided radiotherapy (MRgRT) offers treatment plan adaptation to the anatomy of the day. In the current MRgRT workflow, this requires the time consuming and repetitive task of manual delineation of organs-at-risk (OARs), which is also prone to inter- and intra-observer variability. Therefore, deep learning autosegmentation (DLAS) is becoming increasingly attractive. No investigation of its application to OARs in thoracic magnetic resonance images (MRIs) from MRgRT has been done so far. This study aimed to fill this gap.

MATERIALS AND METHODS

122 planning MRIs from patients treated at a 0.35 T MR-Linac were retrospectively collected. Using an 80/19/23 (training/validation/test) split, individual 3D U-Nets for segmentation of the left lung, right lung, heart, aorta, spinal canal and esophagus were trained. These were compared to the clinically used contours based on Dice similarity coefficient (DSC) and Hausdorff distance (HD). They were also graded on their clinical usability by a radiation oncologist.

RESULTS

Median DSC was 0.96, 0.96, 0.94, 0.90, 0.88 and 0.78 for left lung, right lung, heart, aorta, spinal canal and esophagus, respectively. Median 95th percentile values of the HD were 3.9, 5.3, 5.8, 3.0, 2.6 and 3.5 mm, respectively. The physician preferred the network generated contours over the clinical contours, deeming 85 out of 129 to not require any correction, 25 immediately usable for treatment planning, 15 requiring minor and 4 requiring major corrections.

CONCLUSIONS

We trained 3D U-Nets on clinical MRI planning data which produced accurate delineations in the thoracic region. DLAS contours were preferred over the clinical contours.

Scatter correction of 4D cone beam computed tomography to detect dosimetric effects due to anatomical changes in proton therapy for lung cancer

BACKGROUND

The treatment of moving tumor entities is expected to have superior clinical outcomes, using image-guided adaptive intensity-modulated proton therapy (IMPT).

PURPOSE

For 21 lung cancer patients, IMPT dose calculations were performed on scatter-corrected 4D cone beam CTs (4DCBCTcor ) to evaluate their potential for triggering treatment adaptation. Additional dose calculations were performed on corresponding planning 4DCTs and day-of-treatment 4D virtual CTs (4DvCTs).

METHODS

A 4DCBCT correction workflow, previously validated on a phantom, generates 4DvCT (CT-to-CBCT deformable registration) and 4DCBCTcor images (projection-based correction using 4DvCT as a prior) with 10 phase bins, using day-of-treatment free-breathing CBCT projections and planning 4DCT images as input. Using a research planning system, robust IMPT plans administering eight fractions of 7.5 Gy were created on a free-breathing planning CT (pCT) contoured by a physician. The internal target volume (ITV) was overridden with muscle tissue. Robustness settings for range and setup uncertainties were 3% and 6 mm, and a Monte Carlo dose engine was used. On every phase of planning 4DCT, day-of-treatment 4DvCT, and 4DCBCTcor , the dose was recalculated. For evaluation, image analysis as well as dose analysis were performed using mean error (ME) and mean absolute error (MAE) analysis, dose-volume histogram (DVH) parameters, and 2%/2-mm gamma pass rate analysis. Action levels (1.6% ITV D98 and 90% gamma pass rate) based on our previous phantom validation study were set to determine which patients had a loss of dosimetric coverage.

RESULTS

Quality enhancements of 4DvCT and 4DCBCTcor over 4DCBCT were observed. ITV D98% and bronchi D2% had its largest agreement for 4DCBCTcor -4DvCT, and the largest gamma pass rates (>94%, median 98%) were found for 4DCBCTcor -4DvCT. Deviations were larger and gamma pass rates were smaller for 4DvCT-4DCT and 4DCBCTcor -4DCT. For five patients, deviations were larger than the action levels, suggesting substantial anatomical changes between pCT and CBCT projections acquisition.

CONCLUSIONS

This retrospective study shows the feasibility of daily proton dose calculation on 4DCBCTcor for lung tumor patients. The applied method is of clinical interest as it generates up-to-date in-room images, accounting for breathing motion and anatomical changes. This information could be used to trigger replanning.

ScatterNet for projection-based 4D cone-beam computed tomography intensity correction of lung cancer patients

Background and purpose: In radiotherapy, dose calculations based on 4D cone beam CTs (4DCBCTs) require image intensity corrections. This retrospective study compared the dose calculation accuracy of a deep learning, projection-based scatter correction workflow (ScatterNet), to slower workflows: conventional 4D projection-based scatter correction (CBCTcor) and a deformable image registration (DIR)-based method (4DvCT). Materials and methods: For 26 lung cancer patients, planning CTs (pCTs), 4DCTs and CBCT projections were available. ScatterNet was trained with pairs of raw and corrected CBCT projections. Corrected projections from ScatterNet and the conventional workflow were reconstructed using MA-ROOSTER, yielding 4DCBCTSN and 4DCBCTcor. The 4DvCT was generated by 4DCT to 4DCBCT DIR, as part of the 4DCBCTcor workflow. Robust intensity modulated proton therapy treatment plans were created on free-breathing pCTs. 4DCBCTSN was compared to 4DCBCTcor and the 4DvCT in terms of image quality and dose calculation accuracy (dose-volume-histogram parameters and 3 % /3 mm gamma analysis). Results: 4DCBCTSN resulted in an average mean absolute error of 87 HU and 102 HU when compared to 4DCBCTcor and 4DvCT respectively. High agreement was observed in targets with median dose differences of 0.4 Gy (4DCBCTSN-4DCBCTcor) and 0.3 Gy (4DCBCTSN-4DvCT). The gamma analysis showed high average 3 % /3 mm pass rates of 96 % for both 4DCBCTSN vs. 4DCBCTcor and 4DCBCTSN vs. 4DvCT. Conclusions: Accurate 4D dose calculations are feasible for lung cancer patients using ScatterNet for 4DCBCT correction. Average scatter correction times could be reduced from 10 min (4DCBCTcor) to 3.9 s , showing the clinical suitability of the proposed deep learning-based method.

A convolutional neural network with self-attention for fully automated metabolic tumor volume delineation of head and neck cancer in [Formula: see text]F]FDG PET/CT

PURPOSE

PET-derived metabolic tumor volume (MTV) and total lesion glycolysis of the primary tumor are known to be prognostic of clinical outcome in head and neck cancer (HNC). Including evaluation of lymph node metastases can further increase the prognostic value of PET but accurate manual delineation and classification of all lesions is time-consuming and prone to interobserver variability. Our goal, therefore, was development and evaluation of an automated tool for MTV delineation/classification of primary tumor and lymph node metastases in PET/CT investigations of HNC patients.

METHODS

Automated lesion delineation was performed with a residual 3D U-Net convolutional neural network (CNN) incorporating a multi-head self-attention block. 698 [Formula: see text]F]FDG PET/CT scans from 3 different sites and 5 public databases were used for network training and testing. An external dataset of 181 [Formula: see text]F]FDG PET/CT scans from 2 additional sites was employed to assess the generalizability of the network. In these data, primary tumor and lymph node (LN) metastases were interactively delineated and labeled by two experienced physicians. Performance of the trained network models was assessed by 5-fold cross-validation in the main dataset and by pooling results from the 5 developed models in the external dataset. The Dice similarity coefficient (DSC) for individual delineation tasks and the primary tumor/metastasis classification accuracy were used as evaluation metrics. Additionally, a survival analysis using univariate Cox regression was performed comparing achieved group separation for manual and automated delineation, respectively.

RESULTS

In the cross-validation experiment, delineation of all malignant lesions with the trained U-Net models achieves DSC of 0.885, 0.805, and 0.870 for primary tumor, LN metastases, and the union of both, respectively. In external testing, the DSC reaches 0.850, 0.724, and 0.823 for primary tumor, LN metastases, and the union of both, respectively. The voxel classification accuracy was 98.0% and 97.9% in cross-validation and external data, respectively. Univariate Cox analysis in the cross-validation and the external testing reveals that manually and automatically derived total MTVs are both highly prognostic with respect to overall survival, yielding essentially identical hazard ratios (HR) ([Formula: see text]; [Formula: see text] vs. [Formula: see text]; [Formula: see text] in cross-validation and [Formula: see text]; [Formula: see text] vs. [Formula: see text]; [Formula: see text] in external testing).

CONCLUSION

To the best of our knowledge, this work presents the first CNN model for successful MTV delineation and lesion classification in HNC. In the vast majority of patients, the network performs satisfactory delineation and classification of primary tumor and lymph node metastases and only rarely requires more than minimal manual correction. It is thus able to massively facilitate study data evaluation in large patient groups and also does have clear potential for supervised clinical application.

Virtual 4DCT generated from 4DMRI in gated particle therapy: phantom validation and application to lung cancer patients

OBJECTIVE

Respiration negatively affects the outcome of a radiation therapy treatment, with potentially severe effects especially in particle therapy (PT). If compensation strategies are not applied, accuracy cannot be achieved. To support the clinical practice based on 4D Computed Tomography (CT), 4D Magnetic Resonance Imaging (MRI) acquisitions can be exploited. The purpose of this study was to validate a method for virtual 4DCT generation from 4DMRI data for lung cancers on a porcine lung phantom, and to apply it to lung cancer patients in PT.&#xD;Approach: Deformable image registration was used to register each respiratory phase of the 4DMRI to a reference phase. Then, a static 3DCT was registered to this reference MR image set, and the virtual 4DCT was generated by warping the registered CT according to previously obtained deformation fields. The method was validated on a physical phantom for which a ground truth 4DCT was available and tested on lung tumor patients, treated with gated PT at end-exhale, by comparing the virtual 4DCT with a re-evaluation 4DCT. The geometric and dosimetric evaluation was performed for both proton and carbon ion treatment plans.&#xD;Main results: The phantom validation exhibited a geometrical accuracy within the maximum resolution of the MRI and mean dose deviations, with respect to the prescription dose, up to 3.2% for target D95%, with a mean gamma pass rate of 98%. For patients, the virtual and re-evaluation 4DCTs showed good correspondence, with errors on target D95% up to 2% within the gating window. For one patient, dose variations up to 10% at end-exhale were observed due to relevant inter-fraction anatomo-pathological changes that occurred between the planning and re-evaluation CTs. &#xD;Significance: Results obtained on phantom data showed that the virtual 4DCT method was accurate, allowing its application on patient data for testing within a clinical scenario.&#xD;&#xD.

Pulmonary magnetic resonance-guided online adaptive radiotherapy of locally advanced: the PUMA trial

BACKGROUND

Patients with locally-advanced non-small-cell lung cancer (LA-NSCLC) are often ineligible for surgery, so that definitive chemoradiotherapy (CRT) represents the treatment of choice. Nevertheless, long-term tumor control is often not achieved. Intensification of radiotherapy (RT) to improve locoregional tumor control is limited by the detrimental effect of higher radiation exposure of thoracic organs-at-risk (OAR). This narrow therapeutic ratio may be expanded by exploiting the advantages of magnetic resonance (MR) linear accelerators, mainly the online adaptation of the treatment plan to the current anatomy based on daily acquired MR images. However, MR-guidance is both labor-intensive and increases treatment times, which raises the question of its clinical feasibility to treat LA-NSCLC. Therefore, the PUMA trial was designed as a prospective, multicenter phase I trial to demonstrate the clinical feasibility of MR-guided online adaptive RT in LA-NSCLC.

METHODS

Thirty patients with LA-NSCLC in stage III A-C will be accrued at three German university hospitals to receive MR-guided online adaptive RT at two different MR-linac systems (MRIdian Linac®, View Ray Inc. and Elekta Unity®, Elekta AB) with concurrent chemotherapy. Conventionally fractioned RT with isotoxic dose escalation up to 70 Gy is applied. Online plan adaptation is performed once weekly or in case of major anatomical changes. Patients are followed-up by thoracic CT- and MR-imaging for 24 months after treatment. The primary endpoint is twofold: (1) successfully completed online adapted fractions, (2) on-table time. Main secondary endpoints include adaptation frequency, toxicity, local tumor control, progression-free and overall survival.

DISCUSSION

PUMA aims to demonstrate the clinical feasibility of MR-guided online adaptive RT of LA-NSCLC. If successful, PUMA will be followed by a clinical phase II trial that further investigates the clinical benefits of this approach. Moreover, PUMA is part of a large multidisciplinary project to develop MR-guidance techniques.

TRIAL REGISTRATION

ClinicalTrials.gov: NCT05237453 .

Feasibility of CycleGAN enhanced low dose CBCT imaging for prostate radiotherapy dose calculation

OBJECTIVE

Daily CBCT imaging during the course of fractionated radiotherapy treatment can enable online adaptive radiotherapy but also expose patients to a non-negligible amount of radiation dose. This work investigates the feasibility of low dose CBCT imaging capable of enabling accurate prostate radiotherapy dose calculation with only 25% projections by overcoming under-sampling artifacts and correcting CT numbers by employing cycle-consistent generative adversarial networks (cycleGAN).&#xD;&#xD;Approach: Uncorrected CBCTs of 41 prostate cancer patients, acquired with ∼350 projections (CBCT_org), were retrospectively under-sampled to 25% dose images (CBCT_LD) with only ∼90 projections and reconstructed using FDK. We adapted a cycleGAN including shape loss to translate CBCT_LDinto planning CT (pCT) equivalent images (CBCT_{LD_GAN}). An alternative cycleGAN with a generator residual connection was implemented to improve anatomical fidelity (CBCT_{LD_ResGAN}).&#xD;&#xD;Unpaired 4-fold cross-validation (33 patients) was performed to allow using the median of 4 models as output. Deformable image registration was used to generate virtual CTs (vCT) for Hounsfield units (HU) accuracy evaluation on 8 additional test patients. Volumetric modulated arc therapy (VMAT) plans were optimized on vCT, and recalculated on CBCT_{LD_GAN}and CBCT_{LD_ResGAN}to determine dose calculation accuracy. CBCT_{LD_GAN}, CBCT_{LD_ResGAN}and CBCT_orgwere registered to pCT and residual shifts were analyzed. Bladder and rectum were manually contoured on CBCT_{LD_GAN}, CBCT_{LD_ResGAN}and CBCT_organd compared in terms of dice similarity coefficient (DSC), average and 95th percentile Hausdorff distance (HD_avg, HD₉₅).&#xD;&#xD;Main results: The mean absolute error decreased from 126 HU for CBCT_LDto 55 HU for CBCT_{LD_GAN}and 44 HU for CBCT_{LD_ResGAN}. For PTV, the median differences of D_98%, D_50%and D_2%comparing CBCT_{LD_GAN}to vCT were 0.3%, 0.3% and 0.3%, and comparing CBCT_{LD_ResGAN}to vCT were 0.4%, 0.3% and 0.4%. Dose accuracy was high with both 2% dose difference pass rates of 99% (10% dose threshold). Compared to CBCT_org-to-pCT registration, the majority of mean absolute differences of rigid transformation parameters were less than 0.20 mm/ 0.20°. For bladder and rectum, the DSC were 0.88 and 0.77 for CBCT_{LD_GAN}and 0.92 and 0.87 for CBCT_{LD_ResGAN}compared to CBCT_org, and HD_avgwere 1.34 mm and 1.93 mm for CBCT_{LD_GAN}, and 0.90 mm and 1.05 mm for CBCT_{LD_ResGAN}. The computational time was ∼2 s per patient.&#xD;&#xD;Significance: This study investigated the feasibility of adapting two cycleGAN models to simultaneously remove under-sampling artifacts and correct image intensities of 25% dose CBCT images. High accuracy on dose calculation, HU and patient alignment were achieved. CBCT_{LD_ResGAN}achieved better anatomical fidelity.

Ventilation and perfusion MRI at a 0.35 T MR-Linac: feasibility and reproducibility study

BACKGROUND

Hybrid devices that combine radiation therapy and MR-imaging have been introduced in the clinical routine for the treatment of lung cancer. This opened up not only possibilities in terms of accurate tumor tracking, dose delivery and adapted treatment planning, but also functional lung imaging. The aim of this study was to show the feasibility of Non-uniform Fourier Decomposition (NuFD) MRI at a 0.35 T MR-Linac as a potential treatment response assessment tool, and propose two signal normalization strategies for enhancing the reproducibility of the results.

METHODS

Ten healthy volunteers (median age 28 ± 8 years, five female, five male) were repeatedly scanned at a 0.35 T MR-Linac using an optimized 2D+t balanced steady-state free precession (bSSFP) sequence for two coronal slice positions. Image series were acquired in normal free breathing with breaks inside and outside the scanner as well as deep and shallow breathing. Ventilation- and perfusion-weighted maps were generated for each image series using NuFD. For intra-volunteer ventilation map reproducibility, a normalization factor was defined based on the linear correlation of the ventilation signal and diaphragm position of each scan as well as the diaphragm motion amplitude of a reference scan. This allowed for the correction of signal dependency on the diaphragm motion amplitude, which varies with breathing patterns. The second strategy, which can be used for ventilation and perfusion, eliminates the dependency on the signal amplitude by normalizing the ventilation/perfusion maps with the average ventilation/perfusion signal within a selected region-of-interest (ROI). The position and size dependency of this ROI was analyzed. To evaluate the performance of both approaches, the normalized ventilation/perfusion-weighted maps were compared and the deviation of the mean ventilation/perfusion signal from the reference was calculated for each scan. Wilcoxon signed-rank tests were performed to test whether the normalization methods can significantly improve the reproducibility of the ventilation/perfusion maps.

RESULTS

The ventilation- and perfusion-weighted maps generated with the NuFD algorithm demonstrated a mostly homogenous distribution of signal intensity as expected for healthy volunteers regardless of the breathing maneuver and slice position. Evaluation of the ROI's size and position dependency showed small differences in the performance. Applying both normalization strategies improved the reproducibility of the ventilation by reducing the median deviation of all scans to 9.1%, 5.7% and 8.6% for the diaphragm-based, the best and worst performing ROI-based normalization, respectively, compared to 29.5% for the non-normalized scans. The significance of this improvement was confirmed by the Wilcoxon signed rank test with [Formula: see text] at [Formula: see text]. A comparison of the techniques against each other revealed a significant difference in the performance between best ROI-based normalization and worst ROI ([Formula: see text]) and between best ROI-based normalization and scaling factor ([Formula: see text]), but not between scaling factor and worst ROI ([Formula: see text]). Using the ROI-based approach for the perfusion-maps, the uncorrected deviation of 10.2% was reduced to 5.3%, which was shown to be significant ([Formula: see text]).

CONCLUSIONS

Using NuFD for non-contrast enhanced functional lung MRI at a 0.35 T MR-Linac is feasible and produces plausible ventilation- and perfusion-weighted maps for volunteers without history of chronic pulmonary diseases utilizing different breathing patterns. The reproducibility of the results in repeated scans significantly benefits from the introduction of the two normalization strategies, making NuFD a potential candidate for fast and robust early treatment response assessment of lung cancer patients during MR-guided radiotherapy.

Patient-specific transfer learning for auto-segmentation in adaptive 0.35 T MRgRT of prostate cancer: a bi-centric evaluation

BACKGROUND

Online adaptive radiation therapy (RT) using hybrid magnetic resonance linear accelerators (MR-Linacs) can administer a tailored radiation dose at each treatment fraction. Daily MR imaging followed by organ and target segmentation adjustments allow to capture anatomical changes, improve target volume coverage, and reduce the risk of side effects. The introduction of automatic segmentation techniques could help to further improve the online adaptive workflow by shortening the re-contouring time and reducing intra- and inter-observer variability. In fractionated RT, prior knowledge, such as planning images and manual expert contours, is usually available before irradiation, but not used by current artificial intelligence-based autocontouring approaches.

PURPOSE

The goal of this study was to train convolutional neural networks (CNNs) for automatic segmentation of bladder, rectum (organs at risk, OARs), and clinical target volume (CTV) for prostate cancer patients treated at 0.35 T MR-Linacs. Furthermore, we tested the CNNs generalization on data from independent facilities and compared them with the MR-Linac treatment planning system (TPS) propagated structures currently used in clinics. Finally, expert planning delineations were utilized for patient- (PS) and facility-specific (FS) transfer learning to improve auto-segmentation of CTV and OARs on fraction images.

METHODS

In this study, data from fractionated treatments at 0.35 T MR-Linacs were leveraged to develop a 3D U-Net-based automatic segmentation. Cohort C1 had 73 planning images and cohort C2 had 19 planning and 240 fraction images. The baseline models (BMs) were trained solely on C1 planning data using 53 MRIs for training and 10 for validation. To assess their accuracy, the models were tested on three data subsets: (i) 10 C1 planning images not used for training, (ii) 19 C2 planning, and (iii) 240 C2 fraction images. BMs also served as a starting point for FS and PS transfer learning, where the planning images from C2 were used for network parameter fine tuning. The segmentation output of the different trained models was compared against expert ground truth by means of geometric metrics. Moreover, a trained physician graded the network segmentations as well as the segmentations propagated by the clinical TPS.

RESULTS

The BMs showed dice similarity coefficients (DSC) of 0.88(4) and 0.93(3) for the rectum and the bladder, respectively, independent of the facility. CTV segmentation with the BM was the best for intermediate- and high-risk cancer patients from C1 with DSC=0.84(5) and worst for C2 with DSC=0.74(7). The PS transfer learning brought a significant improvement in the CTV segmentation, yielding DSC=0.72(4) for post-prostatectomy and low-risk patients and DSC=0.88(5) for intermediate- and high-risk patients. The FS training did not improve the segmentation accuracy considerably. The physician's assessment of the TPS-propagated versus network-generated structures showed a clear advantage of the latter.

CONCLUSIONS

The obtained results showed that the presented segmentation technique has potential to improve automatic segmentation for MR-guided RT.

Comparison of MR-guided radiotherapy accumulated doses for central lung tumors with non-adaptive and online adaptive proton therapy

BACKGROUND

Stereotactic body radiation therapy (SBRT) of central lung tumors with photon or proton therapy has a risk of increased toxicity. Treatment planning studies comparing accumulated doses for state-of-the-art treatment techniques, such as MR-guided radiotherapy (MRgRT) and intensity modulated proton therapy (IMPT), are currently lacking.

PURPOSE

We conducted a comparison of accumulated doses for MRgRT, robustly optimized non-adaptive IMPT, and online adaptive IMPT for central lung tumors. A special focus was set on analyzing the accumulated doses to the bronchial tree, a parameter linked to high-grade toxicities.

METHODS

Data of 18 early-stage central lung tumor patients, treated at a 0.35 T MR-linac in eight or five fractions, were analyzed. Three gated treatment scenarios were compared: (S1) online adaptive MRgRT, (S2) non-adaptive IMPT, and (S3) online adaptive IMPT. The treatment plans were recalculated or reoptimized on the daily imaging data acquired during MRgRT, and accumulated over all treatment fractions. Accumulated dose-volume histogram (DVH) parameters of the gross tumor volume (GTV), lung, heart, and organs-at-risk (OARs) within 2 cm of the planning target volume (PTV) were extracted for each scenario and compared in Wilcoxon signed-rank tests between S1 & S2, and S1 & S3.

RESULTS

The accumulated GTV D_98% was above the prescribed dose for all patients and scenarios. Significant reductions (p < 0.05) of the mean ipsilateral lung dose (S2: -8%; S3: -23%) and mean heart dose (S2: -79%; S3: -83%) were observed for both proton scenarios compared to S1. The bronchial tree D_0.1cc was significantly lower for S3 (S1: 48.1 Gy; S3: 39.2 Gy; p = 0.005), but not significantly different for S2 (S2: 45.0 Gy; p = 0.094), compared to S1. The D_0.1cc for S2 and S3 compared to S1 was significantly (p < 0.05) smaller for OARs within 1-2 cm of the PTV (S1: 30.2 Gy; S2: 24.6 Gy; S3: 23.1 Gy), but not significantly different for OARs within 1 cm of the PTV.

CONCLUSIONS

A significant dose sparing potential of non-adaptive and online adaptive proton therapy compared to MRgRT for OARs in close, but not direct proximity of central lung tumors was identified. The near-maximum dose to the bronchial tree was not significantly different for MRgRT and non-adaptive IMPT. Online adaptive IMPT achieved significantly lower doses to the bronchial tree compared to MRgRT.

Evaluation of real-time tumor contour prediction using LSTM networks for MR-guided radiotherapy

BACKGROUND AND PURPOSE

Magnetic resonance imaging guided radiotherapy (MRgRT) with deformable multileaf collimator (MLC) tracking would allow to tackle both rigid displacement and tumor deformation without prolonging treatment. However, the system latency must be accounted for by predicting future tumor contours in real-time. We compared the performance of three artificial intelligence (AI) algorithms based on long short-term memory (LSTM) modules for the prediction of 2D-contours 500ms into the future.

MATERIALS AND METHODS

Models were trained (52 patients, 3.1h of motion), validated (18 patients, 0.6h) and tested (18 patients, 1.1h) with cine MRs from patients treated at one institution. Additionally, we used three patients (2.9h) treated at another institution as second testing set. We implemented 1) a classical LSTM network (LSTM-shift) predicting tumor centroid positions in superior-inferior and anterior-posterior direction which are used to shift the last observed tumor contour. The LSTM-shift model was optimized both in an offline and online fashion. We also implemented 2) a convolutional LSTM model (ConvLSTM) to directly predict future tumor contours and 3) a convolutional LSTM combined with spatial transformer layers (ConvLSTM-STL) to predict displacement fields used to warp the last tumor contour.

RESULTS

The online LSTM-shift model was found to perform slightly better than the offline LSTM-shift and significantly better than the ConvLSTM and ConvLSTM-STL. It achieved a 50% Hausdorff distance of 1.2mm and 1.0mm for the two testing sets, respectively. Larger motion ranges were found to lead to more substantial performance differences across the models.

CONCLUSION

LSTM networks predicting future centroids and shifting the last tumor contour are the most suitable for tumor contour prediction. The obtained accuracy would allow to reduce residual tracking errors during MRgRT with deformable MLC-tracking.

18F-FET PET radiomics-based survival prediction in glioblastoma patients receiving radio(chemo)therapy

Background

Quantitative image analysis based on radiomic feature extraction is an emerging field for survival prediction in oncological patients. 18F-Fluorethyltyrosine positron emission tomography (18F-FET PET) provides important diagnostic and grading information for brain tumors, but data on its use in survival prediction is scarce. In this study, we aim at investigating survival prediction based on multiple radiomic features in glioblastoma patients undergoing radio(chemo)therapy.

Methods

A dataset of 37 patients with glioblastoma (WHO grade 4) receiving radio(chemo)therapy was analyzed. Radiomic features were extracted from pre-treatment 18F-FET PET images, following intensity rebinning with a fixed bin width. Principal component analysis (PCA) was applied for variable selection, aiming at the identification of the most relevant features in survival prediction. Random forest classification and prediction algorithms were optimized on an initial set of 25 patients. Testing of the implemented algorithms was carried out in different scenarios, which included additional 12 patients whose images were acquired with a different scanner to check the reproducibility in prediction results.

Results

First order intensity variations and shape features were predominant in the selection of most important radiomic signatures for survival prediction in the available dataset. The major axis length of the 18F-FET-PET volume at tumor to background ratio (TBR) 1.4 and 1.6 correlated significantly with reduced probability of survival. Additional radiomic features were identified as potential survival predictors in the PTV region, showing 76% accuracy in independent testing for both classification and regression.

Conclusions

18F-FET PET prior to radiation provides relevant information for survival prediction in glioblastoma patients. Based on our preliminary analysis, radiomic features in the PTV can be considered a robust dataset for survival prediction.

Validation of prompt gamma-ray spectroscopy for proton range verification in tissue-mimicking and porcine samples

Objective. Proton therapy of cancer improves dose conformality to the target and sparing of surrounding healthy tissues compared to conventional photon treatments. However, proton therapy's advantage could be even larger if proton range uncertainties were reduced. Sources of range uncertainties include computed tomography treatment planning images and variations in patient anatomy and setup. To reduce range uncertainties, we have developed a system for real-timein vivorange monitoring. The system is based on spectroscopy of prompt gamma-rays emitted through proton-nuclear interactions during irradiation. We validated the performance of our prompt gamma-ray spectroscopy detector prototype using tissue-mimicking and porcine samples.Approach. Measurements were performed in water, four tissue-mimicking samples (spongiosa, muscle, adipose tissue, and cortical bone), and two porcine samples (liver and brain). A dose of 0.9 Gy was delivered to a target at a depth of 12.5-17.5 cm. Multi-layer ionization chamber measurements were performed to determine stopping power ratios relative to water and ground truth proton ranges. Ground truth elemental compositions were determined using combustion analysis. Proton ranges and elemental compositions measured using prompt gamma-ray spectroscopy were compared to the ground truth.Main results. For all samples, the mean measured range over all pencil-beam spots differed from the ground truth by less than 1.2 mm. The mean standard deviation was 0.9 mm (range: 0.4-1.6 mm). The mean difference between ground truth and measured elemental compositions was 0.06gcm3(range: 0.00gcm3to 0.12gcm3).Significance. We verified the performance of our prompt gamma-ray spectroscopy detector prototype for proton range verification using tissue-mimicking and porcine samples. Measured proton ranges and elemental sample compositions were in good agreement with the ground truth. These measurements confirm the system's reliability for a variety of tissues and bridge the gap between previously-reported experiments and ongoingin vivopatient measurements.

Assessment of quantitative information for radiation therapy at a first-generation clinical photon-counting computed tomography scanner

As one of the latest developments in X-ray computed tomography (CT), photon-counting technology allows spectral detection, demonstrating considerable advantages as compared to conventional CT. In this study, we investigated the use of a first-generation clinical photon-counting computed tomography (PCCT) scanner and estimated proton relative (to water) stopping power (RSP) of tissue-equivalent materials from virtual monoenergetic reconstructions provided by the scanner. A set of calibration and evaluation tissue-equivalent inserts were scanned at 120 kVp. Maps of relative electron density (RED) and effective atomic number (EAN) were estimated from the reconstructed virtual monoenergetic images (VMI) using an approach previously applied to a spectral CT scanner with dual-layer detector technology, which allows direct calculation of RSP using the Bethe-Bloch formula. The accuracy of RED, EAN, and RSP was evaluated by root-mean-square errors (RMSE) averaged over the phantom inserts. The reference RSP values were obtained experimentally using a water column in an ion beam. For RED and EAN, the reference values were calculated based on the mass density and the chemical composition of the inserts. Different combinations of low- and high-energy VMIs were investigated in this study, ranging from 40 to 190 keV. The overall lowest error was achieved using VMIs at 60 and 180 keV, with an RSP accuracy of 1.27% and 0.71% for the calibration and the evaluation phantom, respectively.

Fabrication and characterization of a multimodal 3D printed mouse phantom for ionoacoustic quality assurance in image-guided pre-clinical proton radiation research

Objectives Image guidance and precise irradiation are fundamental to ensure the reliability of small animal oncology studies. Accurate positioning of the animal and the in-beam monitoring of the delivered radio-therapeutic treatment necessitate several imaging modalities. In the particular context of proton therapy with a pulsed beam, information on the delivered dose can be retrieved by monitoring the thermoacoustic waves resulting from the brief and local energy deposition induced by a proton beam (ionoacoustics). The objective of this work was to fabricate a multimodal phantom (x-ray, proton, ultrasound, and ionoacoustic) allowing for sufficient imaging contrast for all the modalities. Approach The phantom anatomical parts were extracted from mouse computed tomography scans and printed using polylactic acid (organs) and a granite / polylactic acid composite (skeleton). The anatomical pieces were encapsulated in silicone rubber to ensure long term stability. The phantom was imaged using x-ray cone-beam computed tomography, proton radiography, ultrasound imaging, and monitoring of a 20 MeV pulsed proton beam using ionoacoustics. Main results The anatomical parts could be visualized in all the imaging modalities validating the phantom capability to be used for multimodal imaging. Ultrasound images were simulated from the x-ray cone-beam computed tomography and co-registered with ultrasound images obtained before the phantom irradiation and low-resolution ultrasound images of the mouse phantom in the irradiation position, co-registered with ionoacoustic measurements. The latter confirmed the irradiation of a tumor surrogate for which the reconstructed range was found to be in reasonable agreement with the expectation. Significance This study reports on a realistic small animal phantom which can be used to investigate ionoacoustic range (or dose) verification together with ultrasound, x-ray, and proton imaging. The co-registration between ionoacoustic reconstructions of the impinging proton beam and x-ray imaging is assessed for the first time in a pre-clinical scenario.

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.

Intrafractional monitoring of patients using four different immobilization mask systems for cranial radiotherapy

Background and purpose

Patients receiving cranial radiotherapy are immobilized with a thermoplastic mask to restrict patient motion. Depending on the target volume margins and treatment dose, different mask systems are used. Intrafractional movements can be monitored using stereoscopic X-ray imaging. The aim of the present work was to compare the magnitudes of intrafractional deviation for different mask systems.

Material and methods

Four different head mask systems (open face mask, open mask, stereotactic mask, double mask) used in the treatment of 40 patients were investigated. In total 487 treatment fractions and 3708 X-ray images were collected. Deviations were calculated by comparison of the acquired X-ray images with digitally reconstructed radiographs. The results of intrafractional X-ray deviations for translational and rotational axes were compared between the different mask systems.

Results

Deviations were below 0.6 mm for translations and below 0.6° for rotations for all mask systems. Along the lateral and longitudinal directions the stereotactic mask was superior, while along the vertical direction the double mask showed the lowest deviations. For low rotational deviations the double mask is the best amongst all other mask systems.

Conclusion

As expected, the lowest movement was shown using cranial stereotactic mask systems. The results have shown deviations lower than 0.6 mm and 0.6° using any of the four thermoplastic mask systems.

Deep learning based time-to-event analysis with PET, CT and joint PET/CT for head and neck cancer prognosis

OBJECTIVES

Recent studies have shown that deep learning based on pre-treatment positron emission tomography (PET) or computed tomography (CT) is promising for distant metastasis (DM) and overall survival (OS) prognosis in head and neck cancer (HNC). However, lesion segmentation is typically required, resulting in a predictive power susceptible to variations in primary and lymph node gross tumor volume (GTV) segmentation. This study aimed at achieving prognosis without GTV segmentation, and extending single modality prognosis to joint PET/CT to allow investigating the predictive performance of combined- compared to single-modality inputs.

METHODS

We employed a 3D-Resnet combined with a time-to-event outcome model to incorporate censoring information. We focused on the prognosis of DM and OS for HNC patients. For each clinical endpoint, five models with PET and/or CT images as input were compared: PET-GTV, PET-only, CT-GTV, CT-only, and PET/CT-GTV models, where -GTV indicates that the corresponding images were masked using the GTV contour. Publicly available delineated CT and PET scans from 4 different Canadian hospitals (293) and the MAASTRO clinic (74) were used for training by 3-fold cross-validation (CV). For independent testing, we used 110 patients from a collaborating institution. The predictive performance was evaluated via Harrell's Concordance Index (HCI) and Kaplan-Meier curves.

RESULTS

In a 5-year time-to-event analysis, all models could produce CV HCIs with median values around 0.8 for DM and 0.7 for OS. The best performance was obtained with the PET-only model, achieving a median testing HCI of 0.82 for DM and 0.69 for OS. Compared with the PET/CT-GTV model, the PET-only still had advantages of up to 0.07 in terms of testing HCI. The Kaplan-Meier curves and corresponding log-rank test results also demonstrated significant stratification capability of our models for the testing cohort.

CONCLUSION

Deep learning-based DM and OS time-to-event models showed predictive capability and could provide indications for personalized RT. The best predictive performance achieved by the PET-only model suggested GTV segmentation might be less relevant for PET-based prognosis.

18F-Fluorodeoxyglucose Positron Emission Tomography of Head and Neck Cancer: Location and HPV Specific Parameters for Potential Treatment Individualization

Purpose

18F-fluorodeoxyglucose positron emission tomography (FDG-PET) is utilized for staging and treatment planning of head and neck squamous cell carcinomas (HNSCC). Some older publications on the prognostic relevance showed inconclusive results, most probably due to small study sizes. This study evaluates the prognostic and potentially predictive value of FDG-PET in a large multi-center analysis.

Methods

Original analysis of individual FDG-PET and patient data from 16 international centers (8 institutional datasets, 8 public repositories) with 1104 patients. All patients received curative intent radiotherapy/chemoradiation (CRT) and pre-treatment FDG-PET imaging. Primary tumors were semi-automatically delineated for calculation of SUV_max, SUV_mean, metabolic tumor volume (MTV) and total lesion glycolysis (TLG). Cox regression analyses were performed for event-free survival (EFS), overall survival (OS), loco-regional control (LRC) and freedom from distant metastases (FFDM).

Results

FDG-PET parameters were associated with patient outcome in the whole cohort regarding clinical endpoints (EFS, OS, LRC, FFDM), in uni- and multivariate Cox regression analyses. Several previously published cut-off values were successfully validated. Subgroup analyses identified tumor- and human papillomavirus (HPV) specific parameters. In HPV positive oropharynx cancer (OPC) SUV_max was well suited to identify patients with excellent LRC for organ preservation. Patients with SUV_max of 14 or less were unlikely to develop loco-regional recurrence after definitive CRT. In contrast FDG PET parameters deliver only limited prognostic information in laryngeal cancer.

Conclusion

FDG-PET parameters bear considerable prognostic value in HNSCC and potential predictive value in subgroups of patients, especially regarding treatment de-intensification and organ-preservation. The potential predictive value needs further validation in appropriate control groups. Further research on advanced imaging approaches including radiomics or artificial intelligence methods should implement the identified cut-off values as benchmark routine imaging parameters.

Offline and online LSTM networks for respiratory motion prediction in MR-guided radiotherapy

Objective. Gated beam delivery is the current clinical practice for respiratory motion compensation in MR-guided radiotherapy, and further research is ongoing to implement tracking. To manage intra-fractional motion using multileaf collimator tracking the total system latency needs to be accounted for in real-time. In this study, long short-term memory (LSTM) networks were optimized for the prediction of superior–inferior tumor centroid positions extracted from clinically acquired 2D cine MRIs. Approach. We used 88 patients treated at the University Hospital of the LMU Munich for training and validation (70 patients, 13.1 h), and for testing (18 patients, 3.0 h). Three patients treated at Fondazione Policlinico Universitario Agostino Gemelli were used as a second testing set (1.5 h). The performance of the LSTMs in terms of root mean square error (RMSE) was compared to baseline linear regression (LR) models for forecasted time spans of 250 ms, 500 ms and 750 ms. Both the LSTM and the LR were trained with offline (offline LSTM and offline LR) and online schemes (offline+online LSTM and online LR), the latter to allow for continuous adaptation to recent respiratory patterns. Main results. We found the offline+online LSTM to perform best for all investigated forecasts. Specifically, when predicting 500 ms ahead it achieved a mean RMSE of 1.20 mm and 1.00 mm, while the best performing LR model achieved a mean RMSE of 1.42 mm and 1.22 mm for the LMU and Gemelli testing set, respectively. Significance. This indicates that LSTM networks have potential as respiratory motion predictors and that continuous online re-optimization can enhance their performance.

Single-isocenter stereotactic radiosurgery for multiple brain metastases: Impact of patient misalignments on target coverage in non-coplanar treatments

Frameless single-isocenter non-coplanar stereotactic radiosurgery (SRS) for patients with multiple brain metastases is a treatment at high geometrical complexity. The goal of this study is to analyze the dosimetric impact of non-coplanar image guidance with stereoscopic X-ray imaging. Such an analysis is meant to provide insights on the adequacy of safety margins, and to evaluate the benefit of imaging at non-coplanar configurations. The ExacTrac® (ET) system (Brainlab AG, Munich, Germany) was used for stereoscopic X-ray imaging in frameless single-isocenter non-coplanar SRS for multiple brain metastases. Sub-millimeter precision was found for the ET-based pre-treatment setup, whereas a degradation was noted for non-coplanar treatment angles. Misalignments without intra-fractional positioning corrections were reconstructed in 6 degrees of freedom (DoF) to resemble the situation without non-coplanar image guidance. Dose recalculation in 20 SRS patients with applied positioning corrections did not reveal any significant differences in D_98% for 75 planning target volumes (PTVs) and gross tumor volumes (GTVs). For recalculation without applied positioning corrections, significant differences (p<0.05) were reported in D_98% for both PTVs and GTVs, with stronger effects for small PTV volumes. A worst-case analysis at increasing translational and rotational misalignment revealed that dosimetric changes are a complex function of the combination thereof. This study highlighted the important role of positioning correction with ET at non-coplanar configurations in frameless single-isocenter non-coplanar SRS for patients with multiple brain metastases. Uncorrected patient misalignments at non-coplanar couch angles were linked to a significant loss of PTV coverage, with effects varying according to the combination of single DoF and PTV geometrical properties.

Comparative accuracy and resolution assessment of two prototype proton computed tomography scanners

BACKGROUND

Improving the accuracy of relative stopping power (RSP) in proton therapy may allow reducing range margins. Proton computed tomography (pCT) has been shown to provide state-of-the-art RSP accuracy estimation, and various scanner prototypes have recently been built. The different approaches used in scanner design are expected to impact spatial resolution and RSP accuracy.

PURPOSE

The goal of this study was to perform the first direct comparison, in terms of spatial resolution and RSP accuracy, of two pCT prototype scanners installed at the same facility and by using the same image reconstruction algorithm.

METHODS

A phantom containing cylindrical inserts of known RSP was scanned at the phase-II pCT prototype of the U.S. pCT collaboration and at the commercially oriented ProtonVDA scanner. Following distance-driven binning filtered backprojection reconstruction, the radial edge spread function of high-density inserts was used to estimate the spatial resolution. RSP accuracy was evaluated by the mean absolute percent error (MAPE) over the inserts. No direct imaging dose estimation was possible, which prevented a comparison of the two scanners in terms of RSP noise.

RESULTS

In terms of RSP accuracy, both scanners achieved the same MAPE of 0.72% when excluding the porous sinus insert from the evaluation. The ProtonVDA scanner reached a better overall MAPE when all inserts and the body of the phantom were accounted for (0.81%), compared to the phase-II scanner (1.14%). The spatial resolution with the phase-II scanner was found to be 0.61 lp/mm, while for the ProtonVDA scanner somewhat lower at 0.46 lp/mm.

CONCLUSIONS

The comparison between two prototype pCT scanners operated in the same clinical facility showed that they both fulfill the requirement of an RSP accuracy of about 1%. Their spatial resolution performance reflects the different design choices of either a scanner with full tracking capabilities (phase-II) or of a more compact tracker system which only provides the positions of protons but not their directions (ProtonVDA). This article is protected by copyright. All rights reserved.

Evaluation of an anthropomorphic ion chamber and 3D gel dosimetry head phantom at a 0.35 T MR-linac using separate 1.5 T MR-scanners for gel readout

PURPOSE

To date, no universally accepted technique for the evaluation of the overall dosimetric performance of hybrid integrated magnetic resonance imaging (MR) - linear accelerators (linacs) is available. We report on the suitability and reliability of a novel phantom with modular inserts for combined polymer gel (PG) and ionisation chamber (IC) measurements at a 0.35 T MR-linac.

METHODS

Three 3D-printed, modular head phantoms, based on real patient anatomy, were used for repeated (2 times) PG irradiations of cranial treatment plans on a 0.35 T MR-linac. The PG readout was performed on two 1.5 T diagnostic MR-scanners to reduce scanning time. The PG dose volumes were normalised to the IC dose (normalised dose N1) and to the median planning target volume dose (normalised dose N2). Linearity of the PG dose response was validated and dose profiles, centres of mass (COM) of the 95% isodoses and dose volume histograms (DVH) were compared between planned and measured dose distributions and a 3D gamma analysis was performed.

RESULTS

Dose linearity of the PG was good (R²> 0.99 for all linear fit functions). High agreement was found between planned and measured dose volumes in the dose profiles and DVHs. The largest dose deviation was found in the intermediate dose region (mean dose deviation 0.2Gy; 5.6%). A mean COM offset of 1.2mm indicated high spatial accuracy. Mean 3D gamma passing rates (2%, 2mm) of 83.3% for N1 and 91.6% for N2 dose distributions were determined. When comparing repeated PG measurements to each other, a mean gamma passing rate of 95.7% was found.

CONCLUSION

The new modular phantom was found practical for use at a 0.35 T MR-linac. In contrast to the high dose region, larger mean deviations were found in the mid dose range. The PG measurements showed high reproducibility. The MR-linac performed well in a non-adaptive setting in terms of spatial and dosimetric accuracy.

Dosimetric benefit of MR-guided online adaptive radiotherapy in different tumor entities: liver, lung, abdominal lymph nodes, pancreas and prostate

Background

Hybrid magnetic resonance (MR)-Linac systems have recently been introduced into clinical practice. The systems allow online adaption of the treatment plan with the aim of compensating for interfractional anatomical changes. The aim of this study was to evaluate the dose volume histogram (DVH)-based dosimetric benefits of online adaptive MR-guided radiotherapy (oMRgRT) across different tumor entities and to investigate which subgroup of plans improved the most from adaption.

Methods

Fifty patients treated with oMRgRT for five different tumor entities (liver, lung, multiple abdominal lymph nodes, pancreas, and prostate) were included in this retrospective analysis. Various target volume (gross tumor volume GTV, clinical target volume CTV, and planning target volume PTV) and organs at risk (OAR) related DVH parameters were compared between the dose distributions before and after plan adaption.

Results

All subgroups clearly benefited from online plan adaption in terms of improved PTV coverage. For the liver, lung and abdominal lymph nodes cases, a consistent improvement in GTV coverage was found, while many fractions of the prostate subgroup showed acceptable CTV coverage even before plan adaption. The largest median improvements in GTV near-minimum dose (D_98%) were found for the liver (6.3%, p < 0.001), lung (3.9%, p < 0.001), and abdominal lymph nodes (6.8%, p < 0.001) subgroups. Regarding OAR sparing, the largest median OAR dose reduction during plan adaption was found for the pancreas subgroup (-87.0%). However, in the pancreas subgroup an optimal GTV coverage was not always achieved because sparing of OARs was prioritized.

Conclusion

With online plan adaptation, it was possible to achieve significant improvements in target volume coverage and OAR sparing for various tumor entities and account for interfractional anatomical changes.

Evaluation of the impact of a scanner prototype on proton CT and helium CT image quality and dose efficiency with Monte Carlo simulation

Objective.The use of ion computed tomography (CT) promises to yield improved relative stopping power (RSP) estimation as input to particle therapy treatment planning. Recently, proton CT (pCT) has been shown to yield RSP accuracy on par with state-of-the-art x-ray dual energy CT. There are however concerns that the lower spatial resolution of pCT compared to x-ray CT may limit its potential, which has spurred interest in the use of helium ion CT (HeCT). The goal of this study was to investigate image quality of pCT and HeCT in terms of noise, spatial resolution, RSP accuracy and imaging dose using a detailed Monte Carlo (MC) model of an existing ion CT prototype.Approach.Three phantoms were used in simulated pCT and HeCT scans allowing estimation of noise, spatial resolution and the scoring of dose. An additional phantom was used to evaluate RSP accuracy. The imaging dose required to achieve the same image noise in a water and a head phantom was estimated at both native spatial resolution, and in a scenario where the HeCT spatial resolution was reduced and matched to that of pCT using Hann windowing of the reconstruction filter. A variance reconstruction formalism was adapted to account for Hann windowing.Main results.We confirmed that the scanner prototype would produce higher spatial resolution for HeCT than pCT by a factor 1.8 (0.86 lp mm^-1versus 0.48 lp mm^-1at the center of a 20 cm water phantom). At native resolution, HeCT required a factor 2.9 more dose than pCT to achieve the same noise, while at matched resolution, HeCT required only 38% of the pCT dose. Finally, RSP mean absolute percent error (MAPE) was found to be 0.59% for pCT and 0.67% for HeCT.Significance.This work compared the imaging performance of pCT and HeCT when using an existing scanner prototype, with the spatial resolution advantage of HeCT coming at the cost of increased dose. When matching spatial resolution via Hann windowing, HeCT had a substantial dose advantage. Both modalities provided state-of-the-art RSP MAPE. HeCT might therefore help reduce the dose exposure of patients with comparable image noise to pCT, enhanced spatial resolution and acceptable RSP accuracy at the same time.

Dosimetric impact of deep learning-based CT auto-segmentation on radiation therapy treatment planning for prostate cancer

Background

The evaluation of automatic segmentation algorithms is commonly performed using geometric metrics. An analysis based on dosimetric parameters might be more relevant in clinical practice but is often lacking in the literature. The aim of this study was to investigate the impact of state-of-the-art 3D U-Net-generated organ delineations on dose optimization in radiation therapy (RT) for prostate cancer patients.

Methods

A database of 69 computed tomography images with prostate, bladder, and rectum delineations was used for single-label 3D U-Net training with dice similarity coefficient (DSC)-based loss. Volumetric modulated arc therapy (VMAT) plans have been generated for both manual and automatic segmentations with the same optimization settings. These were chosen to give consistent plans when applying perturbations to the manual segmentations. Contours were evaluated in terms of DSC, average and 95% Hausdorff distance (HD). Dose distributions were evaluated with the manual segmentation as reference using dose volume histogram (DVH) parameters and a 3%/3 mm gamma-criterion with 10% dose cut-off. A Pearson correlation coefficient between DSC and dosimetric metrics, i.e. gamma index and DVH parameters, has been calculated.

Results

3D U-Net-based segmentation achieved a DSC of 0.87 (0.03) for prostate, 0.97 (0.01) for bladder and 0.89 (0.04) for rectum. The mean and 95% HD were below 1.6 (0.4) and below 5 (4) mm, respectively. The DVH parameters, V\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$_{60/65/70\,{\mathrm{Gy}}}$$\end{document}60/65/70Gy for the bladder and V\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$_{50/65/70\,{\mathrm{Gy}}}$$\end{document}50/65/70Gy for the rectum, showed agreement between dose distributions within \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\pm \, 5\%$$\end{document}±5% and \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\pm \,2\%$$\end{document}±2%, respectively. The D\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$_{98/2\%}$$\end{document}98/2% and V\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$_{95\%}$$\end{document}95%, for prostate and its 3 mm expansion (surrogate clinical target volume) showed agreement with the reference dose distribution within 2% and 3 Gy with the exception of one case. The average gamma pass-rate was 85%. The comparison between geometric and dosimetric metrics showed no strong statistically significant correlation.

Conclusions

The 3D U-Net developed for this work achieved state-of-the-art geometrical performance. Analysis based on clinically relevant DVH parameters of VMAT plans demonstrated neither excessive dose increase to OARs nor substantial under/over-dosage of the target in all but one case. Yet the gamma analysis indicated several cases with low pass rates. The study highlighted the importance of adding dosimetric analysis to the standard geometric evaluation.