CBCT-DRRs superior to CT-DRRs for target-tracking applications for pancreatic SBRT.

Objective.In current radiograph-based intra-fraction markerless target-tracking, digitally reconstructed radiographs (DRRs) from planning CTs (CT-DRRs) are often used to train deep learning models that extract information from the intra-fraction radiographs acquired during treatment. Traditional DRR algorithms were designed for patient alignment (i.e.bone matching) and may not replicate the radiographic image quality of intra-fraction radiographs at treatment. Hypothetically, generating DRRs from pre-treatment Cone-Beam CTs (CBCT-DRRs) with DRR algorithms incorporating physical modelling of on-board-imagers (OBIs) could improve the similarity between intra-fraction radiographs and DRRs by eliminating inter-fraction variation and reducing image-quality mismatches between radiographs and DRRs. In this study, we test the two hypotheses that intra-fraction radiographs are more similar to CBCT-DRRs than CT-DRRs, and that intra-fraction radiographs are more similar to DRRs from algorithms incorporating physical models of OBI components than DRRs from algorithms omitting these models.Approach.DRRs were generated from CBCT and CT image sets collected from 20 patients undergoing pancreas stereotactic body radiotherapy. CBCT-DRRs and CT-DRRs were generated replicating the treatment position of patients and the OBI geometry during intra-fraction radiograph acquisition. To investigate whether the modelling of physical OBI components influenced radiograph-DRR similarity, four DRR algorithms were applied for the generation of CBCT-DRRs and CT-DRRs, incorporating and omitting different combinations of OBI component models. The four DRR algorithms were: a traditional DRR algorithm, a DRR algorithm with source-spectrum modelling, a DRR algorithm with source-spectrum and detector modelling, and a DRR algorithm with source-spectrum, detector and patient material modelling. Similarity between radiographs and matched DRRs was quantified using Pearson's correlation and Czekanowski's index, calculated on a per-image basis. Distributions of correlations and indexes were compared to test each of the hypotheses. Distribution differences were determined to be statistically significant when Wilcoxon's signed rank test and the Kolmogorov-Smirnov two sample test returnedp≤ 0.05 for both tests.Main results.Intra-fraction radiographs were more similar to CBCT-DRRs than CT-DRRs for both metrics across all algorithms, with allp≤ 0.007. Source-spectrum modelling improved radiograph-DRR similarity for both metrics, with allp< 10-6. OBI detector modelling and patient material modelling did not influence radiograph-DRR similarity for either metric.Significance.Generating DRRs from pre-treatment CBCT-DRRs is feasible, and incorporating CBCT-DRRs into markerless target-tracking methods may promote improved target-tracking accuracies. Incorporating source-spectrum modelling into a treatment planning system's DRR algorithms may reinforce the safe treatment of cancer patients by aiding in patient alignment.

Super-resolution neural networks improve the spatiotemporal resolution of adaptive MRI-guided radiation therapy.

BACKGROUND: Magnetic resonance imaging (MRI) offers superb non-invasive, soft tissue imaging of the human body. However, extensive data sampling requirements severely restrict the spatiotemporal resolution achievable with MRI. This limits the modality's utility in real-time guidance applications, particularly for the rapidly growing MRI-guided radiation therapy approach to cancer treatment. Recent advances in artificial intelligence (AI) could reduce the trade-off between the spatial and the temporal resolution of MRI, thus increasing the clinical utility of the imaging modality. METHODS: We trained deep learning-based super-resolution neural networks to increase the spatial resolution of real-time MRI. We developed a framework to integrate neural networks directly onto a 1.0 T MRI-linac enabling real-time super-resolution imaging. We integrated this framework with the targeting system of the MRI-linac to demonstrate real-time beam adaptation with super-resolution-based imaging. We tested the integrated system using large publicly available datasets, healthy volunteer imaging, phantom imaging, and beam tracking experiments using bicubic interpolation as a baseline comparison. RESULTS: Deep learning-based super-resolution increases the spatial resolution of real-time MRI across a variety of experiments, offering measured performance benefits compared to bicubic interpolation. The temporal resolution is not compromised as measured by a real-time adaptation latency experiment. These two effects, an increase in the spatial resolution with a negligible decrease in the temporal resolution, leads to a net increase in the spatiotemporal resolution. CONCLUSIONS: Deployed super-resolution neural networks can increase the spatiotemporal resolution of real-time MRI. This has applications to domains such as MRI-guided radiation therapy and interventional procedures.

Magnetic resonance imaging (MRI) is a medical imaging modality that is used to image organs such as the brain, lungs, and liver as well as diseases such as cancer. MRI scans taken at high resolution are of overly long duration. This time constraint limits the accuracy of MRI-guided cancer radiation therapy, where imaging must be fast to adapt treatment to tumour motion. Here, we deployed artificial intelligence (AI) models to achieve fast and high detail MRI. We additionally validated our AI models across various scenarios. These AI-based models could potentially enable people with cancer to be treated with higher accuracy and precision.

The Remove-the-Mask Open-Source head and neck Surface-Guided radiation therapy system.

Background and Purpose: Surface Guided Radiotherapy (SGRT) for head and neck radiotherapy is challenging as obstructions are common and non-rigid facial motion can compromise surface accuracy. The purpose of this work was to develop and benchmark the Remove the Mask (RtM) SGRT system, an open-source system especially designed to address the challenges faced in radiotherapy of head and neck cancer. Materials and Methods: The accuracy of the RtM SGRT system was benchmarked using a head phantom positioned on a robotic motion platform capable of sub-millimetre accuracy which was used to induce unidirectional shifts and to reproduce three real head motion traces. We also assessed the accuracy of the system in ten humans volunteers. The ground truth motion of the volunteers was obtained using a commercial motion capture system with an accuracy < 0.3 mm. Results: The mean tracking error of the RtM SGRT system for the ten volunteers was of -0.1 ± 0.4 mm -0.6 ± 0.6 mm and 0.3 ± 0.2 mm, and 0.0 ± 0.2° 0.0 ± 0.1° and 0.0 ± 0.2° for translations and rotations along the left-right, superior-inferior and anterior-posterior axes respectively and we also found similar results in measurements with the head phantom. Forced facial motion was associated with lower tracking accuracy. The RtM SGRT system achieved submillimetre accuracy. Conclusion: The RtM SGRT system is a low-cost, easy to build and open-source SGRT system that can achieve an accuracy that meets international commissioning guidelines. Its open-source and modular design allows for the development and easy translation of novel surface tracking techniques.

The first clinical implementation of real-time 6 degree-of-freedom image-guided radiotherapy for liver SABR patients.

PURPOSE: Multiple survey results have identified a demand for improved motion management for liver cancer IGRT. Until now, real-time IGRT for liver has been the domain of dedicated and expensive cancer radiotherapy systems. The purpose of this study was to clinically implement and characterise the performance of a novel real-time 6 degree-of-freedom (DoF) IGRT system, Kilovoltage Intrafraction Monitoring (KIM) for liver SABR patients. METHODS/MATERIALS: The KIM technology segmented gold fiducial markers in intra-fraction x-ray images as a surrogate for the liver tumour and converted the 2D segmented marker positions into a real-time 6DoF tumour position. Fifteen liver SABR patients were recruited and treated with KIM combined with external surrogate guidance at three radiotherapy centres in the TROG 17.03 LARK multi-institutional prospective clinical trial. Patients were either treated in breath-hold or in free breathing using the gating method. The KIM localisation accuracy and dosimetric accuracy achieved with KIM + external surrogate were measured and the results were compared to those with the estimated external surrogate alone. RESULTS: The KIM localisation accuracy was 0.2±0.9 mm (left-right), 0.3±0.6 mm (superior-inferior) and 1.2±0.8 mm (anterior-posterior) for translations and -0.1◦±0.8◦ (left-right), 0.6◦±1.2◦ (superior-inferior) and 0.1◦±0.9◦ (anterior-posterior) for rotations. The cumulative dose to the GTV with KIM + external surrogate was always within 5% of the plan. In 2 out of 15 patients, >5% dose error would have occurred to the GTV and an organ-at-risk with external surrogate alone. CONCLUSIONS: This work demonstrates that real-time 6DoF IGRT for liver can be implemented on standard radiotherapy systems to improve treatment accuracy and safety. The observations made during the treatments highlight the potential false assurance of using traditional external surrogates to assess tumour motion in patients and the need for ongoing improvement of IGRT technologies.

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.

A kinematics-based method for creating deformed patient-derived head and neck CT scans.

CT scans of the head and neck have multiple clinical uses, and simulating deformation of these CT scans allows for predicting patient motion and data augmentation for machine-learning methods. Current methods for creating patient-derived deformed CT scans require multiple scans or use unrealistic head and neck motion. This paper describes the CTHeadDeformation software package which allows for realistic synthetic deformation of head and neck CT scans for small amounts of motion. CTHeadDeformation is a python-based package that uses a kinematics-based approach using anatomical landmarks, and rigid/non-rigid registration to create a realistic patient-derived deformed CT scan. CTHeadDeformation is also designed for simple clinical implementation. The CTHeadDeformation software package was demonstrated on a head and neck CT scan of one patient. The CT scan was deformed in the anterior-posterior, superior-inferior, and left-right directions. Internal organ motion and more complex combination motions were also simulated. The results showed the patient's CT scan was able to be deformed in a way that preserved the shape and location of the anatomy.Clinical Relevance- This method allows for the realistic simulation of head and neck motion in CT scans. Clinical applications including simulating how patient motion affects radiation therapy treatment effectiveness. The CTHeadDeformation software can also be used to train machine-learning networks that are robust to patient motion, or to generate ground truth images for imaging or segmentation grand challenges.

Comparison between [68Ga]Ga-PSMA-617 and [18F]FET PET as Imaging Biomarkers in Adult Recurrent Glioblastoma.

The aim of this prospective clinical study was to evaluate the potential of the prostate specific membrane antigen (PSMA) targeting ligand, [68Ga]-PSMA-Glu-NH-CO-NH-Lys-2-naphthyl-L-Ala-cyclohexane-DOTA ([68Ga]Ga-PSMA-617) as a positron emission tomography (PET) imaging biomarker in recurrent glioblastoma patients. Patients underwent [68Ga]Ga-PSMA-617 and O-(2-[18F]-fluoroethyl)-L-tyrosine ([18F]FET) PET scans on two separate days. [68Ga]Ga-PSMA-617 tumour selectivity was assessed by comparing tumour volume delineation and by assessing the intra-patient correlation between tumour uptake on [68Ga]Ga-PSMA-617 and [18F]FET PET images. [68Ga]Ga-PSMA-617 tumour specificity was evaluated by comparing its tumour-to-brain ratio (TBR) with [18F]FET TBR and its tumour volume with the magnetic resonance imaging (MRI) contrast-enhancing (CE) tumour volume. Ten patients were recruited in this study. [68Ga]Ga-PSMA-617-avid tumour volume was larger than the [18F]FET tumour volume (p = 0.063). There was a positive intra-patient correlation (median Pearson r = 0.51; p < 0.0001) between [68Ga]Ga-PSMA-617 and [18F]FET in the tumour volume. [68Ga]Ga-PSMA-617 had significantly higher TBR (p = 0.002) than [18F]FET. The [68Ga]Ga-PSMA-617-avid tumour volume was larger than the CE tumour volume (p = 0.0039). Overall, accumulation of [68Ga]-Ga-PSMA-617 beyond [18F]FET-avid tumour regions suggests the presence of neoangiogenesis in tumour regions that are not overly metabolically active yet. Higher tumour specificity suggests that [68Ga]-Ga-PSMA-617 could be a better imaging biomarker for recurrent tumour delineation and secondary treatment planning than [18F]FET and CE MRI.

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.

Changes in serial multiparametric MRI and FDG-PET/CT functional imaging during radiation therapy can predict treatment response in patients with head and neck cancer.

OBJECTIVES: To test if tumour changes measured using combination of diffusion-weighted imaging (DWI) MRI and FDG-PET/CT performed serially during radiotherapy (RT) in mucosal head and neck carcinoma can predict treatment response. METHODS: Fifty-five patients from two prospective imaging biomarker studies were analysed. FDG-PET/CT was performed at baseline, during RT (week 3), and post RT (3 months). DWI was performed at baseline, during RT (weeks 2, 3, 5, 6), and post RT (1 and 3 months). The ADCmean from DWI and FDG-PET parameters SUVmax, SUVmean, metabolic tumour volume (MTV), and total lesion glycolysis (TLG) were measured. Absolute and relative change (%∆) in DWI and PET parameters were correlated to 1-year local recurrence. Patients were categorised into favourable, mixed, and unfavourable imaging response using optimal cut-off (OC) values of DWI and FDG-PET parameters and correlated to local control. RESULTS: The 1-year local, regional, and distant recurrence rates were 18.2% (10/55), 7.3% (4/55), and 12.7% (7/55), respectively. ∆Week 3 ADCmean (AUC 0.825, p = 0.003; OC ∆ > 24.4%) and ∆MTV (AUC 0.833, p = 0.001; OC ∆ > 50.4%) were the best predictors of local recurrence. Week 3 was the optimal time point for assessing DWI imaging response. Using a combination of ∆ADCmean and ∆MTV improved the strength of correlation to local recurrence (p ≤ 0.001). In patients who underwent both week 3 MRI and FDG-PET/CT, significant differences in local recurrence rates were seen between patients with favourable (0%), mixed (17%), and unfavourable (78%) combined imaging response. CONCLUSIONS: Changes in mid-treatment DWI and FDG-PET/CT imaging can predict treatment response and could be utilised in the design of future adaptive clinical trials. CLINICAL RELEVANCE STATEMENT: Our study shows the complementary information provided by two functional imaging modalities for mid-treatment response prediction in patients with head and neck cancer. KEY POINTS: •FDG-PET/CT and DWI MRI changes in tumour during radiotherapy in head and neck cancer can predict treatment response. •Combination of FDG-PET/CT and DWI parameters improved correlation to clinical outcome. •Week 3 was the optimal time point for DWI MRI imaging response assessment.

Mid-treatment 18F-FDG PET imaging changes in parotid gland correlates to radiation-induced xerostomia.

BACKGROUND: The aim of this study was to measure functional changes in parotid glands using mid-treatment FDG-PET/CT and correlate early imaging changes to subsequent xerostomia in mucosal head and neck squamous cell carcinoma patients undergoing radiotherapy. MATERIALS AND METHODS: 56 patients from two prospective imaging biomarker studies underwent FDG-PET/CT at baseline and during radiotherapy (week 3). Both parotid glands were volumetrically delineated at each time point. PET parameter SUVmedian were calculated for ipsilateral and contralateral parotid glands. Absolute and relative change (Δ) in SUVmedian were correlated to moderate-severe xerostomia (CTCAE grade ≥ 2) at 6 months. Four predictive models were subsequently created using multivariate logistic regression using clinical and radiotherapy planning parameters. Model performance was calculated using ROC analysis and compared using Akaike information criterion (AIC) RESULTS: 29 patients (51.8%) developed grade ≥ 2 xerostomia. Compared to baseline, there was an increase in SUVmedian at week 3 in ipsilateral (8.4%) and contralateral (5.5%) parotid glands. Increase in ipsilateral parotid Δ SUVmedian (p = 0.04) and contralateral mean parotid dose (p = 0.04) were correlated to xerostomia. The reference 'clinical' model correlated to xerostomia (AUC 0.667, AIC 70.9). Addition of ipsilateral parotid Δ SUVmedian to the clinical model resulted in the highest correlation to xerostomia (AUC 0.777, AIC 65.4). CONCLUSION: Our study shows functional changes occurring in the parotid gland early during radiotherapy. We demonstrate that integration of baseline and mid-treatment FDG-PET/CT changes in the parotid gland with clinical factors has the potential to improve xerostomia risk prediction which could be utilised for personalised head and neck radiotherapy.

A patient-specific deep learning framework for 3D motion estimation and volumetric imaging during lung cancer radiotherapy.

Objective. Respiration introduces a constant source of irregular motion that poses a significant challenge for the precise irradiation of thoracic and abdominal cancers. Current real-time motion management strategies require dedicated systems that are not available in most radiotherapy centers. We sought to develop a system that estimates and visualises the impact of respiratory motion in 3D given the 2D images acquired on a standard linear accelerator.Approach. In this paper we introduceVoxelmap, a patient-specific deep learning framework that achieves 3D motion estimation and volumetric imaging using the data and resources available in standard clinical settings. Here we perform a simulation study of this framework using imaging data from two lung cancer patients.Main results. Using 2D images as input and 3D-3DElastixregistrations as ground-truth,Voxelmapwas able to continuously predict 3D tumor motion with mean errors of 0.1 ± 0.5, -0.6 ± 0.8, and 0.0 ± 0.2 mm along the left-right, superior-inferior, and anterior-posterior axes respectively.Voxelmapalso predicted 3D thoracoabdominal motion with mean errors of -0.1 ± 0.3, -0.1 ± 0.6, and -0.2 ± 0.2 mm respectively. Moreover, volumetric imaging was achieved with mean average error 0.0003, root-mean-squared error 0.0007, structural similarity 1.0 and peak-signal-to-noise ratio 65.8.Significance. The results of this study demonstrate the possibility of achieving 3D motion estimation and volumetric imaging during lung cancer treatments on a standard linear accelerator.

Nano X Image Guidance in radiation therapy: feasibility study protocol for cone beam computed tomography imaging with gravity-induced motion.

BACKGROUND: This paper describes the protocol for the Nano X Image Guidance (Nano X IG) trial, a single-institution, clinical imaging study. The Nano X is a prototype fixed-beam radiotherapy system developed to investigate the feasibility of a low-cost, compact radiotherapy system to increase global access to radiation therapy. This study aims to assess the feasibility of volumetric image guidance with cone beam computed tomography (CBCT) acquired during horizontal patient rotation on the Nano X radiotherapy system. METHODS: In the Nano X IG study, we will determine whether radiotherapy image guidance can be performed with the Nano X radiotherapy system where the patient is horizontally rotated while scan projections are acquired. We will acquire both conventional CBCT scans and Nano X CBCT scans for 30 patients aged 18 and above and receiving radiotherapy for head/neck or upper abdomen cancers. For each patient, a panel of experts will assess the image quality of Nano X CBCT scans against conventional CBCT scans. Each patient will receive two Nano X CBCT scans to determine the image quality reproducibility, the extent and reproducibility of patient motion and assess patient tolerance. DISCUSSION: Fixed-beam radiotherapy systems have the potential to help ease the current shortfall and increase global access to radiotherapy treatment. Advances in image guidance could facilitate fixed-beam radiotherapy using horizontal patient rotation. The efficacy of this radiotherapy approach is dependent on our ability to image and adapt to motion due to rotation and for patients to tolerate rotation during treatment. TRIAL REGISTRATION: ClinicalTrials.gov, NCT04488224. Registered on 27 July 2020.

Impact of tumour region of interest delineation method for mid-treatment FDG-PET response prediction in head and neck squamous cell carcinoma undergoing radiotherapy.

Background: The aim of this study was to evaluate the impact of tumour region of interest (ROI) delineation method on mid-treatment 18F-fluoro-2-deoxy-D-glucose positron emission tomography (FDG-PET) response prediction in mucosal head and neck squamous cell carcinoma during radiotherapy. Methods: A total of 52 patients undergoing definitive radiotherapy with or without systemic therapy from two prospective imaging biomarker studies were analysed. FDG-PET was performed at baseline and during radiotherapy (week 3). Primary tumour was delineated using a fixed SUV 2.5 threshold (MTV2.5), relative threshold (MTV40%) and a gradient based segmentation method (PET Edge). PET parameters SUVmax, SUVmean, metabolic tumour volume (MTV) and total lesion glycolysis (TLG) were calculated using different ROI methods. Absolute and relative change (∆) in PET parameters were correlated to 2-year locoregional recurrence. Strength of correlation was tested using receiver operator characteristic analysis using area under the curve (AUC). Response was categorized using optimal cut-off (OC) values. Correlation and agreement between different ROI methods was determined using Bland-Altman analysis. Results: A significant difference in SUVmean, MTV and TLG values were noted between ROI delineation methods. When measuring relative change at week 3, a greater agreement was seen between PET Edge and MTV2.5 methods with average difference in ∆SUVmax, ∆SUVmean, ∆MTV and ∆TLG of 0.0%, 3.6%, 10.3% and 13.6% respectively. A total of 12 patients (22.2%) experienced locoregional recurrence. ∆MTV using PET Edge was the best predictor of locoregional recurrence (AUC =0.761, 95% CI: 0.573-0.948, P=0.001; OC ∆>50%). The corresponding 2-year locoregional recurrence rate was 7% vs. 35%, P=0.001. Conclusions: Our findings suggest that it is preferable to use gradient based method to assess volumetric tumour response during radiotherapy and offers advantage in predicting treatment outcomes compared with threshold-based methods. This finding requires further validation and can assist in future response-adaptive clinical trials.

Realistic CT data augmentation for accurate deep-learning based segmentation of head and neck tumors in kV images acquired during radiation therapy.

BACKGROUND: Using radiation therapy (RT) to treat head and neck (H&N) cancers requires precise targeting of the tumor to avoid damaging the surrounding healthy organs. Immobilisation masks and planning target volume margins are used to attempt to mitigate patient motion during treatment, however patient motion can still occur. Patient motion during RT can lead to decreased treatment effectiveness and a higher chance of treatment related side effects. Tracking tumor motion would enable motion compensation during RT, leading to more accurate dose delivery. PURPOSE: The purpose of this paper is to develop a method to detect and segment the tumor in kV images acquired during RT. Unlike previous tumor segmentation methods for kV images, in this paper, a process for generating realistic and synthetic CT deformations was developed to augment the training data and make the segmentation method robust to patient motion. Detecting the tumor in 2D kV images is a necessary step toward 3D tracking of the tumor position during treatment. METHOD: In this paper, a conditional generative adversarial network (cGAN) is presented that can detect and segment the gross tumor volume (GTV) in kV images acquired during H&N RT. Retrospective data from 15 H&N cancer patients obtained from the Cancer Imaging Archive were used to train and test patient-specific cGANs. The training data consisted of digitally reconstructed radiographs (DRRs) generated from each patient's planning CT and contoured GTV. Training data was augmented by using synthetically deformed CTs to generate additional DRRs (in total 39 600 DRRs per patient or 25 200 DRRs for nasopharyngeal patients) containing realistic patient motion. The method for deforming the CTs was a novel deformation method based on simulating head rotation and internal tumor motion. The testing dataset consisted of 1080 DRRs for each patient, obtained by deforming the planning CT and GTV at different magnitudes to the training data. The accuracy of the generated segmentations was evaluated by measuring the segmentation centroid error, Dice similarity coefficient (DSC) and mean surface distance (MSD). This paper evaluated the hypothesis that when patient motion occurs, using a cGAN to segment the GTV would create a more accurate segmentation than no-tracking segmentations from the original contoured GTV, the current standard-of-care. This hypothesis was tested using the 1-tailed Mann-Whitney U-test. RESULTS: The magnitude of our cGAN segmentation centroid error was (mean ± standard deviation) 1.1 ± 0.8 mm and the DSC and MSD values were 0.90 ± 0.03 and 1.6 ± 0.5 mm, respectively. Our cGAN segmentation method reduced the segmentation centroid error (p < 0.001), and MSD (p = 0.031) when compared to the no-tracking segmentation, but did not significantly increase the DSC (p = 0.294). CONCLUSIONS: The accuracy of our cGAN segmentation method demonstrates the feasibility of this method for H&N cancer patients during RT. Accurate tumor segmentation of H&N tumors would allow for intrafraction monitoring methods to compensate for tumor motion during treatment, ensuring more accurate dose delivery and enabling better H&N cancer patient outcomes.

Genitourinary Quality-of-Life Comparison Between Urethral Sparing Prostate Stereotactic Body Radiation Therapy Monotherapy and Virtual High-Dose-Rate Brachytherapy Boost.

PURPOSE: Although radiation dose escalation improves prostate cancer disease control, it can cause increased toxicity. Genitourinary (GU) symptoms after prostate radiation therapy affect patient health-related quality of life (QoL). We compared patient-reported GU QoL outcomes following 2 alternative urethral sparing stereotactic body radiation therapy regimens. METHODS AND MATERIALS: Expanded Prostate Cancer Index Composite (EPIC)-26 GU scores were compared between 2 urethral sparing stereotactic body radiation therapy trials. The SPARK trial prescribed a "Monotherapy" dose of 36.25 Gy in 5 fractions to the prostate. The PROMETHEUS trial prescribed 2 phases: a 19- to 21-Gy in 2 fractions "Boost" to the prostate, followed by 46 Gy in 23 fractions or 36 Gy in 12 fractions. The biological effective dose (BED) for urethral toxicity was 123.9 Gy for Monotherapy and 155.8 to 171.2 Gy for Boost. Mixed effects logistic regression models were utilized to estimate the difference in the odds of a minimal clinically important change from baseline EPIC-26 GU score between regimens at each follow-up. RESULTS: 46 Monotherapy and 149 Boost patients completed baseline EPIC-26 scoring. Mean EPIC-26 GU scores revealed statistically superior urinary incontinence outcomes for Monotherapy at 12 months (mean difference, 6.9; 95% confidence interval [CI], 1.6-12.1; P = .01) and 36 months (mean difference, 9.6; 95% CI, 4.1-15.1; P < .01). Monotherapy also revealed superior mean urinary irritative/obstructive outcomes at 12 months (mean difference, 6.9; 95% CI, 2.0-12.9; P < .01) and 36 months (mean difference, 6.3; 95% CI, 1.9-10.8; P < .01). For both domains and at all time points, the absolute differences were <10%. There were no significant differences in the odds of reporting a minimal clinically important change between regimens at any time point. CONCLUSIONS: Even in the presence of urethral sparing, the higher BED delivered in the Boost schedule may have a small adverse effect on GU QoL compared with Monotherapy. However, this did not translate to statistically significant differences in minimal clinically important changes. Whether the higher BED of the boost arm offers an efficacy advantage is being investigated in the Trans Tasman Radiation Oncology Group 18.01 NINJA randomized trial.

Deep learning enables MV-based real-time image guided radiation therapy for prostate cancer patients.

Objective. Using MV images for real-time image guided radiation therapy (IGRT) is ideal as it does not require additional imaging equipment, adds no additional imaging dose and provides motion data in the treatment beam frame of reference. However, accurate tracking using MV images is challenging due to low contrast and modulated fields. Here, a novel real-time marker tracking system based on a convolutional neural network (CNN) classifier was developed and evaluated on retrospectively acquired patient data for MV-based IGRT for prostate cancer patients.Approach. MV images, acquired from 29 volumetric modulated arc therapy (VMAT) prostate cancer patients treated in a multi-institutional clinical trial, were used to train and evaluate a CNN-based marker tracking system. The CNN was trained using labelled MV images from 9 prostate cancer patients (35 fractions) with implanted markers. CNN performance was evaluated on an independent cohort of unseen MV images from 20 patients (78 fractions), using a Precision-Recall curve (PRC), area under the PRC plot (AUC) and sensitivity and specificity. The accuracy of the tracking system was evaluated on the same unseen dataset and quantified by calculating mean absolute (±1 SD) and [1st, 99th] percentiles of the geometric tracking error in treatment beam co-ordinates using manual identification as the ground truth.Main results. The CNN had an AUC of 0.99, sensitivity of 98.31% and specificity of 99.87%. The mean absolute geometric tracking error was 0.30 ± 0.27 and 0.35 ± 0.31 mm in the lateral and superior-inferior directions of the MV images, respectively. The [1st, 99th] percentiles of the error were [-1.03, 0.90] and [-1.12, 1.12] mm in the lateral and SI directions, respectively.Significance. The high classification performance on unseen MV images demonstrates the CNN can successfully identify implanted prostate markers. Furthermore, the sub-millimetre accuracy and precision of the marker tracking system demonstrates potential for adaptation to real-time applications.

BRAVEHeart: a randomised trial comparing the accuracy of Breathe Well and RPM for deep inspiration breath hold breast cancer radiotherapy.

BACKGROUND: Deep inspiration breath hold (DIBH) reduces radiotherapy cardiac dose for left-sided breast cancer patients. The primary aim of the BRAVEHeart (Breast Radiotherapy Audio Visual Enhancement for sparing the Heart) trial is to assess the accuracy and usability of a novel device, Breathe Well, for DIBH guidance for left-sided breast cancer patients. Breathe Well will be compared to an adapted widely available monitoring system, the Real-time Position Management system (RPM). METHODS: BRAVEHeart is a single institution prospective randomised trial of two DIBH devices. BRAVEHeart will assess the DIBH accuracy for Breathe Well and RPM during left-sided breast cancer radiotherapy. After informed consent has been obtained, 40 patients will be randomised into two equal groups, the experimental arm (Breathe Well) and the control arm (RPM with in-house modification of an added patient screen). The primary hypothesis of BRAVEHeart is that the accuracy of Breathe Well in maintaining the position of the chest during DIBH is superior to the RPM system. Accuracy will be measured by comparing chest wall motion extracted from images acquired of the treatment field during breast radiotherapy for patients treated using the Breathe Well system and those using the RPM system. DISCUSSION: The Breathe Well device uses a depth camera to monitor the chest surface while the RPM system monitors a block on the patient's abdomen. The hypothesis of this trial is that the chest surface is a better surrogate for the internal chest wall motion used as a measure of treatment accuracy. The Breathe Well device aims to deliver an easy-to-use implementation of surface monitoring. The findings from the study will help inform the technology choice for other centres performing DIBH. TRIAL REGISTRATION: ClinicalTrials.gov NCT02881203 . Registered on 26 August 2016.

Evaluation of deep learning based implanted fiducial markers tracking in pancreatic cancer patients.

Real-time target position verification during pancreas stereotactic body radiation therapy (SBRT) is important for the detection of unplanned tumour motions. Fast and accurate fiducial marker segmentation is a Requirement of real-time marker-based verification. Deep learning (DL) segmentation techniques are ideal because they don't require additional learning imaging or prior marker information (e.g., shape, orientation). In this study, we evaluated three DL frameworks for marker tracking applied to pancreatic cancer patient data. The DL frameworks evaluated were (1) a convolutional neural network (CNN) classifier with sliding window, (2) a pretrained you-only-look-once (YOLO) version-4 architecture, and (3) a hybrid CNN-YOLO. Intrafraction kV images collected during pancreas SBRT treatments were used as training data (44 fractions, 2017 frames). All patients had 1-4 implanted fiducial markers. Each model was evaluated on unseen kV images (42 fractions, 2517 frames). The ground truth was calculated from manual segmentation and triangulation of markers in orthogonal paired kV/MV images. The sensitivity, specificity, and area under the precision-recall curve (AUC) were calculated. In addition, the mean-absolute-error (MAE), root-mean-square-error (RMSE) and standard-error-of-mean (SEM) were calculated for the centroid of the markers predicted by the models, relative to the ground truth. The sensitivity and specificity of the CNN model were 99.41% and 99.69%, respectively. The AUC was 0.9998. The average precision of the YOLO model for different values of recall was 96.49%. The MAE of the three models in the left-right, superior-inferior, and anterior-posterior directions were under 0.88 ± 0.11 mm, and the RMSE were under 1.09 ± 0.12 mm. The detection times per frame on a GPU were 48.3, 22.9, and 17.1 milliseconds for the CNN, YOLO, and CNN-YOLO, respectively. The results demonstrate submillimeter accuracy of marker position predicted by DL models compared to the ground truth. The marker detection time was fast enough to meet the requirements for real-time application.

Real-time radial reconstruction with domain transform manifold learning for MRI-guided radiotherapy.

BACKGROUND: MRI-guidance techniques that dynamically adapt radiation beams to follow tumor motion in real time will lead to more accurate cancer treatments and reduced collateral healthy tissue damage. The gold-standard for reconstruction of undersampled MR data is compressed sensing (CS) which is computationally slow and limits the rate that images can be available for real-time adaptation. PURPOSE: Once trained, neural networks can be used to accurately reconstruct raw MRI data with minimal latency. Here, we test the suitability of deep-learning-based image reconstruction for real-time tracking applications on MRI-Linacs. METHODS: We use automated transform by manifold approximation (AUTOMAP), a generalized framework that maps raw MR signal to the target image domain, to rapidly reconstruct images from undersampled radial k-space data. The AUTOMAP neural network was trained to reconstruct images from a golden-angle radial acquisition, a benchmark for motion-sensitive imaging, on lung cancer patient data and generic images from ImageNet. Model training was subsequently augmented with motion-encoded k-space data derived from videos in the YouTube-8M dataset to encourage motion robust reconstruction. RESULTS: AUTOMAP models fine-tuned on retrospectively acquired lung cancer patient data reconstructed radial k-space with equivalent accuracy to CS but with much shorter processing times. Validation of motion-trained models with a virtual dynamic lung tumor phantom showed that the generalized motion properties learned from YouTube lead to improved target tracking accuracy. CONCLUSION: AUTOMAP can achieve real-time, accurate reconstruction of radial data. These findings imply that neural-network-based reconstruction is potentially superior to alternative approaches for real-time image guidance applications.

Rapid distortion correction enables accurate magnetic resonance imaging-guided real-time adaptive radiotherapy.

Background and purpose: Magnetic resonance imaging (MRI)-Linac systems combine simultaneous MRI with radiation delivery, allowing treatments to be guided by anatomically detailed, real-time images. However, MRI can be degraded by geometric distortions that cause uncertainty between imaged and actual anatomy. In this work, we develop and integrate a real-time distortion correction method that enables accurate real-time adaptive radiotherapy. Materials and methods: The method was based on the pre-treatment calculation of distortion and the rapid correction of intrafraction images. A motion phantom was set up in an MRI-Linac at isocentre (P0 ), the edge (P 1) and just outside (P 2) the imaging volume. The target was irradiated and tracked during real-time adaptive radiotherapy with and without the distortion correction. The geometric tracking error and latency were derived from the measurements of the beam and target positions in the EPID images. Results: Without distortion correction, the mean geometric tracking error was 1.3 mm at P 1 and 3.1 mm at P 2. When distortion correction was applied, the error was reduced to 1.0 mm at P 1 and 1.1 mm at P 2. The corrected error was similar to an error of 0.9 mm at P0 where the target was unaffected by distortion indicating that this method has accurately accounted for distortion during tracking. The latency was 319 ± 12 ms without distortion correction and 335 ± 34 ms with distortion correction. Conclusions: We have demonstrated a real-time distortion correction method that maintains accurate radiation delivery to the target, even at treatment locations with large distortion.