Evaluation of CBCT scatter correction using deep convolutional neural networks for head and neck adaptive proton therapy

Quantitative use of cone-beam computed tomography in proton therapy: challenges and opportunities

The fundamental goal in radiation therapy (RT) is to simultaneously maximize tumor cell killing and healthy tissue sparing. Reducing uncertainty margins improves normal tissue sparing, but generally requires advanced techniques. Adaptive RT (ART) is a compelling technique that leverages daily imaging and anatomical information to support reduced margins and to optimize plan quality for each treatment fraction. An especially exciting avenue for ART is proton therapy (PT), which aims to combine daily plan re-optimization with the unique advantages provided by protons, including reduced integral dose and near-zero dose deposition distal to the target along the beam direction. A core component for ART is onboard image guidance, and currently two options are available on proton systems, including cone-beam computed tomography (CBCT) and CT-on-rail (CToR) imaging. While CBCT suffers from poorer image quality compared to CToR imaging, CBCT platforms can be more easily integrated with PT systems and thus may support more streamlined adaptive proton therapy (APT). In this review, we present current status of CBCT application to proton therapy dose evaluation and plan adaptation, including progress, challenges and future directions.

Scatter and beam hardening effect corrections in pelvic region cone beam CT images using a convolutional neural network

The aim of this study is to remove scattered photons and beam hardening effect in cone beam CT (CBCT) images and make an image available for treatment planning. To remove scattered photons and beam hardening effect, a convolutional neural network (CNN) was used, and trained with distorted projection data including scattered photons and beam hardening effect and supervised projection data calculated with monochromatic X-rays. The number of training projection data was 17,280 with data augmentation and that of test projection data was 540. The performance of the CNN was investigated in terms of the number of photons in the projection data used in the training of the network. Projection data of pelvic CBCT images (32 cases) were calculated with a Monte Carlo simulation with six different count levels ranging from 0.5 to 3 million counts/pixel. For the evaluation of corrected images, the peak signal-to-noise ratio (PSNR), the structural similarity index measure (SSIM), and the sum of absolute difference (SAD) were used. The results of simulations showed that the CNN could effectively remove scattered photons and beam hardening effect, and the PSNR, the SSIM, and the SAD significantly improved. It was also found that the number of photons in the training projection data was important in correction accuracy. Furthermore, a CNN model trained with projection data with a sufficient number of photons could yield good performance even though a small number of photons were used in the input projection data.

Interfractional body surface monitoring using daily cone-beam computed tomography imaging for pediatric adaptive proton therapy

Background and purpose

A novel method was developed to detect body surface changes on daily cone-beam computed tomography (CBCT) and estimate the impact on proton plan quality for pediatric patients.

Materials and methods

Simulation CT, daily CBCT, and repeat CT images were collected for 21 pediatric non-central nervous system (CNS) patients. Changes in the body surface in the proton beam path (ΔSurfaceCBCT) were calculated for each spot by comparing simulation CT with daily CBCT. Subsequently, changes in water equivalent path length (WEPL) (ΔWEPLSynthetic CT) were calculated for each spot by comparing the simulation CT with the synthetic CT converted from daily CBCT. The ground truth surface (ΔSurfaceRepeat CT) and WEPL changes (ΔWEPLRepeat CT) were calculated by comparing the simulation CT with the repeat CT taken on the same day as the CBCT.

Results

The root-mean-square (RMS) error between the ΔSurfaceCBCT and ΔSurfaceRepeat CT was 1.3 mm, while the RMS error between ΔWEPLSynthetic CT and ΔWEPLRepeat CT was 1.6 mm. A strong linear correlation was determined between ΔSurfaceCBCT and ΔWEPLSynthetic CT (R2 = 0.97). The non-linear regression analysis of the dose volume parameters indicated that a 5 % decrease in clinical target volume (CTV) Dmin and D99% was caused by 3.9 mm and 6.3 mm of ΔSurfaceCBCT, and 4.0 mm and 6.6 mm of ΔWEPLSynthetic CT, respectively.

Conclusions

The findings revealed that a 5 mm change in body surface can lead to a significant degradation of plan quality, reducing CTV Dmin by 11.7 % and underscoring the need for adapting treatment plan.

Multi-institution investigations of online daily adaptive proton strategies for head and neck cancer patients

Objective.Fast computation of daily reoptimization is key for an efficient online adaptive proton therapy workflow. Various approaches aim to expedite this process, often compromising daily dose. This study compares Massachusetts General Hospital's (MGH's) online dose reoptimization approach, Paul Scherrer Institute's (PSI's) online replanning workflow and a full reoptimization adaptive workflow for head and neck cancer (H&N) patients.Approach.Ten H&N patients (PSI:5, MGH:5) with daily cone beam computed tomographys (CBCTs) were included. Synthetic CTs were created by deforming the planning CT to each CBCT. Targets and organs at risk (OARs) were deformed on daily images. Three adaptive approaches were investigated: (i) an online dose reoptimization approach modifying the fluence of a subset of beamlets, (ii) full reoptimization adaptive workflow modifying the fluence of all beamlets, and (iii) a full online replanning approach, allowing the optimizer to modify both fluence and position of all beamlets. Two non-adapted (NA) scenarios were simulated by recalculating the original plan on the daily image using: Monte Carlo for NAMGHand raycasting algorithm for NAPSI.Main results.All adaptive scenarios from both institutions achieved the prescribed daily target dose, with further improvements from online replanning. For all patients, low-dose CTV D98%shows mean daily deviations of -2.2%, -1.1%, and 0.4% for workflows (i), (ii), and (iii), respectively. For the online adaptive scenarios, plan optimization averages 2.2 min for (iii) and 2.4 for (i) while the full dose reoptimization requires 72 min. The OAMGH20%dose reoptimization approach produced results comparable to online replanning for most patients and fractions. However, for one patient, differences up to 11% in low-dose CTV D98%occurred.Significance.Despite significant anatomical changes, all three adaptive approaches ensure target coverage without compromising OAR sparing. Our data suggests 20% dose reoptimization suffices, for most cases, yielding comparable results to online replanning with a marginal time increase due to Monte Carlo. For optimal daily adaptation, a rapid online replanning is preferable.

Artificial intelligence for treatment delivery: image-guided radiotherapy

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

A dual-domain network with division residual connection and feature fusion for CBCT scatter correction

Objective.This study aims to propose a dual-domain network that not only reduces scatter artifacts but also retains structure details in cone-beam computed tomography (CBCT).Approach.The proposed network comprises a projection-domain sub-network and an image-domain sub-network. The projection-domain sub-network utilizes a division residual network to amplify the difference between scatter signals and imaging signals, facilitating the learning of scatter signals. The image-domain sub-network contains dual encoders and a single decoder. The dual encoders extract features from two inputs parallelly, and the decoder fuses the extracted features from the two encoders and maps the fused features back to the final high-quality image. Of the two input images to the image-domain sub-network, one is the scatter-contaminated image analytically reconstructed from the scatter-contaminated projections, and the other is the pre-processed image reconstructed from the pre-processed projections produced by the projection-domain sub-network.Main results.Experimental results on both synthetic and real data demonstrate that our method can effectively reduce scatter artifacts and restore image details. Quantitative analysis using synthetic data shows the mean absolute error was reduced by 74% and peak signal-to-noise ratio increased by 57% compared to the scatter-contaminated ones. Testing on real data found a 38% increase in contrast-to-noise ratio with our method compared to the scatter-contaminated image. Additionally, our method consistently outperforms comparative methods such as U-Net, DSE-Net, deep residual convolution neural network (DRCNN) and the collimator-based method.Significance.A dual-domain network that leverages projection-domain division residual connection and image-domain feature fusion has been proposed for CBCT scatter correction. It has potential applications for reducing scatter artifacts and preserving image details in CBCT.

Investigation of 2D anti-scatter grid implementation in a gantry-mounted cone beam computed tomography system for proton therapy

Background and purpose

Robust scatter mitigation by 2D anti-scatter grids (2D-ASG) in proton therapy cone beam computed tomography (CBCT) may improve target visualization and computed tomography (CT) number fidelity, allowing online dose verifications and plan adaptations. However, grid artifact-free implementation of 2D-ASG depends on the CBCT system characteristics. Thus, we investigated the feasibility of 2D-ASG implementation in a proton therapy gantry-mounted CBCT system and evaluated its impact on image quality.

Materials and methods

A prototype 2D-ASG and a grid support platform were developed for a proton therapy CBCT system with a 340 cm source to imager distance. The effect of gantry flex on 2D-ASG's wall shadows and scan-to-scan reproducibility of 2D-ASG's wall shadows were evaluated. Experiments were conducted to assess 2D-ASG's wall shadow suppression and the effect of 2D-ASG on image quality.

Results

While maximum displacement in 2D-ASG wall shadows was 103 µm during gantry rotation, the drift from baseline over 3 months was 8 µm and 1 µm in the transverse and axial directions. 2D-ASG shadows were successfully suppressed in CBCT images. With 2D-ASG, maximum Hounsfield Unit (HU) nonuniformity decreased from 134 to 45 HU, contrast-to-noise ratio (CNR) increased by a factor of 2.5, and HU errors were reduced from 34 % to 5 %.

Conclusions

Proton therapy gantry flex was highly reproducible and did not noticeably affect 2D-ASG wall shadow suppression in CBCT images, supporting its feasibility in proton therapy CBCT system. Improved CT accuracy and artifact reduction with 2D-ASG could enhance CBCT-based proton therapy dose calculations.

Cone Beam Computed Tomography Image-Quality Improvement Using "One-Shot" Super-resolution

Cone beam computed tomography (CBCT) images are convenient representations for obtaining information about patients' internal organs, but their lower image quality than those of treatment planning CT images constitutes an important shortcoming. Several proposed CBCT image-quality improvement methods based on deep learning require large amounts of training data. Our newly developed model using a super-resolution method, "one-shot" super-resolution (OSSR) based on the "zero-shot" super-resolution method, requires only small amounts of training data to improve CBCT image quality using only the target CBCT image and the paired treatment planning CT image. For this study, pelvic CBCT images and treatment planning CT images of 30 prostate cancer patients were used. We calculated the root mean squared error (RMSE), peak signal-to-noise ratio (PSNR), and structural similarity (SSIM) to evaluate image-quality improvement and normalized mutual information (NMI) as a quantitative evaluation of positional accuracy. Our proposed method can improve CBCT image quality without requiring large amounts of training data. After applying our proposed method, the resulting RMSE, PSNR, SSIM, and NMI between the CBCT images and the treatment planning CT images were as much as 0.86, 1.05, 1.03, and 1.31 times better than those obtained without using our proposed method. By comparison, CycleGAN exhibited values of 0.91, 1.03, 1.02, and 1.16. The proposed method achieved performance equivalent to that of CycleGAN, which requires images from approximately 30 patients for training. Findings demonstrated improvement of CBCT image quality using only the target CBCT images and the paired treatment planning CT images.

The emerging role of Artificial Intelligence in proton therapy: A review

Artificial intelligence (AI) has made a tremendous impact in the space of healthcare, and proton therapy is not an exception. Proton therapy has witnessed growing popularity in oncology over recent decades, and researchers are increasingly looking to develop AI and machine learning tools to aid in various steps of the treatment planning and delivery processes. This review delves into the emergent role of AI in proton therapy, evaluating its development, advantages, intended clinical contexts, and areas of application. Through the analysis of 76 studies, we aim to underscore the importance of AI applications in advancing proton therapy and to highlight their prospective influence on clinical practices.

Evaluation of a compact cone beam CT concept with high image fidelity for point-of-care brain imaging

Cone beam computed tomography (CBCT) has potential advantages for developing portable, cost-effective point-of-care CT systems for intracranial imaging, such as early stroke diagnosis, hemorrhage detection, and intraoperative navigation. However, large volume imaging with flat panel detector based CBCT significantly increases the scattered radiation fluence which reduces its image quality and utility. To address these issues, a compact CBCT concept with enhanced image quality was investigated for intracranial imaging. The new system features a novel antiscatter collimator and data correction method to address the challenges in imaging large volumes with CBCT. A benchtop CBCT prototype was constructed. Imaging studies with anthropomorphic phantoms showed that soft tissue visualization, Hounsfield Unit (HU) accuracy, contrast, and spatial resolution increased significantly with the proposed CBCT concept, and they were comparable to the values measured in the gold standard multidetector-row CT (MDCT) images. Contrast-to-noise ratio (CNR) in CBCT images was within 12-31% of the CNR in MDCT images. These findings indicate that a compact CBCT system integrated with effective scatter suppression techniques may have increased utility in the context of brain imaging, and the proposed approach may enable the development of point-of-care CT systems for head imaging based on flat panel detector based CBCT technology.

Monte Carlo methods for medical imaging research

In radiation-based medical imaging research, computational modeling methods are used to design and validate imaging systems and post-processing algorithms. Monte Carlo methods are widely used for the computational modeling as they can model the systems accurately and intuitively by sampling interactions between particles and imaging subject with known probability distributions. This article reviews the physics behind Monte Carlo methods, their applications in medical imaging, and available MC codes for medical imaging research. Additionally, potential research areas related to Monte Carlo for medical imaging are discussed.

Scatter estimation and correction using time-of-flight and deconvolution in x-ray medical imaging

Objective.Time-of-flight (TOF) scatter rejection requires a total timing jitter, including the detector timing jitter and the x-ray source's pulses width, of 50 ps or less to mitigate most of the effects of scattered photons in radiography and CT imaging. However, since the total contribution of the source and detector to the timing jitter can be retrieved during an acquisition with nothing between the source and detector, it can be demonstrated that this contribution may be partially removed to improve the image quality.Approach.A scatter correction method using iterative deconvolution of the measured time point-spread function estimates the number of scattered photons detected in each pixel. To evaluate the quality of the estimation, GATE was used to simulate the radiography of a water cylinder with bone inserts, and a head and torso in a system with total timing jitters from 100 ps up to 500 ps full-width-at-half-maximum (FWHM).Main results.With a total timing jitter of 200 ps FWHM, 89% of the contrast degradation caused by scattered photons was recovered in a head and torso radiography, compared to 28% with a simple time threshold method. Corrected images using the estimation have a percent root-mean square error between 2% and 14% in both phantoms with timing jitters from 100 to 500 ps FWHM which is lower than the error achieved with scatter rejection alone at 100 ps FWHM.Significance.TOF x-ray imaging has the potential to mitigate the effects of the scattering contribution and offers an alternative to anti-scatter grids that avoids loss of primary photons. Compare to simple TOF scatter rejection using only a threshold, the deconvolution estimation approach has lower requirements on both the source and detector. These requirements are now within reach of state-of-the-art systems.

An operator-independent quality assurance system for automatically generated structure sets

Objective. This study describes geometry-based and intensity-based tools for quality assurance (QA) of automatically generated structures for online adaptive radiotherapy, and designs an operator-independent traffic light system that identifies erroneous structure sets.Approach.A cohort of eight head and neck (HN) patients with daily CBCTs was selected for test development. Radiotherapy contours were propagated from planning computed tomography (CT) to daily cone beam CT (CBCT) using deformable image registration. These propagated structures were visually verified for acceptability. For each CBCT, several error scenarios were used to generate what were judged unacceptable structures. Ten additional HN patients with daily CBCTs and different error scenarios were selected for validation. A suite of tests based on image intensity, intensity gradient, and structure geometry was developed using acceptable and unacceptable HN planning structures. Combinations of one test applied to one structure, referred to as structure-test combinations, were selected for inclusion in the QA system based on their discriminatory power. A traffic light system was used to aggregate the structure-test combinations, and the system was evaluated on all fractions of the ten validation HN patients.Results.The QA system distinguished between acceptable and unacceptable fractions with high accuracy, labeling 294/324 acceptable fractions as green or yellow and 19/20 unacceptable fractions as yellow or red.Significance.This study demonstrates a system to supplement manual review of radiotherapy planning structures. Automated QA is performed by aggregating results from multiple intensity- and geometry-based tests.

A retrospective study on the investigation of potential dosimetric benefits of online adaptive proton therapy for head and neck cancer

PURPOSE

Proton therapy is sensitive to anatomical changes, often occurring in head-and-neck (HN) cancer patients. Although multiple studies have proposed online adaptive proton therapy (APT), there is still a concern in the radiotherapy community about the necessity of online APT. We have performed a retrospective study to investigate the potential dosimetric benefits of online APT for HN patients relative to the current offline APT.

METHODS

Our retrospective study has a patient cohort of 10 cases. To mimic online APT, we re-evaluated the dose of the in-use treatment plan on patients' actual treatment anatomy captured by cone-beam CT (CBCT) for each fraction and performed a templated-based automatic replanning if needed, assuming that these were performed online before treatment delivery. Cumulative dose of the simulated online APT course was calculated and compared with that of the actual offline APT course and the designed plan dose of the initial treatment plan (referred to as nominal plan). The ProKnow scoring system was employed and adapted for our study to quantify the actual quality of both courses against our planning goals.

RESULTS

The average score of the nominal plans over the 10 cases is 41.0, while those of the actual offline APT course and our simulated online course is 25.8 and 37.5, respectively. Compared to the offline APT course, our online course improved dose quality for all cases, with the score improvement ranging from 0.4 to 26.9 and an average improvement of 11.7.

CONCLUSION

The results of our retrospective study have demonstrated that online APT can better address anatomical changes for HN cancer patients than the current offline replanning practice. The advanced artificial intelligence based automatic replanning technology presents a promising avenue for extending potential benefits of online APT.

A fast and robust constraint-based online re-optimization approach for automated online adaptive intensity modulated proton therapy in head and neck cancer

Objective. In head-and-neck cancer intensity modulated proton therapy, adaptive radiotherapy is currently restricted to offline re-planning, mitigating the effect of slow changes in patient anatomies. Daily online adaptations can potentially improve dosimetry. Here, a new, fully automated online re-optimization strategy is presented. In a retrospective study, this online re-optimization approach was compared to our trigger-based offline re-planning (offlineTBre-planning) schedule, including extensive robustness analyses.Approach. The online re-optimization method employs automated multi-criterial re-optimization, using robust optimization with 1 mm setup-robustness settings (in contrast to 3 mm for offlineTBre-planning). Hard planning constraints and spot addition are used to enforce adequate target coverage, avoid prohibitively large maximum doses and minimize organ-at-risk doses. For 67 repeat-CTs from 15 patients, fraction doses of the two strategies were compared for the CTVs and organs-at-risk. Per repeat-CT, 10.000 fractions with different setup and range robustness settings were simulated using polynomial chaos expansion for fast and accurate dose calculations.Main results. For 14/67 repeat-CTs, offlineTBre-planning resulted in <50% probability ofD98%≥ 95% of the prescribed dose (Dpres) in one or both CTVs, which never happened with online re-optimization. With offlineTBre-planning, eight repeat-CTs had zero probability of obtainingD98%≥ 95%Dpresfor CTV7000, while the minimum probability with online re-optimization was 81%. Risks of xerostomia and dysphagia grade ≥ II were reduced by 3.5 ± 1.7 and 3.9 ± 2.8 percentage point [mean ± SD] (p< 10-5for both). In online re-optimization, adjustment of spot configuration followed by spot-intensity re-optimization took 3.4 min on average.Significance. The fast online re-optimization strategy always prevented substantial losses of target coverage caused by day-to-day anatomical variations, as opposed to the clinical trigger-based offline re-planning schedule. On top of this, online re-optimization could be performed with smaller setup robustness settings, contributing to improved organs-at-risk sparing.

Synthetic CT imaging for PET monitoring in proton therapy: a simulation study

Objective.This study addresses a fundamental limitation of in-beam positron emission tomography (IB-PET) in proton therapy: the lack of direct anatomical representation in the images it produces. We aim to overcome this shortcoming by pioneering the application of deep learning techniques to create synthetic control CT images (sCT) from combining IB-PET and planning CT scan data.Approach.We conducted simulations involving six patients who underwent irradiation with proton beams. Leveraging the architecture of a visual transformer (ViT) neural network, we developed a model to generate sCT images of these patients using the planning CT scans and the inter-fractional simulated PET activity maps during irradiation. To evaluate the model's performance, a comparison was conducted between the sCT images produced by the ViT model and the authentic control CT images-serving as the benchmark.Main results.The structural similarity index was computed at a mean value across all patients of 0.91, while the mean absolute error measured 22 Hounsfield Units (HU). Root mean squared error and peak signal-to-noise ratio values were 56 HU and 30 dB, respectively. The Dice similarity coefficient exhibited a value of 0.98. These values are comparable to or exceed those found in the literature. More than 70% of the synthetic morphological changes were found to be geometrically compatible with the ones reported in the real control CT scan.Significance.Our study presents an innovative approach to surface the hidden anatomical information of IB-PET in proton therapy. Our ViT-based model successfully generates sCT images from inter-fractional PET data and planning CT scans. Our model's performance stands on par with existing models relying on input from cone beam CT or magnetic resonance imaging, which contain more anatomical information than activity maps.

UBES: Unified scatter correction using ultrafast Boltzmann equation solver for conebeam CT

A semi-analytical solution to the unified Boltzmann equation is constructed to exactly describe the scatter distribution on a flat-panel detector for high-quality conebeam CT (CBCT) imaging. The solver consists of three parts, including the phase space distribution estimator, the effective source constructor and the detector signal extractor. Instead of the tedious Monte Carlo solution, the derived Boltzmann equation solver achieves ultrafast computational capability for scatter signal estimation by combining direct analytical derivation and time-efficient one-dimensional numerical integration over the trajectory along each momentum of the photon phase space distribution. The execution of scatter estimation using the proposed ultrafast Boltzmann equation solver (UBES) for a single projection is finalized in around 0.4 seconds. We compare the performance of the proposed method with the state-of-the-art schemes, including a time-expensive Monte Carlo (MC) method and a conventional kernel-based algorithm using the same dataset, which is acquired from the CBCT scans of a head phantom and an abdominal patient. The evaluation results demonstrate that the proposed UBES method achieves comparable correction accuracy compared with the MC method, while exhibits significant improvements in image quality over learning and kernel-based methods. With the advantages of MC equivalent quality and superfast computational efficiency, the UBES method has the potential to become a standard solution to scatter correction in high-quality CBCT reconstruction.

Cone beam CT-based adaptive intensity modulated proton therapy assessment using automated planning for head-and-neck cancer

BACKGROUND

To assess the feasibility of CBCT-based adaptive intensity modulated proton therapy (IMPT) using automated planning for treatment of head and neck (HN) cancers.

METHODS

Twenty HN cancer patients who received radiotherapy and had pretreatment CBCTs were included in this study. Initial IMPT plans were created using automated planning software for all patients. Synthetic CTs (sCT) were then created by deforming the planning CT (pCT) to the pretreatment CBCTs. To assess dose calculation accuracy on sCTs, repeat CTs (rCTs) were deformed to the pretreatment CBCT obtained on the same day to create deformed rCT (rCTdef), serving as gold standard. The dose recalculated on sCT and on rCTdef were compared by using Gamma analysis. The accuracy of DIR generated contours was also assessed. To explore the potential benefits of adaptive IMPT, two sets of plans were created for each patient, a non-adapted IMPT plan and an adapted IMPT plan calculated on weekly sCT images. The weekly doses for non-adaptive and adaptive IMPT plans were accumulated on the pCT, and the accumulated dosimetric parameters of two sets were compared.

RESULTS

Gamma analysis of the dose recalculated on sCT and rCTdef resulted in a passing rate of 97.9% ± 1.7% using 3 mm/3% criteria. With the physician-corrected contours on the sCT, the dose deviation range of using sCT to estimate mean dose for the most organ at risk (OARs) can be reduced to (- 2.37%, 2.19%) as compared to rCTdef, while for V95 of primary or secondary CTVs, the deviation can be controlled within (- 1.09%, 0.29%). Comparison of the accumulated doses from the adaptive planning against the non-adaptive plans reduced mean dose to constrictors (- 1.42 Gy ± 2.79 Gy) and larynx (- 2.58 Gy ± 3.09 Gy). The reductions result in statistically significant reductions in the normal tissue complication probability (NTCP) of larynx edema by 7.52% ± 13.59%. 4.5% of primary CTVs, 4.1% of secondary CTVs, and 26.8% tertiary CTVs didn't meet the V95 > 95% constraint on non-adapted IMPT plans. All adaptive plans were able to meet the coverage constraint.

CONCLUSION

sCTs can be a useful tool for accurate proton dose calculation. Adaptive IMPT resulted in better CTV coverage, OAR sparing and lower NTCP for some OARs as compared with non-adaptive IMPT.

"Under the hood": artificial intelligence in personalized radiotherapy

This review presents and discusses the ways in which artificial intelligence (AI) tools currently intervene, or could potentially intervene in the future, to enhance the diverse tasks involved in the radiotherapy workflow. The radiotherapy framework is presented on 2 different levels for the personalization of the treatment, distinct in tasks and methodologies. The first level is the clinically well-established anatomy-based workflow, known as adaptive radiation therapy. The second level is referred to as biology-driven workflow, explored in the research literature and recently appearing in some preliminary clinical trials for personalized radiation treatments. A 2-fold role for AI is defined according to these 2 different levels. In the anatomy-based workflow, the role of AI is to streamline and improve the tasks in terms of time and variability reductions compared to conventional methodologies. The biology-driven workflow instead fully relies on AI, which introduces decision-making tools opening uncharted frontiers that were in the past deemed challenging to explore. These methodologies are referred to as radiomics and dosiomics, handling imaging and dosimetric information, or multiomics, when complemented by clinical and biological parameters (ie, biomarkers). The review explicitly highlights the methodologies that are currently incorporated into clinical practice or still in research, with the aim of presenting the AI's growing role in personalized radiotherapy.

Artificial intelligence applied to image-guided radiation therapy (IGRT): a systematic review by the Young Group of the Italian Association of Radiotherapy and Clinical Oncology (yAIRO)

INTRODUCTION

The advent of image-guided radiation therapy (IGRT) has recently changed the workflow of radiation treatments by ensuring highly collimated treatments. Artificial intelligence (AI) and radiomics are tools that have shown promising results for diagnosis, treatment optimization and outcome prediction. This review aims to assess the impact of AI and radiomics on modern IGRT modalities in RT.

METHODS

A PubMed/MEDLINE and Embase systematic review was conducted to investigate the impact of radiomics and AI to modern IGRT modalities. The search strategy was "Radiomics" AND "Cone Beam Computed Tomography"; "Radiomics" AND "Magnetic Resonance guided Radiotherapy"; "Radiomics" AND "on board Magnetic Resonance Radiotherapy"; "Artificial Intelligence" AND "Cone Beam Computed Tomography"; "Artificial Intelligence" AND "Magnetic Resonance guided Radiotherapy"; "Artificial Intelligence" AND "on board Magnetic Resonance Radiotherapy" and only original articles up to 01.11.2022 were considered.

RESULTS

A total of 402 studies were obtained using the previously mentioned search strategy on PubMed and Embase. The analysis was performed on a total of 84 papers obtained following the complete selection process. Radiomics application to IGRT was analyzed in 23 papers, while a total 61 papers were focused on the impact of AI on IGRT techniques.

DISCUSSION

AI and radiomics seem to significantly impact IGRT in all the phases of RT workflow, even if the evidence in the literature is based on retrospective data. Further studies are needed to confirm these tools' potential and provide a stronger correlation with clinical outcomes and gold-standard treatment strategies.

Deep learning enables time-efficient soft tissue enhancement in CBCT: Proof-of-concept study for dentomaxillofacial applications

PURPOSE

The use of iterative and deep learning reconstruction methods, which would allow effective noise reduction, is limited in cone-beam computed tomography (CBCT). As a consequence, the visibility of soft tissues is limited with CBCT. The study aimed to improve this issue through time-efficient deep learning enhancement (DLE) methods.

METHODS

Two DLE networks, UNIT and U-Net, were trained with simulated CBCT data. The performance of the networks was tested with three different test data sets. The quantitative evaluation measured the structural similarity index measure (SSIM) and the peak signal-to-noise ratio (PSNR) of the DLE reconstructions with respect to the ground truth iterative reconstruction method. In the second assessment, a dentomaxillofacial radiologist assessed the resolution of hard tissue structures, visibility of soft tissues, and overall image quality of real patient data using the Likert scale. Finally, the technical image quality was determined using modulation transfer function, noise power spectrum, and noise magnitude analyses.

RESULTS

The study demonstrated that deep learning CBCT denoising is feasible and time efficient. The DLE methods, trained with simulated CBCT data, generalized well, and DLE provided quantitatively (SSIM/PSNR) and visually similar noise-reduction as conventional IR, but with faster processing time. The DLE methods improved soft tissue visibility compared to the conventional Feldkamp-Davis-Kress (FDK) algorithm through noise reduction. However, in hard tissue quantification tasks, the radiologist preferred the FDK over the DLE methods.

CONCLUSION

Post-reconstruction DLE allowed feasible reconstruction times while yielding improvements in soft tissue visibility in each dataset.

Review and recommendations on deformable image registration uncertainties for radiotherapy applications

Deformable image registration (DIR) is a versatile tool used in many applications in radiotherapy (RT). DIR algorithms have been implemented in many commercial treatment planning systems providing accessible and easy-to-use solutions. However, the geometric uncertainty of DIR can be large and difficult to quantify, resulting in barriers to clinical practice. Currently, there is no agreement in the RT community on how to quantify these uncertainties and determine thresholds that distinguish a good DIR result from a poor one. This review summarises the current literature on sources of DIR uncertainties and their impact on RT applications. Recommendations are provided on how to handle these uncertainties for patient-specific use, commissioning, and research. Recommendations are also provided for developers and vendors to help users to understand DIR uncertainties and make the application of DIR in RT safer and more reliable.

Deep learning framework to improve the quality of cone-beam computed tomography for radiotherapy scenarios

BACKGROUND

The application of cone-beam computed tomography (CBCT) in image-guided radiotherapy and adaptive radiotherapy remains limited due to its poor image quality.

PURPOSE

In this study, we aim to develop a deep learning framework to generate high-quality CBCT images for therapeutic applications.

METHODS

The synthetic CT (sCT) generation from the CBCT was proposed using a transformer-based network with a hybrid loss function. The network was trained and validated using the data from 176 patients to produce a general model that can be extensively applied to enhance CBCT images. After the first therapy, each patient can receive paired CBCT/planning CT (pCT) scans, and the obtained data were used to fine-tune the general model for further improvement. For subsequent treatment, a patient-specific, personalized model was made available. In total, 34 patients were examined for general model testing, and another six patients who underwent rescanned pCT scan were used for personalized model training and testing.

RESULTS

The general model decreased the mean absolute error (MAE) from 135 HU to 59 HU as compared to the CBCT. The hybrid loss function demonstrated superior performance in CT number correction and noise/artifacts reduction. The proposed transformer-based network also showed superior power in CT number correction compared to the classical convolutional neural network. The personalized model showed improvement based on the general model in some details, and the MAE was reduced from 59 HU (for the general model) to 57 HU (p < 0.05 Wilcoxon signed-rank test).

CONCLUSION

We established a deep learning framework based on transformer for clinical needs. The deep learning model demonstrated potential for continuous improvement with the help of a suggested personalized training strategy compatible with the clinical workflow.

CBCT-to-CT Synthesis for Cervical Cancer Adaptive Radiotherapy via U-Net-Based Model Hierarchically Trained with Hybrid Dataset

PURPOSE

To develop a deep learning framework based on a hybrid dataset to enhance the quality of CBCT images and obtain accurate HU values.

MATERIALS AND METHODS

A total of 228 cervical cancer patients treated in different LINACs were enrolled. We developed an encoder-decoder architecture with residual learning and skip connections. The model was hierarchically trained and validated on 5279 paired CBCT/planning CT images and tested on 1302 paired images. The mean absolute error (MAE), peak signal to noise ratio (PSNR), and structural similarity index (SSIM) were utilized to access the quality of the synthetic CT images generated by our model.

RESULTS

The MAE between synthetic CT images generated by our model and planning CT was 10.93 HU, compared to 50.02 HU for the CBCT images. The PSNR increased from 27.79 dB to 33.91 dB, and the SSIM increased from 0.76 to 0.90. Compared with synthetic CT images generated by the convolution neural networks with residual blocks, our model had superior performance both in qualitative and quantitative aspects.

CONCLUSIONS

Our model could synthesize CT images with enhanced image quality and accurate HU values. The synthetic CT images preserved the edges of tissues well, which is important for downstream tasks in adaptive radiotherapy.

Virtual cone-beam computed tomography simulator with human phantom library and its application to the elemental material decomposition

PURPOSE

The purpose of this study is to develop a virtual CBCT simulator with a head and neck (HN) human phantom library and to demonstrate the feasibility of elemental material decomposition (EMD) for quantitative CBCT imaging using this virtual simulator.

METHODS

The library of 36 HN human phantoms were developed by extending the ICRP 110 adult phantoms based on human age, height, and weight statistics. To create the CBCT database for the library, a virtual CBCT simulator that simulated the direct and scattered X-ray on a flat panel detector using ray-tracing and deep-learning (DL) models was used. Gaussian distributed noise was also included on the flat panel detector, which was evaluated using a real CBCT system. The usefulness of the virtual CBCT system was demonstrated through the application of the developed DL-based EMD model for case involving virtual phantom and real patient.

RESULTS

The virtual simulator could generate various virtual CBCT images based on the human phantom library, and the prediction of the EMD could be successfully performed by preparing the CBCT database from the proposed virtual system, even for a real patient. The CBCT image degradation owing to the scattered X-ray and the statistical noise affected the prediction accuracy, although these effects were minimal. Furthermore, the elemental distribution using the real CBCT image was also predictable.

CONCLUSIONS

This study demonstrated the potential of using computer vision for medical data preparation and analysis, which could have important implications for improving patient outcomes, especially in adaptive radiation therapy.

Image-based scatter correction for cone-beam CT using flip swin transformer U-shape network

BACKGROUND

Cone beam computed tomography (CBCT) plays an increasingly important role in image-guided radiation therapy. However, the image quality of CBCT is severely degraded by excessive scatter contamination, especially in the abdominal region, hindering its further applications in radiation therapy.

PURPOSE

To restore low-quality CBCT images contaminated by scatter signals, a scatter correction algorithm combining the advantages of convolutional neural networks (CNN) and Swin Transformer is proposed.

METHODS

In this paper a scatter correction model for CBCT image, the Flip Swin Transformer U-shape network (FSTUNet) model, is proposed. In this model, the advantages of CNN in texture detail and Swin Transformer in global correlation are used to accurately extract shallow and deep features, respectively. Instead of using the original Swin Transformer tandem structure, we build the Flip Swin Transformer Block to achieve a more powerful inter-window association extraction. The validity and clinical relevance of the method is demonstrated through extensive experiments on a Monte Carlo (MC) simulation dataset and frequency split dataset generated by a validated method, respectively.

RESULT

Experimental results on the MC simulated dataset show that the root mean square error of images corrected by the method is reduced from over 100 HU to about 7 HU. Both the structural similarity index measure (SSIM) and the universal quality index (UQI) are close to 1. Experimental results on the frequency split dataset demonstrate that the method not only corrects shading artifacts but also exhibits a high degree of structural consistency. In addition, comparison experiments show that FSTUNet outperforms UNet, Deep Residual Convolutional Neural Network (DRCNN), DSENet, Pix2pixGAN, and 3DUnet methods in both qualitative and quantitative metrics.

CONCLUSIONS

Accurately capturing the features at different levels is greatly beneficial for reconstructing high-quality scatter-free images. The proposed FSTUNet method is an effective solution to CBCT scatter correction and has the potential to improve the accuracy of CBCT image-guided radiation therapy.

Enhancing Radiotherapy Workflow for Head and Neck Cancer with Artificial Intelligence: A Systematic Review

BACKGROUND

Head and neck cancer (HNC) is characterized by complex-shaped tumors and numerous organs at risk (OARs), inducing challenging radiotherapy (RT) planning, optimization, and delivery. In this review, we provided a thorough description of the applications of artificial intelligence (AI) tools in the HNC RT process.

METHODS

The PubMed database was queried, and a total of 168 articles (2016-2022) were screened by a group of experts in radiation oncology. The group selected 62 articles, which were subdivided into three categories, representing the whole RT workflow: (i) target and OAR contouring, (ii) planning, and (iii) delivery.

RESULTS

The majority of the selected studies focused on the OARs segmentation process. Overall, the performance of AI models was evaluated using standard metrics, while limited research was found on how the introduction of AI could impact clinical outcomes. Additionally, papers usually lacked information about the confidence level associated with the predictions made by the AI models.

CONCLUSIONS

AI represents a promising tool to automate the RT workflow for the complex field of HNC treatment. To ensure that the development of AI technologies in RT is effectively aligned with clinical needs, we suggest conducting future studies within interdisciplinary groups, including clinicians and computer scientists.

Evaluating the effect of setup uncertainty reduction and adaptation to geometric changes on normal tissue complication probability using online adaptive head and neck intensity modulated proton therapy

Objective. To evaluate the impact of setup uncertainty reduction (SUR) and adaptation to geometrical changes (AGC) on normal tissue complication probability (NTCP) when using online adaptive head and neck intensity modulated proton therapy (IMPT).Approach.A cohort of ten retrospective head and neck cancer patients with daily scatter corrected cone-beam CT (CBCT) was studied. For each patient, two IMPT treatment plans were created: one with a 3 mm setup uncertainty robustness setting and one with no explicit setup robustness. Both plans were recalculated on the daily CBCT considering three scenarios: the robust plan without adaptation, the non-robust plan without adaptation and the non-robust plan with daily online adaptation. Online-adaptation was simulated using an in-house developed workflow based on GPU-accelerated Monte Carlo dose calculation and partial spot-intensity re-optimization. Dose distributions associated with each scenario were accumulated on the planning CT, where NTCP models for six toxicities were applied. NTCP values from each scenario were intercompared to quantify the reduction in toxicity risk induced by SUR alone, AGC alone and SUR and AGC combined. Finally, a decision tree was implemented to assess the clinical significance of the toxicity reduction associated with each mechanism.Main results. For most patients, clinically meaningful NTCP reductions were only achieved when SUR and AGC were performed together. In these conditions, total reductions in NTCP of up to 30.48 pp were obtained, with noticeable NTCP reductions for aspiration, dysphagia and xerostomia (mean reductions of 8.25, 5.42 and 5.12 pp respectively). While SUR had a generally larger impact than AGC on NTCP reductions, SUR alone did not induce clinically meaningful toxicity reductions in any patient, compared to only one for AGC alone.SignificanceOnline adaptive head and neck proton therapy can only yield clinically significant reductions in the risk of long-term side effects when combining the benefits of SUR and AGC.

CBCT-to-CT Translation Using Registration-Based Generative Adversarial Networks in Patients with Head and Neck Cancer

Recently, deep learning with generative adversarial networks (GANs) has been applied in multi-domain image-to-image translation. This study aims to improve the image quality of cone-beam computed tomography (CBCT) by generating synthetic CT (sCT) that maintains the patient’s anatomy as in CBCT, while having the image quality of CT. As CBCT and CT are acquired at different time points, it is challenging to obtain paired images with aligned anatomy for supervised training. To address this limitation, the study incorporated a registration network (RegNet) into GAN during training. RegNet can dynamically estimate the correct labels, allowing supervised learning with noisy labels. The study developed and evaluated the approach using imaging data from 146 patients with head and neck cancer. The results showed that GAN trained with RegNet performed better than those trained without RegNet. Specifically, in the UNIT model trained with RegNet, the mean absolute error (MAE) was reduced from 40.46 to 37.21, the root mean-square error (RMSE) was reduced from 119.45 to 108.86, the peak signal-to-noise ratio (PSNR) was increased from 28.67 to 29.55, and the structural similarity index (SSIM) was increased from 0.8630 to 0.8791. The sCT generated from the model had fewer artifacts and retained the anatomical information as in CBCT.

Real-time liver tumor localization via combined surface imaging and a single x-ray projection

Objective. Real-time imaging, a building block of real-time adaptive radiotherapy, provides instantaneous knowledge of anatomical motion to drive delivery adaptation to improve patient safety and treatment efficacy. The temporal constraint of real-time imaging (<500 milliseconds) significantly limits the imaging signals that can be acquired, rendering volumetric imaging and 3D tumor localization extremely challenging. Real-time liver imaging is particularly difficult, compounded by the low soft tissue contrast within the liver. We proposed a deep learning (DL)-based framework (Surf-X-Bio), to track 3D liver tumor motion in real-time from combined optical surface image and a single on-board x-ray projection.Approach. Surf-X-Bio performs mesh-based deformable registration to track/localize liver tumors volumetrically via three steps. First, a DL model was built to estimate liver boundary motion from an optical surface image, using learnt motion correlations between the respiratory-induced external body surface and liver boundary. Second, the residual liver boundary motion estimation error was further corrected by a graph neural network-based DL model, using information extracted from a single x-ray projection. Finally, a biomechanical modeling-driven DL model was applied to solve the intra-liver motion for tumor localization, using the liver boundary motion derived via prior steps.Main results. Surf-X-Bio demonstrated higher accuracy and better robustness in tumor localization, as compared to surface-image-only and x-ray-only models. By Surf-X-Bio, the mean (±s.d.) 95-percentile Hausdorff distance of the liver boundary from the 'ground-truth' decreased from 9.8 (±4.5) (before motion estimation) to 2.4 (±1.6) mm. The mean (±s.d.) center-of-mass localization error of the liver tumors decreased from 8.3 (±4.8) to 1.9 (±1.6) mm.Significance. Surf-X-Bio can accurately track liver tumors from combined surface imaging and x-ray imaging. The fast computational speed (<250 milliseconds per inference) allows it to be applied clinically for real-time motion management and adaptive radiotherapy.

Large anatomical changes in head-and-neck cancers – a dosimetric comparison of online and offline adaptive proton therapy

Purpose

This work evaluates an online adaptive (OA) workflow for head-and-neck (H&N) intensity-modulated proton therapy (IMPT) and compares it with full offline replanning (FOR) in patients with large anatomical changes.

Methods

IMPT treatment plans are created retrospectively for a cohort of eight H&N cancer patients that previously required replanning during the course of treatment due to large anatomical changes. Daily cone-beam CTs (CBCT) are acquired and corrected for scatter, resulting in 253 analyzed fractions. To simulate the FOR workflow, nominal plans are created on the planning-CT and delivered until a repeated-CT is acquired; at this point, a new plan is created on the repeated-CT. To simulate the OA workflow, nominal plans are created on the planning-CT and adapted at each fraction using a simple beamlet weight-tuning technique. Dose distributions are calculated on the CBCTs with Monte Carlo for both delivery methods. The total treatment dose is accumulated on the planning-CT.

Results

Daily OA improved target coverage compared to FOR despite using smaller target margins. In the high-risk CTV, the median D₉₈ degradation was 1.1 % and 2.1 % for OA and FOR, respectively. In the low-risk CTV, the same metrics yield 1.3 % and 5.2 % for OA and FOR, respectively. Smaller setup margins of OA reduced the dose to all OARs, which was most relevant for the parotid glands.

Conclusion

Daily OA can maintain prescription doses and constraints over the course of fractionated treatment, even in cases of large anatomical changes, reducing the necessity for manual replanning in H&N IMPT.

Dosimetric impact of adaptive proton therapy in head and neck cancer - A review

Background

Intensity Modulated Proton Therapy (IMPT) in head and neck cancer (HNC) is susceptible to anatomical changes and patient set-up inaccuracies during the radiotherapy course, which can cause discrepancies between planned and delivered dose. The discrepancies can be counteracted by adaptive replanning strategies. This article reviews the observed dosimetric impact of adaptive proton therapy (APT) and the timing to perform a plan adaptation in IMPT in HNC.

Methods

A literature search of articles published in PubMed/MEDLINE, EMBASE and Web of Science from January 2010 to March 2022 was performed. Among a total of 59 records assessed for possible eligibility, ten articles were included in this review.

Results

Included studies reported on target coverage deterioration in IMPT plans during the RT course, which was recovered with the application of an APT approach. All APT plans showed an average improved target coverage for the high- and low-dose targets as compared to the accumulated dose on the planned plans. Dose improvements up to 2.5 Gy (3.5 %) and up to 4.0 Gy (7.1 %) in the D98 of the high- and low dose targets were observed with APT. Doses to the organs at risk (OARs) remained equal or decreased slightly after APT was applied. In the included studies, APT was largely performed once, which resulted in the largest target coverage improvement, but eventual additional APT improved the target coverage further. There is no data showing what is the most appropriate timing for APT.

Conclusion

APT during IMPT for HNC patients improves target coverage. The largest improvement in target coverage was found with a single adaptive intervention, and an eventual second or more frequent APT application improved the target coverage further. Doses to the OARs remained equal or decreased slightly after applying APT. The most optimal timing for APT is yet to be determined.

Use of CBCT plus plan robustness for reducing QACT frequency in intensity-modulated proton therapy: Head-and-neck cases

PURPOSE

Anatomic variation has a significant dosimetric impact in intensity-modulated proton therapy. Weekly or biweekly computed tomography (CT) scans, called quality assurance CTs (QACTs), are used to monitor anatomic and resultant dose changes to determine whether adaptive plans are needed. Frequent CT scans result in unwanted QACT dose and increased clinical workloads. This study proposed utilizing patient setup cone-beam CTs (CBCTs) and treatment plan robustness to reduce the frequency of QACTs.

METHODS

We retrospectively analyzed data from 27 patients with head-and-neck cancer, including 594 CBCTs, 136 QACTs, and 19 adaptive plans. For each CBCT, water-equivalent thickness (WET) along the pencil-beam path was calculated. For each treatment plan, the WET of the first-day CBCT was used as the reference, and the mean WET changes (ΔWET) in each following CBCT was used as the surrogate of proton range change. Using CBCTs acquired prior to a QACT, we predicted the ΔWET on the QACT day by a linear regression model. The impact of range change on target dose was calculated as the predicted ΔWET weighted by the monitor units of each field. In addition, plan robustness was estimated from the robust dose-volume histograms (DVHs) and combined with ΔWET to reduce QACT frequency. Robustness was estimated from the distance between the DVH curves of the nominal and worst scenarios.

RESULTS

When the estimated mean ΔWET was <6.5 mm (or <7.5 mm if the robustness was >95%), the QACT could be skipped without missing any adaptive planning; otherwise a QACT was required. Overall, 41% of QACTs could be eliminated when ΔWET was <6.5 mm and 56% when ΔWET was <7.5 mm, and robustness was >95%. At least one QACT could have been omitted in 25 of the 27 cases under skipping thresholds at ΔWETs <7.5 mm and R > 95%.

CONCLUSION

This study suggests that the number of QACTs can be greatly reduced by calculating range change in patient setup CBCTs and can be further reduced by combining this information with analyses of plan robustness.

A more effective CT synthesizer using transformers for cone-beam CT-guided adaptive radiotherapy

Purpose

The challenge of cone-beam computed tomography (CBCT) is its low image quality, which limits its application for adaptive radiotherapy (ART). Despite recent substantial improvement in CBCT imaging using the deep learning method, the image quality still needs to be improved for effective ART application. Spurred by the advantages of transformers, which employs multi-head attention mechanisms to capture long-range contextual relations between image pixels, we proposed a novel transformer-based network (called TransCBCT) to generate synthetic CT (sCT) from CBCT. This study aimed to further improve the accuracy and efficiency of ART.

Materials and methods

In this study, 91 patients diagnosed with prostate cancer were enrolled. We constructed a transformer-based hierarchical encoder–decoder structure with skip connection, called TransCBCT. The network also employed several convolutional layers to capture local context. The proposed TransCBCT was trained and validated on 6,144 paired CBCT/deformed CT images from 76 patients and tested on 1,026 paired images from 15 patients. The performance of the proposed TransCBCT was compared with a widely recognized style transferring deep learning method, the cycle-consistent adversarial network (CycleGAN). We evaluated the image quality and clinical value (application in auto-segmentation and dose calculation) for ART need.

Results

TransCBCT had superior performance in generating sCT from CBCT. The mean absolute error of TransCBCT was 28.8 ± 16.7 HU, compared to 66.5 ± 13.2 for raw CBCT, and 34.3 ± 17.3 for CycleGAN. It can preserve the structure of raw CBCT and reduce artifacts. When applied in auto-segmentation, the Dice similarity coefficients of bladder and rectum between auto-segmentation and oncologist manual contours were 0.92 and 0.84 for TransCBCT, respectively, compared to 0.90 and 0.83 for CycleGAN. When applied in dose calculation, the gamma passing rate (1%/1 mm criterion) was 97.5% ± 1.1% for TransCBCT, compared to 96.9% ± 1.8% for CycleGAN.

Conclusions

The proposed TransCBCT can effectively generate sCT for CBCT. It has the potential to improve radiotherapy accuracy.

Deep learning methods for enhancing cone-beam CT image quality towards adaptive radiation therapy: A systematic review

The use of deep learning (DL) to improve cone-beam CT (CBCT) image quality has gained popularity as computational resources and algorithmic sophistication have advanced in tandem. CBCT imaging has the potential to facilitate online adaptive radiation therapy (ART) by utilizing up-to-date patient anatomy to modify treatment parameters before irradiation. Poor CBCT image quality has been an impediment to realizing ART due to the increased scatter conditions inherent to cone-beam acquisitions. Given the recent interest in DL applications in radiation oncology, and specifically DL for CBCT correction, we provide a systematic theoretical and literature review for future stakeholders. The review encompasses DL approaches for synthetic CT generation, as well as projection domain methods employed in the CBCT correction literature. We review trends pertaining to publications from January 2018 to April 2022 and condense their major findings - with emphasis on study design and deep learning techniques. Clinically relevant endpoints relating to image quality and dosimetric accuracy are summarised, highlighting gaps in the literature. Finally, we make recommendations for both clinicians and DL practitioners based on literature trends and the current DL state of the art methods utilized in radiation oncology. This article is protected by copyright. All rights reserved.

A Survey on Deep Learning for Precision Oncology

Precision oncology, which ensures optimized cancer treatment tailored to the unique biology of a patient’s disease, has rapidly developed and is of great clinical importance. Deep learning has become the main method for precision oncology. This paper summarizes the recent deep-learning approaches relevant to precision oncology and reviews over 150 articles within the last six years. First, we survey the deep-learning approaches categorized by various precision oncology tasks, including the estimation of dose distribution for treatment planning, survival analysis and risk estimation after treatment, prediction of treatment response, and patient selection for treatment planning. Secondly, we provide an overview of the studies per anatomical area, including the brain, bladder, breast, bone, cervix, esophagus, gastric, head and neck, kidneys, liver, lung, pancreas, pelvis, prostate, and rectum. Finally, we highlight the challenges and discuss potential solutions for future research directions.

A generalized image quality improvement strategy of cone-beam CT using multiple spectral CT labels in Pix2pix GAN

Objective. The quantitative and routine imaging capabilities of cone-beam CT (CBCT) are hindered from clinical applications due to the severe shading artifacts of scatter contamination. The scatter correction methods proposed in the literature only consider the anatomy of the scanned objects while disregarding the impact of incident x-ray energy spectra. The multiple-spectral model is in urgent need for CBCT scatter estimation. Approach. In this work, we incorporate the multiple spectral diagnostic multidetector CT labels into the pixel-to-pixel (Pix2pix) GAN to estimate accurate scatter distributions from CBCT projections acquired at various imaging volume sizes and x-ray energy spectra. The Pix2pix GAN combines the residual network as the generator and the PatchGAN as the discriminator to construct the correspondence between the scatter-contaminated projection and scatter distribution. The network architectures and loss function of Pix2pix GAN are optimized to achieve the best performance on projection-to-scatter transition. Results. The CBCT data of a head phantom and abdominal patients are applied to test the performance of the proposed method. The error of the corrected CBCT image using the proposed method is reduced from over 200 HU to be around 20 HU in both phantom and patient studies. The mean structural similarity index of the CT image is improved from 0.2 to around 0.9 after scatter correction using the proposed method compared with the MC-simulation method, which indicates a high similarity of the anatomy in the images before and after the proposed correction. The proposed method achieves higher accuracy of scatter estimation than using the Pix2pix GAN with the U-net generator. Significance. The proposed scheme is an effective solution to the multiple spectral CBCT scatter correction. The scatter-correction software using the proposed model will be available at: https://github.com/YangkangJiang/Cone-beam-CT-scatter-correction-tool.

Evaluating Proton Dose and Associated Range Uncertainty Using Daily Cone-Beam CT

Purpose

This study aimed to quantitatively evaluate the range uncertainties that arise from daily cone-beam CT (CBCT) images for proton dose calculation compared to CT using a measurement-based technique.

Methods

For head and thorax phantoms, wedge-shaped intensity-modulated proton therapy (IMPT) treatment plans were created such that the gradient of the wedge intersected and was measured with a 2D ion chamber array. The measured 2D dose distributions were compared with 2D dose planes extracted from the dose distributions using the IMPT plan calculated on CT and CBCT. Treatment plans of a thymoma cancer patient treated with breath-hold (BH) IMPT were recalculated on 28 CBCTs and 9 CTs, and the resulting dose distributions were compared.

Results

The range uncertainties for the head phantom were determined to be 1.2% with CBCT, compared to 0.5% for CT, whereas the range uncertainties for the thorax phantom were 2.1% with CBCT, compared to 0.8% for CT. The doses calculated on CBCT and CT were similar with similar anatomy changes. For the thymoma patient, the primary source of anatomy change was the BH uncertainty, which could be up to 8 mm in the superior-inferior (SI) direction.

Conclusion

We developed a measurement-based range uncertainty evaluation method with high sensitivity and used it to validate the accuracy of CBCT-based range and dose calculation. Our study demonstrated that the CBCT-based dose calculation could be used for daily dose validation in selected proton patients.

Management of Motion and Anatomical Variations in Charged Particle Therapy: Past, Present, and Into the Future

The major aim of radiation therapy is to provide curative or palliative treatment to cancerous malignancies while minimizing damage to healthy tissues. Charged particle radiotherapy utilizing carbon ions or protons is uniquely suited for this task due to its ability to achieve highly conformal dose distributions around the tumor volume. For these treatment modalities, uncertainties in the localization of patient anatomy due to inter- and intra-fractional motion present a heightened risk of undesired dose delivery. A diverse range of mitigation strategies have been developed and clinically implemented in various disease sites to monitor and correct for patient motion, but much work remains. This review provides an overview of current clinical practices for inter and intra-fractional motion management in charged particle therapy, including motion control, current imaging and motion tracking modalities, as well as treatment planning and delivery techniques. We also cover progress to date on emerging technologies including particle-based radiography imaging, novel treatment delivery methods such as tumor tracking and FLASH, and artificial intelligence and discuss their potential impact towards improving or increasing the challenge of motion mitigation in charged particle therapy.

Effects of group housing and incremental hay supplementation in calf starters at different ages on growth performance, behavior, and health

The present study examined the effects of age at group housing and age at incremental hay supplementation in calf starters from 7.5 to 15% (dry matter, DM) and their interaction on growth performance, behavior, health of dairy calves, and development of heifers through first breeding. A total of 64 calves (n = 16 calves/treatment, 8 male and 8 female) were randomly assigned to 4 treatments in a 2 × 2 factorial arrangement, with age at group housing (early = d 28 ± 2, EG vs. late = d 70 ± 2, LG; 4 calves per group) and age at incremental hay supplementation of calf starters from 7.5 to 15% of DM (early = d 42 ± 2 d, EH vs. late = d 77 ± 2, LH) as the main factors. All calves (female and male) were weaned at 63 days of age and observed until 90 days of age. Heifer calves were managed uniformly from 90 days of age until first calving to evaluate the long-term effects of treatment. No interactions were observed between age at group housing and age at incremental hay to calves on starter feed intake, performance, calf health and behavior, and heifer development through first breeding, which was contrary to our hypothesis. The age at which incremental hay supplementation was administered had no effect on starter feed intake, growth performance, or heifer development until first calving. When EG calves were compared with LG calves, nutrient intake (starter, total dry matter, metabolizable energy, neutral detergent fiber, starch, and crude protein), average daily gain, and final body weight increased. In addition, frequency of standing decreased and time and frequency of eating increased in EG calves compared to LG calves. Overall, early group housing leads to improved growth performance in dairy calves with no negative effects on calf health compared to late group housing.

Virtual monoenergetic micro-CT imaging in mice with artificial intelligence

Micro cone-beam computed tomography (µCBCT) imaging is of utmost importance for carrying out extensive preclinical research in rodents. The imaging of animals is an essential step prior to preclinical precision irradiation, but also in the longitudinal assessment of treatment outcomes. However, imaging artifacts such as beam hardening will occur due to the low energetic nature of the X-ray imaging beam (i.e., 60 kVp). Beam hardening artifacts are especially difficult to resolve in a ‘pancake’ imaging geometry with stationary source and detector, where the animal is rotated around its sagittal axis, and the X-ray imaging beam crosses a wide range of thicknesses. In this study, a seven-layer U-Net based network architecture (vMonoCT) is adopted to predict virtual monoenergetic X-ray projections from polyenergetic X-ray projections. A Monte Carlo simulation model is developed to compose a training dataset of 1890 projection pairs. Here, a series of digital anthropomorphic mouse phantoms was derived from the reference DigiMouse phantom as simulation geometry. vMonoCT was trained on 1512 projection pairs (= 80%) and tested on 378 projection pairs (= 20%). The percentage error calculated for the test dataset was 1.7 ± 0.4%. Additionally, the vMonoCT model was evaluated on a retrospective projection dataset of five mice and one frozen cadaver. It was found that beam hardening artifacts were minimized after image reconstruction of the vMonoCT-corrected projections, and that anatomically incorrect gradient errors were corrected in the cranium up to 15%. Our results disclose the potential of Artificial Intelligence to enhance the µCBCT image quality in biomedical applications. vMonoCT is expected to contribute to the reproducibility of quantitative preclinical applications such as precision irradiations in X-ray cabinets, and to the evaluation of longitudinal imaging data in extensive preclinical studies.

Generating synthesized computed tomography from CBCT using a conditional generative adversarial network for head and neck cancer patients

Purpose: To overcome the imaging artifacts and Hounsfield unit inaccuracy limitations of cone-beam computed tomography, a conditional generative adversarial network is proposed to synthesize high-quality computed tomography-like images from cone-beam computed tomography images. Methods: A total of 120 paired cone-beam computed tomography and computed tomography scans of patients with head and neck cancer who were treated during January 2019 and December 2020 retrospectively collected; the scans of 90 patients were assembled into training and validation datasets, and the scans of 30 patients were used in testing datasets. The proposed method integrates a U-Net backbone architecture with residual blocks into a conditional generative adversarial network framework to learn a mapping from cone-beam computed tomography images to pair planning computed tomography images. The mean absolute error, root-mean-square error, structural similarity index, and peak signal-to-noise ratio were used to assess the performance of this method compared with U-Net and CycleGAN. Results: The synthesized computed tomography images produced by the conditional generative adversarial network were visually similar to planning computed tomography images. The mean absolute error, root-mean-square error, structural similarity index, and peak signal-to-noise ratio calculated from test images generated by conditional generative adversarial network were all significantly different than CycleGAN and U-Net. The mean absolute error, root-mean-square error, structural similarity index, and peak signal-to-noise ratio values between the synthesized computed tomography and the reference computed tomography were 16.75 ± 11.07 Hounsfield unit, 58.15 ± 28.64 Hounsfield unit, 0.92 ± 0.04, and 30.58 ± 3.86 dB in conditional generative adversarial network, 20.66 ± 12.15 Hounsfield unit, 66.53 ± 29.73 Hounsfield unit, 0.90 ± 0.05, and 29.29 ± 3.49 dB in CycleGAN, and 16.82 ± 10.99 Hounsfield unit, 58.68 ± 28.34 Hounsfield unit, 0.92 ± 0.04, and 30.48 ± 3.83 dB in U-Net, respectively. Conclusions: The synthesized computed tomography generated from the cone-beam computed tomography-based conditional generative adversarial network method has accurate computed tomography numbers while keeping the same anatomical structure as cone-beam computed tomography. It can be used effectively for quantitative applications in radiotherapy.

CT-on-Rails Versus In-Room CBCT for Online Daily Adaptive Proton Therapy of Head-and-Neck Cancers

PURPOSE

To compare the efficacy of CT-on-rails versus in-room CBCT for daily adaptive proton therapy.

METHODS

We analyzed a cohort of ten head-and-neck patients with daily CBCT and corresponding virtual CT images. The necessity of moving the patient after a CT scan is the most significant difference in the adaptation workflow, leading to an increased treatment execution uncertainty σ. It is a combination of the isocenter-matching σ_i and random patient movements induced by the couch motion σ_m. The former is assumed to never exceed 1 mm. For the latter, we studied three different scenarios with σ_m = 1, 2, and 3 mm. Accordingly, to mimic the adaptation workflow with CT-on-rails, we introduced random offsets after Monte-Carlo-based adaptation but before delivery of the adapted plan.

RESULTS

There were no significant differences in accumulated dose-volume histograms and dose distributions for σ_m = 1 and 2 mm. Offsets with σ_m = 3 mm resulted in underdosage to CTV and hot spots of considerable volume.

CONCLUSION

Since σ_m typically does not exceed 2 mm for in-room CT, there is no clinically significant dosimetric difference between the two modalities for online adaptive therapy of head-and-neck patients. Therefore, in-room CT-on-rails can be considered a good alternative to CBCT for adaptive proton therapy.

Adaptive proton therapy

Radiation therapy treatments are typically planned based on a single image set, assuming that the patient's anatomy and its position relative to the delivery system remains constant during the course of treatment. Similarly, the prescription dose assumes constant biological dose-response over the treatment course. However, variations can and do occur on multiple time scales. For treatment sites with significant intra-fractional motion, geometric changes happen over seconds or minutes, while biological considerations change over days or weeks. At an intermediate timescale, geometric changes occur between daily treatment fractions. Adaptive radiation therapy is applied to consider changes in patient anatomy during the course of fractionated treatment delivery. While traditionally adaptation has been done off-line with replanning based on new CT images, online treatment adaptation based on on-board imaging has gained momentum in recent years due to advanced imaging techniques combined with treatment delivery systems. Adaptation is particularly important in proton therapy where small changes in patient anatomy can lead to significant dose perturbations due to the dose conformality and finite range of proton beams. This review summarizes the current state-of-the-art of on-line adaptive proton therapy and identifies areas requiring further research.

Planning CT-guided robust and fast cone-beam CT scatter correction using a local filtration technique

PURPOSE

Cone-beam CT (CBCT) has been widely utilized in image-guided radiotherapy. Planning CT (pCT)-aided CBCT scatter correction could further enhance image quality and extend CBCT application to dose calculation and adaptive planning. Nevertheless, existing pCT-based approaches demand accurate registration between pCT and CBCT, leading to limited imaging performance and increased computational cost when large anatomical discrepancies exist. In this work, we proposed a robust and fast CBCT scatter correction method using local filtration technique and rigid registration between pCT and CBCT (LF-RR).

METHODS

First of all, the pCT was rigidly registered with CBCT, then forward projection was performed on registered pCT to create scatter-free projections. The raw scatter signals were obtained via subtracting the scatter-free projections from the measured CBCT projections. Based on frequency and intensity threshold criteria, reliable scatter signals were selected from the raw scatter signals, and further filtered for global scatter estimation via local filtration technique. Finally, corrected CBCT was reconstructed with the projections generated by subtracting the scatter estimation from the raw CBCT projections using FDK algorithm. The LF-RR method was evaluated via comparison with another pCT-based scatter correction method based on Median and Gaussian filters (MG method).

RESULTS

Proposed method was first validated on an anthropomorphic pelvis phantom, and showed satisfied performance on scatter removal even when anatomical mismatches were intentionally created on pCT. The quantitative analysis was further performed on four clinical CBCT images. Compared with the uncorrected CBCT, CBCT corrected by MG with rigid registration (MG-RR), MG with deformable registration (MG-DR), and LF-RR reduced the CT number error from 79 ± 35 to 25 ± 18 , 17 ± 13 and 7 ± 3 HU for adipose and from 115 ± 61 to 36 ± 22 , 30 ± 24 , 7 ± 3 HU for muscle, respectively. After correction, the spatial non-uniformity (SNU) of CBCT corrected with MG-RR, MG-DR and LF-RR was 51 ± 13 , 60 ± 21 , and 21 ± 9 HU for adipose, and 50 ± 22 , 57 ± 41 , and 25 ± 6 HU for muscle, respectively. Meanwhile, the contrast-to-noise ratio (CNR) between muscle and adipose was increased by a factor of 2.70, 2.89 and 2.56, respectively. Using the LF-RR method, the scatter correction of 656 projections can be finished within 10 s and the corrected volumetric images (200 slices) can be obtained within 2 min.

CONCLUSION

We developed a fast and robust pCT-based CBCT scatter correction method which exploits the local-filtration technique to promote the accuracy of scatter estimation and is resistant to pCT-to-CBCT registration uncertainties. Both phantom and patient studies showed the superiority of the proposed correction in imaging accuracy and computational efficiency, indicating promisingfuture clinical application.

Generating synthetic CT from low-dose cone-beam CT by using generative adversarial networks for adaptive radiotherapy

OBJECTIVE

To develop high-quality synthetic CT (sCT) generation method from low-dose cone-beam CT (CBCT) images by using attention-guided generative adversarial networks (AGGAN) and apply these images to dose calculations in radiotherapy.

METHODS

The CBCT/planning CT images of 170 patients undergoing thoracic radiotherapy were used for training and testing. The CBCT images were scanned under a fast protocol with 50% less clinical projection frames compared with standard chest M20 protocol. Training with aligned paired images was performed using conditional adversarial networks (so-called pix2pix), and training with unpaired images was carried out with cycle-consistent adversarial networks (cycleGAN) and AGGAN, through which sCT images were generated. The image quality and Hounsfield unit (HU) value of the sCT images generated by the three neural networks were compared. The treatment plan was designed on CT and copied to sCT images to calculated dose distribution.

RESULTS

The image quality of sCT images by all the three methods are significantly improved compared with original CBCT images. The AGGAN achieves the best image quality in the testing patients with the smallest mean absolute error (MAE, 43.5 ± 6.69), largest structural similarity (SSIM, 93.7 ± 3.88) and peak signal-to-noise ratio (PSNR, 29.5 ± 2.36). The sCT images generated by all the three methods showed superior dose calculation accuracy with higher gamma passing rates compared with original CBCT image. The AGGAN offered the highest gamma passing rates (91.4 ± 3.26) under the strictest criteria of 1 mm/1% compared with other methods. In the phantom study, the sCT images generated by AGGAN demonstrated the best image quality and the highest dose calculation accuracy.

CONCLUSIONS

High-quality sCT images were generated from low-dose thoracic CBCT images by using the proposed AGGAN through unpaired CBCT and CT images. The dose distribution could be calculated accurately based on sCT images in radiotherapy.

Experimental validation of daily adaptive proton therapy

Anatomical changes during proton therapy require rapid treatment plan adaption to mitigate the associated dosimetric impact. This in turn requires a highly efficient workflow that minimizes the time between imaging and delivery. At the Paul Scherrer Institute, we have developed an online adaptive workflow, which is specifically designed for treatments in the skull-base/cranium, with the focus set on simplicity and minimizing changes to the conventional workflow. The dosimetric and timing performance of this daily adaptive proton therapy (DAPT) workflow has been experimentally investigated using an in-house developed DAPT software and specifically developed anthropomorphic phantom. After a standard treatment preparation, which includes the generation of a template plan, the treatment can then be adapted each day, based on daily imaging acquired on an in-room CT. The template structures are then rigidly propagated to this CT and the daily plan is fully re-optimized using the same field arrangement, DVH constraints and optimization settings of the template plan. After a dedicated plan QA, the daily plan is delivered. To minimize the time between imaging and delivery, clinically integrated software for efficient execution of all online adaption steps, as well as tools for comprehensive and automated QA checks, have been developed. Film measurements of an end-to-end validation of a multi-fraction DAPT treatment showed high agreement to the calculated doses. Gamma pass rates with a 3%/3 mm criteria were >92% when comparing the measured dose to the template plan. Additionally, a gamma pass rate >99% was found comparing measurements to the Monte Carlo dose of the daily plans reconstructed from the logfile, accumulated over the delivered fractions. With this, we experimentally demonstrate that the described adaptive workflow can be delivered accurately in a timescale similar to a standard delivery.

Validation of proton dose calculation on scatter corrected 4D cone beam computed tomography using a porcine lung phantom

Proton therapy treatment for lungs remains challenging as images enabling the detection of inter- and intra-fractional motion, which could be used for proton dose adaptation, are not readily available. 4D computed tomography (4DCT) provides high image quality but is rarely available in-room, while in-room 4D cone beam computed tomography (4DCBCT) suffers from image quality limitations stemming mostly from scatter detection. This study investigated the feasibility of using virtual 4D computed tomography (4DvCT) as a prior for a phase-per-phase scatter correction algorithm yielding a 4D scatter corrected cone beam computed tomography image (4DCBCT_cor), which can be used for proton dose calculation. 4DCT and 4DCBCT scans of a porcine lung phantom, which generated reproducible ventilation, were acquired with matching breathing patterns. Diffeomorphic Morphons, a deformable image registration algorithm, was used to register the mid-position 4DCT to the mid-position 4DCBCT and yield a 4DvCT. The 4DCBCT was reconstructed using motion-aware reconstruction based on spatial and temporal regularization (MA-ROOSTER). Successively for each phase, digitally reconstructed radiographs of the 4DvCT, simulated without scatter, were exploited to correct scatter in the corresponding CBCT projections. The 4DCBCT_corwas then reconstructed with MA-ROOSTER using the corrected CBCT projections and the same settings and deformation vector fields as those already used for reconstructing the 4DCBCT. The 4DCBCT_corand the 4DvCT were evaluated phase-by-phase, performing proton dose calculations and comparison to those of a ground truth 4DCT by means of dose-volume-histograms (DVH) and gamma pass-rates (PR). For accumulated doses, DVH parameters deviated by at most 1.7% in the 4DvCT and 2.0% in the 4DCBCT_corcase. The gamma PR for a (2%, 2 mm) criterion with 10% threshold were at least 93.2% (4DvCT) and 94.2% (4DCBCT_cor), respectively. The 4DCBCT_cortechnique enabled accurate proton dose calculation, which indicates the potential for applicability to clinical 4DCBCT scans.

Anatomic changes in head and neck intensity-modulated proton therapy: Comparison between robust optimization and online adaptation

BACKGROUND/PURPOSE

Setup variations and anatomical changes can severely affect the quality of head and neck intensity-modulated proton therapy (IMPT) treatments. The impact of these changes can be alleviated by increasing the plan's robustness a priori, or by adapting the plan online. This work compares these approaches in the context of head and neck IMPT.

MATERIALS/METHODS

A representative cohort of 10 head and neck squamous cell carcinoma (HNSCC) patients with daily cone-beam computed tomography (CBCT) was evaluated. For each patient, three IMPT plans were created: 1- a classical robust optimization (cRO) plan optimized on the planning CT, 2- an anatomical robust optimization (aRO) plan additionally including the two first daily CBCTs and 3- a plan optimized without robustness constraints, but online-adapted (OA) daily, using a constrained spot intensity re-optimization technique only.

RESULTS

The cumulative dose following OA fulfilled the clinical objective of both the high-risk and low-risk clinical target volumes (CTV) coverage in all 10 patients, compared to 8 for aRO and 4 for cRO. aRO did not significantly increase the dose to most organs at risk compared to cRO, although the integral dose was higher. OA significantly reduced the integral dose to healthy tissues compared to both robust methods, while providing equivalent or superior target coverage.

CONCLUSION

Using a simple spot intensity re-optimization, daily OA can achieve superior target coverage and lower dose to organs at risk than robust optimization methods.