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.

In vivo dosimetry for proton therapy: A Monte Carlo study of the Gadolinium spectral response throughout the course of treatment

BACKGROUND

In proton radiotherapy, the steep dose deposition profile near the end of the proton's track, the Bragg peak, ensures a more conformed deposition of dose to the tumor region when compared with conventional radiotherapy while reducing the probability of normal tissue complications. However, uncertainties, as in the proton range, patient geometry, and positioning pose challenges to the precise and secure delivery of the treatment plan (TP). In vivo range determination and dose distribution are pivotal for mitigation of uncertainties, opening the possibility to reduce uncertainty margins and for adaptation of the TP.

PURPOSE

This study aims to explore the feasibility of utilizing gadolinium (Gd), a highly used contrast agent in MRI, as a surrogate for in vivo dosimetry during the course of scanning proton therapy, tracking the delivery of a TP and the impact of uncertainties intra- and inter-fraction in the course of treatment.

METHODS

Monte Carlo simulations (Geant4 11.1.1) were performed, where a Gd-filled volume was placed within a water phantom and underwent treatment with a scanning proton TP delivering 4 Gy. The secondary photons emitted upon proton-Gd interaction were recorded and assessed for various tumor displacements. The spectral response of Gd to each pencil beam irradiation is therefore used as a surrogate for dose measurements during treatment.

RESULTS

Results show that the deposited dose at the target volume can be tracked for each TP scanning point by correlating it with the recorded Gd signal. The analyzed Gd spectral line corresponded to the characteristic X-rayk α $\text{k}_\alpha$ line at 43 keV. Displacements from the planned geometry could be distinguished by observing changes in the Gd signal induced by each pencil beam. Moreover, the total 43 keV signal recorded subsequently to the full TP delivery reflected deviations from the planned integral dose to the target.

CONCLUSIONS

The study suggests that the spectral response of a Gd-based contrast agent can be used for in vivo dosimetry, providing insights into the TP delivery. The Gd 43 keV spectral line was correlated with the dose at the tumor, its volume, and its position. Other variables that can impact the method, such as the kinetic energy of the incident protons and Gd concentration in the target were also discussed.

Partial adaptation for online-adaptive proton therapy triggered by during-delivery treatment verification: Feasibility study on prostate cancer treatments

Background and Purpose

Online treatment verification during proton therapy delivery may detect deviations due to anatomical changes occurring along the treatment course and trigger immediate intervention, if necessary. We investigated the potential of partial plan adaptation in two-field prostate cancer treatments as a solution for online-adaptive proton therapy (OAPT) after the detection of relevant treatment deviations during the first field delivery.

Materials and Methods

In a retrospective study, ten fractions from eight prostate cancer patients with prompt gamma imaging (PGI) detected treatment deviations, which were confirmed on respective in-room control computed tomography (cCT) scans, were considered. For each cCT, a dose-mimicking-based robust partial adaptation reoptimized the second field by considering the suboptimal dose delivery of the first non-adapted, PGI-monitored field. The results were compared to the non-adapted scenario and upfront full adaptation (both fields) in terms of achievable target coverage (prescription: 48 Gy/60 Gy to low-risk/high-risk target) and organ-at-risk (OAR) sparing.

Results

Partially adapted plans showed comparable target coverage (median D 98%: 99.9%/98.0% for low-/high-risk target) to fully adapted plans (100.3%/98.7%) and were superior to non-adapted plans (98.7%/94.5%). Achievable OAR sparing was patient-specific depending on the proximity to the target region, but within clinical goals for the partially and fully adapted plans.

Conclusions

Partial adaptation triggered mid-delivery of a fraction can still generate plans of comparable conformity to full adaptation, even in the case of plans with only two, opposing fields. A verification-triggered OAPT may therefore become an alternative to upfront OAPT, saving time and imaging dose in fractions without relevant anatomy changes.

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.

Proton dose calculation with transformer: Transforming spot map to dose

BACKGROUND

Conventional proton dose calculation methods are either time- and resource-intensive, like Monte Carlo (MC) simulations, or they sacrifice accuracy, as seen with analytical methods. This trade-off between computational efficiency and accuracy highlights the need for improved dose calculation approaches in clinical settings.

PURPOSE

This study aims to develop a deep-learning-based model that calculates dose-to-water (DW) and dose-to-medium (DM) using patient anatomy and proton spot map (PSM), achieving approaching MC-level accuracy with significantly reduced computation time. Additionally, the study seeks to generalize the model to different treatment sites using transfer learning.

METHODS

A SwinUNetr model was developed using 259 four-field prostate proton stereotactic body radiation therapy (SBRT) plans to calculate patient-specific DW and DM distributions from CT and projected PSM (PPSM). The PPSM was created by projecting PSM into the CT scans using spot coordinates, stopping power ratio, beam divergence, and water-equivalent thickness. Fine-tuning was then performed for the central nervous system (CNS) site using 84 CNS plans. The model's accuracy was evaluated against MC simulation benchmarks using mean absolute error (MAE), gamma analysis (2% local dose difference, 2-mm distance-to-agreement, 10% low dose threshold), and relevant clinical indices on the test dataset.

RESULTS

The trained model achieved a single-field dose calculation time of 0.07 s on a Nvidia-A100 GPU, over 100 times faster than MC simulators. For the prostate site, the best-performing model showed an average MAE of 0.26 ± 0.17 Gy and a gamma index of 92.2% ± 3.1% in dose regions above 10% of the maximum dose for DW calculations, and an MAE of 0.30 ± 0.19 Gy with a gamma index of 89.7% ± 3.9% for DM calculations. After transfer learning for CNS plans, the model achieved an MAE of 0.49 ± 0.24 Gy and a gamma index of 90.1% ± 2.7% for DW computations, and an MAE of 0.47 ± 0.25 Gy with a gamma index of 85.4% ± 7.1% for DM computations.

CONCLUSIONS

The SwinUNetr model provides an efficient and accurate method for computing dose distributions in proton therapy. It also opens the possibility of reverse-engineering PSM from DW, potentially speeding up treatment planning while maintaining accuracy.

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.

Accuracy Evaluation of Dose Warping Using Deformable Image Registration in Carbon Ion Therapy

Purpose

The study's purpose was to use a simple geometry phantom to validate the deformable image registration (DIR) accuracy and dose warping accuracy in carbon ion radiotherapy (CIRT) and to provide an index for dosimetry in CIRT.

Materials and methods

We used geometric and anatomical phantoms provided by AAPM TG-132. The DIRs of 3 different settings were performed between reference and translational images for each phantom. CIRT and photon therapy (3-dimensional conformal radiotherapy and volumetric modulated radiotherapy) treatment plans were transformed by the use of deformation vector fields calculated from the DIR of each setting. The dose distribution calculated on the basis of rigid registration between images was used as the ground truth and compared with the warped dose determined by DIR to evaluate the error.

Results

The photon therapy treatment plans showed a dose warping error of <2% for a DIR error of <2 mm, whereas CIRT showed a dose warping error >10% for the same DIR accuracy. From this, even with similar DIR accuracy, the errors tended to be larger for CIRT than for photon therapy dose distributions. Due to the steepness of the CIRT dose gradient, the dose difference increased by about 5% for a DIR error of 5 mm, which was larger than the 3% dose difference generated for a 5 mm DIR error in photon therapy.

Conclusion

We evaluated the relationship between DIR accuracy and dose warping accuracy in the CIRT dose distribution. Due to the steepness of the dose gradient in CIRT, we concluded that dose warping based on DIR accuracy should be required to be sufficiently higher than that in photon therapy.

Exploration of an adaptive proton therapy strategy using CBCT with the concept of digital twins

Objective.This study aims to develop a digital twin (DT) framework to achieve adaptive proton prostate stereotactic body radiation therapy (SBRT) with fast treatment plan selection and patient-specific clinical target volume (CTV) setup uncertainty. Prostate SBRT has emerged as a leading option for external beam radiotherapy due to its effectiveness and reduced treatment duration. However, interfractional anatomy variations can impact treatment outcomes. This study seeks to address these uncertainties using DT concept to improve treatment quality.Approach. A retrospective study on two-fraction prostate proton SBRT was conducted, involving a cohort of 10 randomly selected patient cases from an institutional database (n= 43). DT-based treatment plans were developed using patient-specific CTV setup uncertainty, determined through machine learning predictions. Plans were optimized using pre-treatment CT and corrected cone-beam CT (cCBCT). The cCBCT was corrected for CT numbers and artifacts, and plan evaluation was performed using cCBCT to account for actual patient anatomy. The ProKnow scoring system was adapted to determine the optimal treatment plans.Main Results.Average CTV D98 values for original clinical and DT-based plans across 10 patients were 99.0% and 98.8%, with hot spots measuring 106.0% and 105.1%. Regarding bladder, clinical plans yielded average bladder neck V100 values of 29.6% and bladder V20.8 Gy values of 12.0cc, whereas DT-based plans showed better sparing of bladder neck with values of 14.0% and 9.5cc. Clinical and DT-based plans resulted in comparable rectum dose statistics due to SpaceOAR. Compared to clinical plans, the proposed DT-based plans improved dosimetry quality, improving plan scores ranging from 2.0 to 15.5.Significance.Our study presented a pioneering approach that leverages DT technology to enhance adaptive proton SBRT, potentially revolutionizing prostate radiotherapy to offer personalized treatment solutions using fast adaptive treatment plan selections and patient-specific setup uncertainty. This research contributes to the ongoing efforts to achieve personalized prostate radiotherapy.

First dosimetric evaluation of clinical raster-scanned proton, helium and carbon ion treatment plan delivery during simultaneous real-time magnetic resonance imaging

This work presents an experimental dosimetric evaluation of raster-scanning particle beam delivery during simultaneous in-beam magnetic resonance (MR) imaging. Using an open MR scanner at an experimental treatment room, radiochromic film comparisons for protons, helium and carbon ions, each with and without simultaneous in-beam cine MR imaging, yielded 2D gamma pass rates ≥ 98.8 % for a 3 % / 1.5 mm criterion, and ≥ 99.9 % for 5 % / 1.5 mm. These results constitute a first experimental confirmation that time varying magnetic fields of MR gradients do not result in clinically relevant additional dose perturbations.

Potential of automated online adaptive proton therapy to reduce margins for oesophageal cancer

Background and purpose

Proton therapy for oesophageal cancer is administered over multiple fractions, based on a single pre-treatment image. However, anatomical changes can lead to the deterioration of the treatment plan, necessitating manual replanning. To keep this within limits, increased residual margins are employed. This study aimed to evaluate the proposed automated Online Adaptive Proton Therapy (OAPT) strategies on their capability to reduce the need for manual replanning, while also exploring the possibility of margin reduction.

Materials and methods

Two automated OAPT methods were examined: Automated Dose Restoration (ADR) and Automated Full Adaptation (AFA). ADR makes use of dose restoration, restoring the original dose map based on the patient's altered anatomy. AFA adapts the contours used for plan optimization by applying a deformation field, not only correcting for density changes, but also for the relative location of organs. A comparative analysis of OAPT strategies, evaluatingD 98% tumour coverage on 17 patients, was conducted.

Results

The nominal results of non-adapted plans with 7 mm residual margins required manual replanning for 18% of the patients. ADR reduced this to 6%, while AFA eliminated the need for manual replanning. With 2 mm margins, 47% of cases required manual replanning. ADR reduced this to 18%, and AFA further reduced it to 11%.

Conclusions

The proposed OAPT strategies offered a marked improvement compared to a non-adaptive approach. ADR and AFA significantly reduced the necessity for manual replanning and facilitated the reduction of residual margins, enhancing dose conformity and reducing treatment toxicity.

Unsupervised Deep Learning for Synthetic CT Generation from CBCT Images for Proton and Carbon Ion Therapy for Paediatric Patients

Image-guided treatment adaptation is a game changer in oncological particle therapy (PT), especially for younger patients. The purpose of this study is to present a cycle generative adversarial network (CycleGAN)-based method for synthetic computed tomography (sCT) generation from cone beam CT (CBCT) towards adaptive PT (APT) of paediatric patients. Firstly, 44 CBCTs of 15 young pelvic patients were pre-processed to reduce ring artefacts and rigidly registered on same-day CT scans (i.e., verification CT scans, vCT scans) and then inputted to the CycleGAN network (employing either Res-Net and U-Net generators) to synthesise sCT. In particular, 36 and 8 volumes were used for training and testing, respectively. Image quality was evaluated qualitatively and quantitatively using the structural similarity index metric (SSIM) and the peak signal-to-noise ratio (PSNR) between registered CBCT (rCBCT) and vCT and between sCT and vCT to evaluate the improvements brought by CycleGAN. Despite limitations due to the sub-optimal input image quality and the small field of view (FOV), the quality of sCT was found to be overall satisfactory from a quantitative and qualitative perspective. Our findings indicate that CycleGAN is promising to produce sCT scans with acceptable CT-like image texture in paediatric settings, even when CBCT with narrow fields of view (FOV) are employed.

First clinical implementation of a highly efficient daily online adapted proton therapy (DAPT) workflow

Objective.This study presents the first clinical implementation of an efficient online daily adaptive proton therapy workflow (DAPT).Approach.The DAPT workflow includes apre-treatment phase,where atemplateand afallback planare optimized on the planning computed tomography (CT). In theonline phase, theadapted planis re-optimized on daily images from an in-room CT. Daily structures are rigidly propagated from the planning CT. Automated Quality Assurance (QA) involves geometric, sanity checks and an independent dose calculation from the machine files. Differences from the template plan are analyzed field-by-field, and clinical plan is assessed by reviewing the achieved clinical goals using a traffic light protocol. If the daily adapted plan fails any QA or clinical goals, the fallback plan is used. In theoffline phasethe delivered dose is recalculated from log-files onto the daily CT, and a gamma analysis is performed (3%/3 mm). The DAPT workflow has been applied to selected adult patients treated in rigid anatomy for the last serie of the treatment between October 2023 and April 2024.Main Results.DAPT treatment sessions averaged around 23 min [range: 15-30 min] and did not exceed the typical 30 minute time slot. Treatment adaptation, including QA and clinical plan assessment, averaged just under 7 min [range: 3:30-16 min] per fraction. All plans passed the online QAs steps. In the offline phase a good agreement with the log-files reconstructed dose was achieved (minimum gamma pass rate of 97.5%). The online adapted plan was delivered for >85% of the fractions. In 92% of total fractions, adapted plans exhibited improved individual dose metrics to the targets and/or organs at risk.Significance.This study demonstrates the successful implementation of an online daily DAPT workflow. Notably, the duration of a DAPT session did not exceed the time slot typically allocated for non-DAPT treatment. As far as we are aware, this is a first clinical implementation of daily online adaptive proton therapy.

The influence of daily imaging and target margin reduction on secondary cancer risk in image-guided and adaptive proton therapy

Objective. Image-guided and adaptive proton therapy rely on daily CBCT or CT imaging, which increases radiation dose and radiation-induced cancer risk. Online adaptation however also reduces setup uncertainty, and the additional risk might be compensated by reducing the setup robustness margin. This work developed a framework to investigate how much this robustness margin should be reduced to offset the secondary cancer risk from additional imaging dose and applied it to proton therapy for head-and-neck cancer.Approach. For five patients with head-and-neck cancer, voxel-wise CT and CBCT imaging doses were estimated with Monte Carlo radiation transport simulations, calibrated with air and PMMA phantom measurements. The total dose of several image-guided and adaptive treatments protocols was calculated by summing the planning CT dose, daily and weekly CBCT or CT dose, and therapy dose, robustly optimized with setup margins between 0 and 4 mm. These were compared to a reference protocol with 4 mm setup margin without daily imaging. All plans further used 3% range robustness. Organ-wise excess absolute risk (EAR) of cancer was calculated with three models to determine at which setup margin the total EAR of image-guided and adaptive treatment protocols was equal to the total EAR of the reference.Results. The difference between the simulated and measured CT and CBCT doses was within 10%. Using the Monte Carlo models, we found that a 1 mm setup margin reduction was sufficient for most patients, treatment protocols, and cancer risk models to compensate the additional risk imposed by daily and weekly imaging. For some protocols, even a smaller reduction sufficed, depending on the imaging frequency and type. The risk reduction by reducing the margin was mainly due to reducing the risk for carcinomas in the brain and, for some patients, the oral cavity.Significance. Our framework allows to compare an increased imaging dose with the reduced treatment dose from margin reductions in terms of radiation-induced cancer risk. It is extendable to different treatment sites, modalities, and imaging protocols, in clinic-specific or even patient-specific assessments.

Commissioning of a novel gantry-less proton therapy system

Purpose

The focus of this article is to describe the configuration, testing, and commissioning of a novel gantry-less synchrotron-based proton therapy (PT) facility.

Materials and methods

The described PT system delivers protons with a water equivalent range between 4 and 38 cm in 1800 energy layers. The fixed beam delivery permits a maximum field size of 28 × 30 cm2. The patient positioning and imaging system includes a six-degree-of-freedom robotic arm, a convertible patient chair, a vertical 4DCT, and an orthogonal 2D X-ray imaging system.

Results

The spot positioning reproducibility was consistent within ±1 mm. The width (σ) of the beam profile at the isocenter was energy dependent and ranged from 2.8 mm to 7.7 mm. Absolute dose reproducibility was measured and deviations were found to be <0.62% for all possible beam scenarios. The built-in dose monitoring system was successfully tested for its ability to generate interlocks under specific conditions (beam spot deviation ≥2 mm, individual spot dose ≥10% or ≥0.25 Gy, spot energy deviation ≥0.5 MeV). The robot positioning exhibited a consistent reproducibility within ±1 mm. All tested scenarios achieved laser-free initial 3D/3D image-guided positioning within ±5 mm. Subsequent 2D/3D positioning showed an accuracy of ±1 mm. A single 2D/3D image registration event corrected positions in all cases. Results of gamma analysis (3%, 3 mm) demonstrated pass rates greater than 95% for head and neck, thorax, abdomen treatment plans.

Conclusions

We report on the performance of a novel single-room gantry-less PT system comprised of a compact synchrotron and an adjustable (from nearly horizontal to almost vertical) patient positioning system. The commissioning results show high accuracy and reproducibility of the main proton beam parameters and the patient positioning system. The new PT facility started patient treatments in March 2023, which were the first in Israel and the Middle Eastern region.

Anatomical and dosimetric variations during volumetric modulated arc therapy in patients with locally advanced nasopharyngeal carcinoma after induction therapy: Implications for adaptive radiation therapy

Purpose

To investigate anatomical and dosimetric changes during volumetric modulated arc therapy (VMAT) in patients with locally advanced nasopharyngeal carcinoma (LA-NPC) after induction therapy (IT) and explore characteristics of patients with notable variations.

Materials and methods

From July 2021 to June 2023, 60 LA-NPC patients undergoing VMAT after IT were retrospectively recruited. Adaptive computed tomography (aCT), reconstructed from weekly cone-beam computed tomography(CBCT), facilitates recontouring and planning transplantation. Volume, dice similarity coefficients, and dose to target volumes and organs at risk(OARs) on planning CT(pCT) and aCT were compared to identify changing patterns. Multivariate logistic regression was used to investigate risk factors.

Results

The volumes of PGTVnasopharynx (PGTVp), PGTVnode (PGTVn), ipsilateral and contralateral parotid glands decreased during VMAT, with reductions of 2.25 %, 6.98 %, 20.09 % and 18.00 %, respectively, at 30 fractions from baseline (P < 0.001). After 25 fractions, D99 and D95 of PGTVn decreased by 7.94 % and 4.18 % from baseline, respectively, while the Dmean of ipsilateral and contralateral parotid glands increased by 7.80 % and 6.50 %, marking the peak rates of dosimetric variations (P < 0.001). The dosimetric fluctuations in PGTVp, the brainstem, and the spinal cord remained within acceptable limits. Furthermore, an initial BMI ≥ 23.5 kg/m2 and not-achieving objective response (OR) after IT were regarded as risk factors for a remarkable PGTVn dose reduction in the later stages of VMAT.

Conclusions

Replanning for post-IT LA-NPC patients appears reasonable at 25F during VMAT. Patients with an initial BMI ≥ 23.5 kg/m2 and not-achieving OR after IT should be considered for adaptive radiation therapy to stabilize the delivered dose.

Brainstem Toxicity Following Proton Beam Radiation Therapy in Pediatric Brain Tumors: A Systematic Review and Meta-Analysis

Background: Proton beam radiation therapy (PBRT) is an advanced cancer treatment modality that utilizes the distinctive physical properties of protons to precisely deliver radiation to tumor targets while sparing healthy tissue. This cannot be obtained with photon radiation. In this systematic review and meta-analysis, we aimed to comprehensively assess the risk of brainstem toxicity in pediatric brain tumor patients undergoing PBRT. Methods: With adherence to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines, a predetermined search strategy was used to identify eligible articles from PubMed, Web of Science, Scopus, and Cochrane Library through July 2024. Results: The current study included a total of 11 eligible articles. The pooled prevalence of patients who suffered from brainstem toxicity was 1.8% (95% CI: 1%, 2.6%). The pooled prevalences of patients with Grade 1 to Grade 5 brainstem toxicity were found to be 10.6% (95% CI: 8.8%, 30%), 1.5% (95% CI: 0.6%, 2.5%), 0.7% (95% CI: 0.3%, 1.1%), 0.4% (95% CI: 0.1%, 0.7%), and 0.4% (95% CI: 0.1%, 0.8%), respectively, with an overall pooled prevalence of 0.7% (95% CI: 0.4%, 1%). Conclusions: This study revealed a relatively low incidence of symptomatic brainstem toxicity and its related mortality in the pediatric population undergoing PBRT. However, further research is encouraged to study the broader effects of PBRT and to explore various factors that may influence the risk of brainstem toxicity in patients treated with PBRT.

Exploring dual energy CT synthesis in CBCT-based adaptive radiotherapy and proton therapy: application of denoising diffusion probabilistic models

Background.Adaptive radiotherapy (ART) requires precise tissue characterization to optimize treatment plans and enhance the efficacy of radiation delivery while minimizing exposure to organs at risk. Traditional imaging techniques such as cone beam computed tomography (CBCT) used in ART settings often lack the resolution and detail necessary for accurate dosimetry, especially in proton therapy.Purpose.This study aims to enhance ART by introducing an innovative approach that synthesizes dual-energy computed tomography (DECT) images from CBCT scans using a novel 3D conditional denoising diffusion probabilistic model (DDPM) multi-decoder. This method seeks to improve dose calculations in ART planning, enhancing tissue characterization.Methods.We utilized a paired CBCT-DECT dataset from 54 head and neck cancer patients to train and validate our DDPM model. The model employs a multi-decoder Swin-UNET architecture that synthesizes high-resolution DECT images by progressively reducing noise and artifacts in CBCT scans through a controlled diffusion process.Results.The proposed method demonstrated superior performance in synthesizing DECT images (High DECT MAE 39.582 ± 0.855 and Low DECT MAE 48.540± 1.833) with significantly enhanced signal-to-noise ratio and reduced artifacts compared to traditional GAN-based methods. It showed marked improvements in tissue characterization and anatomical structure similarity, critical for precise proton and radiation therapy planning.Conclusions.This research has opened a new avenue in CBCT-CT synthesis for ART/APT by generating DECT images using an enhanced DDPM approach. The demonstrated similarity between the synthesized DECT images and ground truth images suggests that these synthetic volumes can be used for accurate dose calculations, leading to better adaptation in treatment planning.

Quality and Safety Considerations for Adaptive Radiation Therapy: An ASTRO White Paper

PURPOSE

Adaptive radiation therapy (ART) is the latest topic in a series of white papers published by the American Society for Radiation Oncology addressing quality processes and patient safety. ART widens the therapeutic index by improving the precision of radiation dose to targets, allowing for dose escalation and/or minimization of dose to normal tissue. ART is performed via offline or online methods; offline ART is the process of replanning a patient's treatment plan between fractions, whereas online ART involves plan adjustment with the patient on the treatment table. This is achieved with in-room imaging capable of assessing anatomic changes and the ability to reoptimize the treatment plan rapidly during the treatment session. Although ART has occurred in its simplest forms in clinical practice for decades, recent technological developments have enabled more clinical applications of ART. With increased clinical prevalence, compressed timelines, and the associated complexity of ART, quality and safety considerations are an important focus area.

METHODS

The American Society for Radiation Oncology convened an interdisciplinary task force to provide expert consensus on key workflows and processes for ART. Recommendations were created using a consensus-building methodology, and task force members indicated their level of agreement based on a 5-point Likert scale, from "strongly agree" to "strongly disagree." A prespecified threshold of ≥75% of raters selecting "strongly agree" or "agree" indicated consensus. Content not meeting this threshold was removed or revised.

SUMMARY

Establishing and maintaining an adaptive program requires a team-based approach, appropriately trained and credentialed specialists, significant resources, specialized technology, and implementation time. A comprehensive quality assurance program must be developed, using established guidance, to make sure all forms of ART are performed in a safe and effective manner. Patient safety when delivering ART is everyone's responsibility, and professional organizations, regulators, vendors, and end users must demonstrate a clear commitment to working together to deliver the highest levels of quality and safety.

A comparative study on automatic treatment planning for online adaptive proton therapy of esophageal cancer: which combination of deformable registration and deep learning planning tools performs the best?

Objective.To demonstrate the feasibility of integrating fully-automated online adaptive proton therapy strategies (OAPT) within a commercially available treatment planning system and underscore what limits their clinical implementation. These strategies leverage existing deformable image registration (DIR) algorithms and state-of-the-art deep learning (DL) networks for organ segmentation and proton dose prediction.Approach.Four OAPT strategies featuring automatic segmentation and robust optimization were evaluated on a cohort of 17 patients, each undergoing a repeat CT scan. (1) DEF-INIT combines deformably registered contours with template-based optimization. (2) DL-INIT, (3) DL-DEF, and (4) DL-DL employ a nnU-Net DL network for organ segmentation and a controlling ROIs-guided DIR algorithm for internal clinical target volume (iCTV) segmentation. DL-INIT uses this segmentation alongside template-based optimization, DL-DEF integrates it with a dose-mimicking (DM) step using a reference deformed dose, and DL-DL merges it with DM on a reference DL-predicted dose. All strategies were evaluated on manual contours and contours used for optimization and compared with manually adapted plans. Key dose volume metrics like iCTV D98% are reported.Main results.iCTV D98% was comparable in manually adapted plans and for all strategies in nominal cases but dropped to 20 Gy in worst-case scenarios for a few patients per strategy, highlighting the need to correct segmentation errors in the target volume. Evaluations on optimization contours showed minimal relative error, with some outliers, particularly in template-based strategies (DEF-INIT and DL-INIT). DL-DEF achieves a good trade-off between speed and dosimetric quality, showing a passing rate (iCTV D98% > 94%) of 90% when evaluated against 2, 4 and 5 mm setup error and of 88% when evaluated against 7 mm setup error. While template-based methods are more rigid, DL-DEF and DL-DL have potential for further enhancements with proper DM algorithm tuning.Significance.Among investigated strategies, DL-DEF and DL-DL demonstrated promising within 10 min OAPT implementation results and significant potential for improvements.

Proton dose calculation on cone-beam computed tomography using unsupervised 3D deep learning networks

Background and Purpose

Poor image quality of cone-beam computed tomography (CBCT) images can hinder proton dose calculation to assess the influence of anatomy changes. The aim of this study was to evaluate image quality and proton dose calculation accuracy of synthetic CTs generated from CBCT using unsupervised 3D deep-learning networks.

Materials and methods

A total of 102 head-and-neck cancer patients were used to train (N=82) and test (N=20) i) a cycle-consistent generative adversarial network, ii) a contrastive unpaired translation, and iii) a fusion of the two (CycleCUT). For patients in the test set, a repeat CT was deformably registered to a same-day CBCT to create a ground-truth CT for comparison. The proton plan was re-calculated on the ground-truth CT and synthetic CTs. The image quality of the synthetic CTs was evaluated using peak signal-to-noise ratio, structural similarity index measure, mean error, and mean absolute error (MAE). Proton dose calculation accuracy was assessed through 3D gamma analysis and dose-volume-histogram parameters.

Results

All synthetic CTs accurately preserved the CBCT anatomy (verified by visual inspection) while improving the image quality. The CycleCUT network had slightly improved image quality compared to the other networks (MAE in body: 53 Hounsfield units (HU) vs. 54/55 HU). All networks had similar proton dose calculation accuracy with gamma passing rate above 97%.

Conclusions

All three evaluated networks generated synthetic CT images with dose distributions comparable to those of conventional fan-beam CT. The synthetic CT generation was fast, making all networks feasible for adaptive proton therapy.

Comparing robust proton versus online adaptive photon radiotherapy for short-course treatment of rectal cancer

Background and purpose

Image-guided proton beam therapy (IG-PBT) and cone-beam CT (CBCT)-based online adaptive photon radiotherapy (oART) have potentials to restrict radiation toxicity. They are both hypothesised to reduce therapy limiting bowel toxicity in the multimodality treatment of locally advanced rectal cancer (LARC). This study aimed to quantify the difference in relevant dose-volume metrics for these modalities.

Material and Methods

Six-degrees-of-freedom IG-PBT and oART short-course radiotherapy (SCRT) were simulated for 18 LARC patients. Relative biological effectiveness (RBE) was 1.1 for IG-PBT. Delivered dose was evaluated using post-CBCTs. Target coverage was considered robust if average dose to 99% of the clinical target volume was ≥ 95% of the prescription. Organ at risk (OAR) doses were compared using dose-volume histograms and severe bowel toxicity estimated using dose-response modelling.

Results

Target coverage was robust in all patients for oART and all but one patient for IG-PBT. For the main OARs, IG-PBT increased the volume exposed to ≥ 15 Gy (RBE), but reduced volumes exposed to lower doses. Both low- and high-dose exposure to bowel loops were significantly different between the modalities (median (interquartile range) IG-PBT-V8.9Gy(RBE) = 92 (51-156) cm3, oART-V8.9Gy(RBE) = 166 (107-234) cm3, p < 0.001; IG-PBT-V23Gy(RBE) = 62 (25-106) cm3, oART-V23Gy(RBE) = 38 (18-75) cm3, p < 0.001), translating into similar total grade ≥ 3 bowel toxicity risk.

Conclusion

IG-PBT and oART delivered comparable and satisfying target coverage in SCRT for LARC with similar estimated risk of severe bowel toxicity. Volumes of OAR exposed to 15 Gy (RBE) or more were reduced by oART, while IG-PBT reduced the volumes receiving doses below this level.

Patient-specific deep learning for 3D protoacoustic image reconstruction and dose verification in proton therapy

BACKGROUND

Protoacoustic (PA) imaging has the potential to provide real-time 3D dose verification of proton therapy. However, PA images are susceptible to severe distortion due to limited angle acquisition. Our previous studies showed the potential of using deep learning to enhance PA images. As the model was trained using a limited number of patients' data, its efficacy was limited when applied to individual patients.

PURPOSE

In this study, we developed a patient-specific deep learning method for protoacoustic imaging to improve the reconstruction quality of protoacoustic imaging and the accuracy of dose verification for individual patients.

METHODS

Our method consists of two stages: in the first stage, a group model is trained from a diverse training set containing all patients, where a novel deep learning network is employed to directly reconstruct the initial pressure maps from the radiofrequency (RF) signals; in the second stage, we apply transfer learning on the pre-trained group model using patient-specific dataset derived from a novel data augmentation method to tune it into a patient-specific model. Raw PA signals were simulated based on computed tomography (CT) images and the pressure map derived from the planned dose. The reconstructed PA images were evaluated against the ground truth by using the root mean squared errors (RMSE), structural similarity index measure (SSIM) and gamma index on 10 specific prostate cancer patients. The significance level was evaluated by t-test with the p-value threshold of 0.05 compared with the results from the group model.

RESULTS

The patient-specific model achieved an average RMSE of 0.014 (p < 0.05 ${{{p}}}<{0.05}$ ), and an average SSIM of 0.981 (p < 0.05 ${{{p}}}<{0.05}$ ), out-performing the group model. Qualitative results also demonstrated that our patient-specific approach acquired better imaging quality with more details reconstructed when comparing with the group model. Dose verification achieved an average RMSE of 0.011 (p < 0.05 ${{{p}}}<{0.05}$ ), and an average SSIM of 0.995 (p < 0.05 ${{{p}}}<{0.05}$ ). Gamma index evaluation demonstrated a high agreement (97.4% [p < 0.05 ${{{p}}}<{0.05}$ ] and 97.9% [p < 0.05 ${{{p}}}<{0.05}$ ] for 1%/3  and 1%/5 mm) between the predicted and the ground truth dose maps. Our approach approximately took 6 s to reconstruct PA images for each patient, demonstrating its feasibility for online 3D dose verification for prostate proton therapy.

CONCLUSIONS

Our method demonstrated the feasibility of achieving 3D high-precision PA-based dose verification using patient-specific deep-learning approaches, which can potentially be used to guide the treatment to mitigate the impact of range uncertainty and improve the precision. Further studies are needed to validate the clinical impact of the technique.

Proton Therapy Adaptation of Perisinusoidal and Brain Areas in the Cyclotron Centre Bronowice in Krakow: A Dosimetric Analysis

Applying a proton beam in radiotherapy enables precise irradiation of the tumor volume, but only for continuous assessment of changes in patient anatomy. Proton beam range uncertainties in the treatment process may originate not only from physical beam properties but also from patient-specific factors such as tumor shrinkage, edema formation and sinus filling, which are not incorporated in tumor volume safety margins. In this paper, we evaluated variations in dose distribution in proton therapy resulting from the differences observed in the control tomographic images and the dosimetric influence of applied adaptive treatment. The data from weekly computed tomography (CT) control scans of 21 patients, which serve as the basis for adaptive radiotherapy, were used for this study. Dosimetric analysis of adaptive proton therapy (APT) was performed on patients with head and neck (H&N) area tumors who were divided into two groups: patients with tumors in the sinus/nasal area and patients with tumors in the brain area. For this analysis, the reference treatment plans were forward-calculated using weekly control CT scans. A comparative evaluation of organ at risk (OAR) dose-volume histogram (DVH) parameters, as well as conformity and homogeneity indices, was conducted between the initial and recalculated dose distributions to assess the necessity of the adaptation process in terms of dosimetric parameters. Changes in PTV volume after replanning were observed in seventeen patient cases, showing a discrepancy of over 1 cm3 in ten cases. In these cases, tumor progression occurred in 30% of patients, while regression was observed in 70%. The statistical analysis indicates that the use of the adaptive planning procedure results in a statistically significant improvement in dose distribution, particularly in the PTV area. The findings led to the conclusion that the adaptive procedure provides significant advantages in terms of dose distribution within the treated volume. However, when considering the entire patient group, APT did not result in a statistically significant dose reduction in OARs (α = 0.05).

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 deep-learning-based surrogate model for Monte-Carlo simulations of the linear energy transfer in primary brain tumor patients treated with proton-beam radiotherapy

Objective.This study explores the use of neural networks (NNs) as surrogate models for Monte-Carlo (MC) simulations in predicting the dose-averaged linear energy transfer (LETd) of protons in proton-beam therapy based on the planned dose distribution and patient anatomy in the form of computed tomography (CT) images. As LETdis associated with variability in the relative biological effectiveness (RBE) of protons, we also evaluate the implications of using NN predictions for normal tissue complication probability (NTCP) models within a variable-RBE context.Approach.The predictive performance of three-dimensional NN architectures was evaluated using five-fold cross-validation on a cohort of brain tumor patients (n= 151). The best-performing model was identified and externally validated on patients from a different center (n= 107). LETdpredictions were compared to MC-simulated results in clinically relevant regions of interest. We assessed the impact on NTCP models by leveraging LETdpredictions to derive RBE-weighted doses, using the Wedenberg RBE model.Main results.We found NNs based solely on the planned dose distribution, i.e. without additional usage of CT images, can approximate MC-based LETddistributions. Root mean squared errors (RMSE) for the median LETdwithin the brain, brainstem, CTV, chiasm, lacrimal glands (ipsilateral/contralateral) and optic nerves (ipsilateral/contralateral) were 0.36, 0.87, 0.31, 0.73, 0.68, 1.04, 0.69 and 1.24 keV µm-1, respectively. Although model predictions showed statistically significant differences from MC outputs, these did not result in substantial changes in NTCP predictions, with RMSEs of at most 3.2 percentage points.Significance.The ability of NNs to predict LETdbased solely on planned dose distributions suggests a viable alternative to compute-intensive MC simulations in a variable-RBE setting. This is particularly useful in scenarios where MC simulation data are unavailable, facilitating resource-constrained proton therapy treatment planning, retrospective patient data analysis and further investigations on the variability of proton RBE.

Multi-institutional experimental validation of online adaptive proton therapy workflows

Objective.To experimentally validate two online adaptive proton therapy (APT) workflows using Gafchromic EBT3 films and optically stimulated luminescent dosimeters (OSLDs) in an anthropomorphic head-and-neck phantom.Approach.A three-field proton plan was optimized on the planning CT of the head-and-neck phantom with 2.0 Gy(RBE) per fraction prescribed to the clinical target volume. Four fractions were simulated by varying the internal anatomy of the phantom. Three distinct methods were delivered: daily APT researched by the Paul Scherrer Institute (DAPTPSI), online adaptation researched by the Massachusetts General Hospital (OAMGH), and a non-adaptive (NA) workflow. All methods were implemented and measured at PSI. DAPTPSIperformed full online replanning based on analytical dose calculation, optimizing to the same objectives as the initial treatment plan. OAMGHperformed Monte-Carlo-based online plan adaptation by only changing the fluences of a subset of proton beamlets, mimicking the planned dose distribution. NA delivered the initial plan with a couch-shift correction based on in-room imaging. For all 12 deliveries, two films and two sets of OSLDs were placed at different locations in the phantom.Main results.Both adaptive methods showed improved dosimetric results compared to NA. For film measurements in the presence of anatomical variations, the [min-max] gamma pass rates (3%/3 mm) between measured and clinically approved doses were [91.5%-96.1%], [94.0%-95.8%], and [67.2%-93.1%] for DAPTPSI, OAMGH, and NA, respectively. The OSLDs confirmed the dose calculations in terms of absolute dosimetry. Between the two adaptive workflows, OAMGHshowed improved target coverage, while DAPTPSIshowed improved normal tissue sparing, particularly relevant for the brainstem.Significance.This is the first multi-institutional study to experimentally validate two different concepts with respect to online APT workflows. It highlights their respective dosimetric advantages, particularly in managing interfractional variations in patient anatomy that cannot be addressed by non-adaptive methods, such as internal anatomy changes.

Yet anOther Dose Algorithm (YODA) for independent computations of dose and dose changes due to anatomical changes

Objective.To assess the viability of a physics-based, deterministic and adjoint-capable algorithm for performing treatment planning system independent dose calculations and for computing dosimetric differences caused by anatomical changes.Approach.A semi-numerical approach is employed to solve two partial differential equations for the proton phase-space density which determines the deposited dose. Lateral hetereogeneities are accounted for by an optimized (Gaussian) beam splitting scheme. Adjoint theory is applied to approximate the change in the deposited dose caused by a new underlying patient anatomy.Main results.The dose engine's accuracy was benchmarked through three-dimensional gamma index comparisons against Monte Carlo simulations done in TOPAS. For a lung test case, the worst passing rate with (1 mm, 1%, 10% dose cut-off) criteria is 94.55%. The effect of delivering treatment plans on repeat CTs was also tested. For non-robustly optimized plans the adjoint component was accurate to 5.7% while for a robustly optimized plan it was accurate to 4.8%.Significance.Yet anOther Dose Algorithm is capable of accurate dose computations in both single and multi spot irradiations when compared to TOPAS. Moreover, it is able to compute dosimetric differences due to anatomical changes with small to moderate errors thereby facilitating its use for patient-specific quality assurance in online adaptive proton therapy.

Robust optimization strategies for contour uncertainties in online adaptive radiation therapy

Objective.Online adaptive radiation therapy requires fast and automated contouring of daily scans for treatment plan re-optimization. However, automated contouring is imperfect and introduces contour uncertainties. This work aims at developing and comparing robust optimization strategies accounting for such uncertainties.Approach.A deep-learning method was used to predict the uncertainty of deformable image registration, and to generate a finite set of daily contour samples. Ten optimization strategies were compared: two baseline methods, five methods that convert contour samples into voxel-wise probabilities, and three methods accounting explicitly for contour samples as scenarios in robust optimization. Target coverage and organ-at-risk (OAR) sparing were evaluated robustly for simplified proton therapy plans for five head-and-neck cancer patients.Results.We found that explicitly including target contour uncertainty in robust optimization provides robust target coverage with better OAR sparing than the baseline methods, without increasing the optimization time. Although OAR doses first increased when increasing target robustness, this effect could be prevented by additionally including robustness to OAR contour uncertainty. Compared to the probability-based methods, the scenario-based methods spared the OARs more, but increased integral dose and required more computation time.Significance.This work proposed efficient and beneficial strategies to mitigate contour uncertainty in treatment plan optimization. This facilitates the adoption of automatic contouring in online adaptive radiation therapy and, more generally, enables mitigation also of other sources of contour uncertainty in treatment planning.

Deep learning-based voxel sampling for particle therapy treatment planning

Objective.Scanned particle therapy often requires complex treatment plans, robust optimization, as well as treatment adaptation. Plan optimization is especially complicated for heavy ions due to the variable relative biological effectiveness. We present a novel deep-learning model to select a subset of voxels in the planning process thus reducing the planning problem size for improved computational efficiency.Approach.Using only a subset of the voxels in target and organs at risk (OARs) we produced high-quality treatment plans, but heuristic selection strategies require manual input. We designed a deep-learning model based onP-Net to obtain an optimal voxel sampling without relying on patient-specific user input. A cohort of 70 head and neck patients that received carbon ion therapy was used for model training (50), validation (10) and testing (10). For training, a total of 12 500 carbon ion plans were optimized, using a highly efficient artificial intelligence (AI) infrastructure implemented into a research treatment planning platform. A custom loss function increased sampling density in underdosed regions, while aiming to reduce the total number of voxels.Main results.On the test dataset, the number of voxels in the optimization could be reduced by 84.8% (median) at <1% median loss in plan quality. When the model was trained to reduce sampling in the target only while keeping all voxels in OARs, a median reduction up to 71.6% was achieved, with 0.5% loss in the plan quality. The optimization time was reduced by a factor of 7.5 for the total AI selection model and a factor of 3.7 for the model with only target selection.Significance.The novel deep-learning voxel sampling technique achieves a significant reduction in computational time with a negligible loss in the plan quality. The reduction in optimization time can be especially useful for future real-time adaptation strategies.

Navigating the straits: realizing the potential of proton FLASH through physics advances and further pre-clinical characterization

Ultra-high dose-rate 'FLASH' radiotherapy may be a pivotal step forward for cancer treatment, widening the therapeutic window between radiation tumour killing and damage to neighbouring normal tissues. The extent of normal tissue sparing reported in pre-clinical FLASH studies typically corresponds to an increase in isotoxic dose-levels of 5-20%, though gains are larger at higher doses. Conditions currently thought necessary for FLASH normal tissue sparing are a dose-rate ≥40 Gy s-1, dose-per-fraction ≥5-10 Gy and irradiation duration ≤0.2-0.5 s. Cyclotron proton accelerators are the first clinical systems to be adapted to irradiate deep-seated tumours at FLASH dose-rates, but even using these machines it is challenging to meet the FLASH conditions. In this review we describe the challenges for delivering FLASH proton beam therapy, the compromises that ensue if these challenges are not addressed, and resulting dosimetric losses. Some of these losses are on the same scale as the gains from FLASH found pre-clinically. We therefore conclude that for FLASH to succeed clinically the challenges must be systematically overcome rather than accommodated, and we survey physical and pre-clinical routes for achieving this.

Enhancing adaptive proton therapy through CBCT images: Synthetic head and neck CT generation based on 3D vision transformers

BACKGROUND

Proton therapy is a form of radiotherapy commonly used to treat various cancers. Due to its high conformality, minor variations in patient anatomy can lead to significant alterations in dose distribution, making adaptation crucial. While cone-beam computed tomography (CBCT) is a well-established technique for adaptive radiation therapy (ART), it cannot be directly used for adaptive proton therapy (APT) treatments because the stopping power ratio (SPR) cannot be estimated from CBCT images.

PURPOSE

To address this limitation, Deep Learning methods have been suggested for converting pseudo-CT (pCT) images from CBCT images. In spite of convolutional neural networks (CNNs) have shown consistent improvement in pCT literature, there is still a need for further enhancements to make them suitable for clinical applications.

METHODS

The authors introduce the 3D vision transformer (ViT) block, studying its performance at various stages of the proposed architectures. Additionally, they conduct a retrospective analysis of a dataset that includes 259 image pairs from 59 patients who underwent treatment for head and neck cancer. The dataset is partitioned into 80% for training, 10% for validation, and 10% for testing purposes.

RESULTS

The SPR maps obtained from the pCT using the proposed method present an absolute relative error of less than 5% from those computed from the planning CT, thus improving the results of CBCT.

CONCLUSIONS

We introduce an enhanced ViT3D architecture for pCT image generation from CBCT images, reducing SPR error within clinical margins for APT workflows. The new method minimizes bias compared to CT-based SPR estimation and dose calculation, signaling a promising direction for future research in this field. However, further research is needed to assess the robustness and generalizability across different medical imaging applications.

RadDeploy: A framework for integrating in-house developed software and artificial intelligence models seamlessly into radiotherapy workflows

The use of and research in automation and artificial intelligence (AI) in radiotherapy is moving with incredible pace. Many innovations do, however, not make it into the clinic. One technical reason for this may be the lack of a platform to deploy such software into clinical practice. We suggest RadDeploy as a framework for integrating containerized software in clinical workflows outside of treatment planning systems. RadDeploy supports multiple DICOM as input for model containers and can run model containers asynchronously across GPUs and computers. This technical note summarizes the inner workings of RadDeploy and demonstrates three use-cases with varying complexity.

A treatment-site-specific evaluation of commercial synthetic computed tomography solutions for proton therapy

Background and purpose

Despite the superior dose conformity of proton therapy, the dose distribution is sensitive to daily anatomical changes, which can affect treatment accuracy. This study evaluated the dose recalculation accuracy of two synthetic computed tomography (sCT) generation algorithms in a commercial treatment planning system.

Materials and methods

The evaluation was conducted for head-and-neck, thorax-and-abdomen, and pelvis sites treated with proton therapy. Thirty patients with two cone-beam computed tomography (CBCT) scans each were selected. The sCT images were generated from CBCT scans using two algorithms, Corrected CBCT (corrCBCT) and Virtual CT (vCT). Dose recalculations were performed based on these images for comparison with "ground truth" deformed CTs.

Results

The choice of algorithm influenced dose recalculation accuracy, particularly in high dose regions. For head-and-neck cases, the corrCBCT method showed closer agreement with the "ground truth", while for thorax-and-abdomen and pelvis cases, the vCT algorithm yielded better results (mean percentage dose discrepancy of 0.6 %, 1.3 % and 0.5 % for the three sites, respectively, in the high dose region). Head-and-neck and pelvis cases exhibited excellent agreement in high dose regions (2 %/2 mm gamma passing rate >98 %), while thorax-and-abdomen cases exhibited the largest differences, suggesting caution in sCT algorithm usage for this site. Significant systematic differences were observed in the clinical target volume and organ-at-risk doses in head-and-neck and pelvis cases, highlighting the importance of using the correct algorithm.

Conclusions

This study provided treatment site-specific recommendations for sCT algorithm selection in proton therapy. The findings offered insights for proton beam centers implementing adaptive radiotherapy workflows.

A reference-point-method-based online proton treatment plan re-optimization strategy and a novel solution to planning constraint infeasibility problem

Objective. Propose a highly automated treatment plan re-optimization strategy suitable for online adaptive proton therapy. The strategy includes a rapid re-optimization method that generates quality replans and a novel solution that efficiently addresses the planning constraint infeasibility issue that can significantly prolong the re-optimization process.Approach. We propose a systematic reference point method (RPM) model that minimizes the l-infinity norm from the initial treatment plan in the daily objective space for online re-optimization. This model minimizes the largest objective value deviation among the objectives of the daily replan from their reference values, leading to a daily replan similar to the initial plan. Whether a set of planning constraints is feasible with respect to the daily anatomy cannot be known before solving the corresponding optimization problem. The conventional trial-and-error-based relaxation process can cost a significant amount of time. To that end, we propose an optimization problem that first estimates the magnitude of daily violation of each planning constraint. Guided by the violation magnitude and clinical importance of the constraints, the constraints are then iteratively converted into objectives based on their priority until the infeasibility issue is solved.Main results.The proposed RPM-based strategy generated replans similar to the offline manual replans within the online time requirement for six head and neck and four breast patients. The average targetD95and relevant organ at risk sparing parameter differences between the RPM replans and clinical offline replans were -0.23, -1.62 Gy for head and neck cases and 0.29, -0.39 Gy for breast cases. The proposed constraint relaxation solution made the RPM problem feasible after one round of relaxation for all four patients who encountered the infeasibility issue.Significance. We proposed a novel RPM-based re-optimization strategy and demonstrated its effectiveness on complex cases, regardless of whether constraint infeasibility is encountered.

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.

Clinical Workflow of Cone Beam Computer Tomography-Based Daily Online Adaptive Radiotherapy with Offline Magnetic Resonance Guidance: The Modular Adaptive Radiotherapy System (MARS)

PURPOSE

The Ethos (Varian Medical Systems) radiotherapy device combines semi-automated anatomy detection and plan generation for cone beam computer tomography (CBCT)-based daily online adaptive radiotherapy (oART). However, CBCT offers less soft tissue contrast than magnetic resonance imaging (MRI). This work aims to present the clinical workflow of CBCT-based oART with shuttle-based offline MR guidance.

METHODS

From February to November 2023, 31 patients underwent radiotherapy on the Ethos (Varian, Palo Alto, CA, USA) system with machine learning (ML)-supported daily oART. Moreover, patients received weekly MRI in treatment position, which was utilized for daily plan adaptation, via a shuttle-based system. Initial and adapted treatment plans were generated using the Ethos treatment planning system. Patient clinical data, fractional session times (MRI + shuttle transport + positioning, adaptation, QA, RT delivery) and plan selection were assessed for all fractions in all patients.

RESULTS

In total, 737 oART fractions were applied and 118 MRIs for offline MR guidance were acquired. Primary sites of tumors were prostate (n = 16), lung (n = 7), cervix (n = 5), bladder (n = 1) and endometrium (n = 2). The treatment was completed in all patients. The median MRI acquisition time including shuttle transport and positioning to initiation of the Ethos adaptive session was 53.6 min (IQR 46.5-63.4). The median total treatment time without MRI was 30.7 min (IQR 24.7-39.2). Separately, median adaptation, plan QA and RT times were 24.3 min (IQR 18.6-32.2), 0.4 min (IQR 0.3-1,0) and 5.3 min (IQR 4.5-6.7), respectively. The adapted plan was chosen over the scheduled plan in 97.7% of cases.

CONCLUSION

This study describes the first workflow to date of a CBCT-based oART combined with a shuttle-based offline approach for MR guidance. The oART duration times reported resemble the range shown by previous publications for first clinical experiences with the Ethos system.

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.

Technical note: development of a simulation framework, enabling the investigation of locally tuned single energy proton radiography

Range uncertainties remain a limitation for the confined dose distribution that proton therapy can offer. The uncertainty stems from the ambiguity when translating CT Hounsfield Units (HU) into proton stopping powers. Proton Radiography (PR) can be used to verify the proton range. Specifically, PR can be used as a quality-control tool for CBCT-based synthetic CTs. An essential part of the work illustrating the potential of PR has been conducted using multi-layer ionization chamber (MLIC) detectors and mono-energetic PR. Due to the dimensions of commercially available MLICs, clinical adoption is cumbersome. Here, we present a simulation framework exploring locally-tuned single energy (LTSE) proton radiography and corresponding potential compact PR detector designs. Based on a planning CT data set, the presented framework models the water equivalent thickness. Subsequently, it analyses the proton energies required to pass through the geometry within a defined ROI. In the final step, an LTSE PR is simulated using the MCsquare Monte Carlo code. In an anatomical head phantom, we illustrate that LTSE PR allows for a significantly shorter longitudinal dimension of MLICs. We compared PR simulations for two exemplary 30 × 30 mm2proton fields passing the phantom at a 90° angle at an anterior and a posterior location in an iso-centric setup. The longitudinal distance over which all spots per field range out is significantly reduced for LTSE PR compared to mono-energetic PR. In addition, we illustrate the difference in shape of integral depth dose (IDD) when using constrained PR energies. Finally, we demonstrate the accordance of simulated and experimentally acquired IDDs for an LTSE PR acquisition. As the next steps, the framework will be used to investigate the sensitivity of LTSE PR to various sources of errors. Furthermore, we will use the framework to systematically explore the dimensions of an optimized MLIC design for daily clinical use.

Optically stimulated luminescence dosimeters for simultaneous measurement of point dose and dose-weighted LET in an adaptive proton therapy workflow

Purpose

To demonstrate the suitability of optically stimulated luminescence detectors (OSLDs) for accurate simultaneous measurement of the absolute point dose and dose-weighted linear energy transfer (LETD) in an anthropomorphic phantom for experimental validation of daily adaptive proton therapy.

Methods

A clinically realistic intensity-modulated proton therapy (IMPT) treatment plan was created based on a CT of an anthropomorphic head-and-neck phantom made of tissue-equivalent material. The IMPT plan was optimized with three fields to deliver a uniform dose to the target volume covering the OSLDs. Different scenarios representing inter-fractional anatomical changes were created by modifying the phantom. An online adaptive proton therapy workflow was used to recover the daily dose distribution and account for the applied geometry changes. To validate the adaptive workflow, measurements were performed by irradiating Al2O3:C OSLDs inside the phantom. In addition to the measurements, retrospective Monte Carlo simulations were performed to compare the absolute dose and dose-averaged LET (LETD) delivered to the OSLDs.

Results

The online adaptive proton therapy workflow was shown to recover significant degradation in dose conformity resulting from large anatomical and positioning deviations from the reference plan. The Monte Carlo simulations were in close agreement with the OSLD measurements, with an average relative error of 1.4% for doses and 3.2% for LETD. The use of OSLDs for LET determination allowed for a correction for the ionization quenched response.

Conclusion

The OSLDs appear to be an excellent detector for simultaneously assessing dose and LET distributions in proton irradiation of an anthropomorphic phantom. The OSLDs can be cut to almost any size and shape, making them ideal for in-phantom measurements to probe the radiation quality and dose in a predefined region of interest. Although we have presented the results obtained in the experimental validation of an adaptive proton therapy workflow, the same approach can be generalized and used for a variety of clinical innovations and workflow developments that require accurate assessment of point dose and/or average LET.

A review of the clinical introduction of 4D particle therapy research concepts

Background and purpose

Many 4D particle therapy research concepts have been recently translated into clinics, however, remaining substantial differences depend on the indication and institute-related aspects. This work aims to summarise current state-of-the-art 4D particle therapy technology and outline a roadmap for future research and developments.

Material and methods

This review focused on the clinical implementation of 4D approaches for imaging, treatment planning, delivery and evaluation based on the 2021 and 2022 4D Treatment Workshops for Particle Therapy as well as a review of the most recent surveys, guidelines and scientific papers dedicated to this topic.

Results

Available technological capabilities for motion surveillance and compensation determined the course of each 4D particle treatment. 4D motion management, delivery techniques and strategies including imaging were diverse and depended on many factors. These included aspects of motion amplitude, tumour location, as well as accelerator technology driving the necessity of centre-specific dosimetric validation. Novel methodologies for X-ray based image processing and MRI for real-time tumour tracking and motion management were shown to have a large potential for online and offline adaptation schemes compensating for potential anatomical changes over the treatment course. The latest research developments were dominated by particle imaging, artificial intelligence methods and FLASH adding another level of complexity but also opportunities in the context of 4D treatments.

Conclusion

This review showed that the rapid technological advances in radiation oncology together with the available intrafractional motion management and adaptive strategies paved the way towards clinical implementation.

Deep learning based uncertainty prediction of deformable image registration for contour propagation and dose accumulation in online adaptive radiotherapy

Objective.Online adaptive radiotherapy aims to fully leverage the advantages of highly conformal therapy by reducing anatomical and set-up uncertainty, thereby alleviating the need for robust treatments. This requires extensive automation, among which is the use of deformable image registration (DIR) for contour propagation and dose accumulation. However, inconsistencies in DIR solutions between different algorithms have caused distrust, hampering its direct clinical use. This work aims to enable the clinical use of DIR by developing deep learning methods to predict DIR uncertainty and propagating it into clinically usable metrics.Approach.Supervised and unsupervised neural networks were trained to predict the Gaussian uncertainty of a given deformable vector field (DVF). Since both methods rely on different assumptions, their predictions differ and were further merged into a combined model. The resulting normally distributed DVFs can be directly sampled to propagate the uncertainty into contour and accumulated dose uncertainty.Main results.The unsupervised and combined models can accurately predict the uncertainty in the manually annotated landmarks on the DIRLAB dataset. Furthermore, for 5 patients with lung cancer, the propagation of the predicted DVF uncertainty into contour uncertainty yielded for both methods anexpected calibration errorof less than 3%. Additionally, theprobabilisticly accumulated dose volume histograms(DVH) encompass well the accumulated proton therapy doses using 5 different DIR algorithms. It was additionally shown that the unsupervised model can be used for different DIR algorithms without the need for retraining.Significance.Our work presents first-of-a-kind deep learning methods to predict the uncertainty of the DIR process. The methods are fast, yield high-quality uncertainty estimates and are useable for different algorithms and applications. This allows clinics to use DIR uncertainty in their workflows without the need to change their DIR implementation.

Detectability of Anatomical Changes With Prompt-Gamma Imaging: First Systematic Evaluation of Clinical Application During Prostate-Cancer Proton Therapy

PURPOSE

The development of online-adaptive proton therapy (PT) is essential to overcome limitations encountered by day-to-day variations of the patient's anatomy. Range verification could play an essential role in an online feedback loop for the detection of treatment deviations such as anatomical changes. Here, we present the results of the first systematic patient study regarding the detectability of anatomical changes by a prompt-gamma imaging (PGI) slit-camera system.

METHODS AND MATERIALS

For 15 patients with prostate cancer, PGI measurements were performed during 105 fractions (201 fields) with in-room control computed tomography (CT)acquisitions. Field-wise doses on control CT scans were manually classified as whether showing relevant or non-relevant anatomical changes. This manual classification of the treatment fields was then used to establish an automatic field-wise ground truth based on spot-wise dosimetric range shifts, which were retrieved from integrated depth-dose (IDD) profiles. To determine the detection capability of anatomical changes with PGI, spot-wise PGI-based range shifts were initially compared with corresponding dosimetric IDD range shifts. As final endpoint, the agreement of a developed field-wise PGI classification model with the field-wise ground truth was determined. Therefore, the PGI model was optimized and tested for a subcohort of 131 and 70 treatment fields, respectively.

RESULTS

The correlation between PGI and IDD range shifts was high, ρpearson = 0.67 (p < 0.01). Field-wise binary PGI classification resulted in an area under the curve of 0.72 and 0.80 for training and test cohorts, respectively. The model detected relevant anatomical changes in the independent test cohort, with a sensitivity and specificity of 74% and 79%, respectively.

CONCLUSIONS

For the first time, evidence of the detection capability of anatomical changes in prostate-cancer PT from clinically acquired PGI data is shown. This emphasizes the benefit of PGI-based range verification and demonstrates its potential for online-adaptive PT.

Comparing Predicted Toxicities between Hypofractionated Proton and Photon Radiotherapy of Liver Cancer Patients with Different Adaptive Schemes

With the availability of MRI linacs, online adaptive intensity modulated radiotherapy (IMRT) has become a treatment option for liver cancer patients, often combined with hypofractionation. Intensity modulated proton therapy (IMPT) has the potential to reduce the dose to healthy tissue, but it is particularly sensitive to changes in the beam path and might therefore benefit from online adaptation. This study compares the normal tissue complication probabilities (NTCPs) for liver and duodenal toxicity for adaptive and non-adaptive IMRT and IMPT treatments of liver cancer patients. Adaptive and non-adaptive IMRT and IMPT plans were optimized to 50 Gy (RBE = 1.1 for IMPT) in five fractions for 10 liver cancer patients, using the original MRI linac images and physician-drawn structures. Three liver NTCP models were used to predict radiation-induced liver disease, an increase in albumin-bilirubin level, and a Child-Pugh score increase of more than 2. Additionally, three duodenal NTCP models were used to predict gastric bleeding, gastrointestinal (GI) toxicity with grades >3, and duodenal toxicity grades 2-4. NTCPs were calculated for adaptive and non-adaptive IMRT and IMPT treatments. In general, IMRT showed higher NTCP values than IMPT and the differences were often significant. However, the differences between adaptive and non-adaptive treatment schemes were not significant, indicating that the NTCP benefit of adaptive treatment regimens is expected to be smaller than the expected difference between IMRT and IMPT.

Dosimetric comparison of autocontouring techniques for online adaptive proton therapy

Objective.Anatomical and daily set-up uncertainties impede high precision delivery of proton therapy. With online adaptation, the daily plan is reoptimized on an image taken shortly before the treatment, reducing these uncertainties and, hence, allowing a more accurate delivery. This reoptimization requires target and organs-at-risk (OAR) contours on the daily image, which need to be delineated automatically since manual contouring is too slow. Whereas multiple methods for autocontouring exist, none of them are fully accurate, which affects the daily dose. This work aims to quantify the magnitude of this dosimetric effect for four contouring techniques.Approach.Plans reoptimized on automatic contours are compared with plans reoptimized on manual contours. The methods include rigid and deformable registration (DIR), deep-learning based segmentation and patient-specific segmentation.Main results.It was found that independently of the contouring method, the dosimetric influence of usingautomaticOARcontoursis small (<5% prescribed dose in most cases), with DIR yielding the best results. Contrarily, the dosimetric effect of using theautomatic target contourwas larger (>5% prescribed dose in most cases), indicating that manual verification of that contour remains necessary. However, when compared to non-adaptive therapy, the dose differences caused by automatically contouring the target were small and target coverage was improved, especially for DIR.Significance.The results show that manual adjustment of OARs is rarely necessary and that several autocontouring techniques are directly usable. Contrarily, manual adjustment of the target is important. This allows prioritizing tasks during time-critical online adaptive proton therapy and therefore supports its further clinical implementation.

Emerging technologies for cancer therapy using accelerated particles

Cancer therapy with accelerated charged particles is one of the most valuable biomedical applications of nuclear physics. The technology has vastly evolved in the past 50 years, the number of clinical centers is exponentially growing, and recent clinical results support the physics and radiobiology rationale that particles should be less toxic and more effective than conventional X-rays for many cancer patients. Charged particles are also the most mature technology for clinical translation of ultra-high dose rate (FLASH) radiotherapy. However, the fraction of patients treated with accelerated particles is still very small and the therapy is only applied to a few solid cancer indications. The growth of particle therapy strongly depends on technological innovations aiming to make the therapy cheaper, more conformal and faster. The most promising solutions to reach these goals are superconductive magnets to build compact accelerators; gantryless beam delivery; online image-guidance and adaptive therapy with the support of machine learning algorithms; and high-intensity accelerators coupled to online imaging. Large international collaborations are needed to hasten the clinical translation of the research results.

Research progress on deep learning in magnetic resonance imaging-based diagnosis and treatment of prostate cancer: a review on the current status and perspectives

Multiparametric magnetic resonance imaging (mpMRI) has emerged as a first-line screening and diagnostic tool for prostate cancer, aiding in treatment selection and noninvasive radiotherapy guidance. However, the manual interpretation of MRI data is challenging and time-consuming, which may impact sensitivity and specificity. With recent technological advances, artificial intelligence (AI) in the form of computer-aided diagnosis (CAD) based on MRI data has been applied to prostate cancer diagnosis and treatment. Among AI techniques, deep learning involving convolutional neural networks contributes to detection, segmentation, scoring, grading, and prognostic evaluation of prostate cancer. CAD systems have automatic operation, rapid processing, and accuracy, incorporating multiple sequences of multiparametric MRI data of the prostate gland into the deep learning model. Thus, they have become a research direction of great interest, especially in smart healthcare. This review highlights the current progress of deep learning technology in MRI-based diagnosis and treatment of prostate cancer. The key elements of deep learning-based MRI image processing in CAD systems and radiotherapy of prostate cancer are briefly described, making it understandable not only for radiologists but also for general physicians without specialized imaging interpretation training. Deep learning technology enables lesion identification, detection, and segmentation, grading and scoring of prostate cancer, and prediction of postoperative recurrence and prognostic outcomes. The diagnostic accuracy of deep learning can be improved by optimizing models and algorithms, expanding medical database resources, and combining multi-omics data and comprehensive analysis of various morphological data. Deep learning has the potential to become the key diagnostic method in prostate cancer diagnosis and treatment in the future.

Global democratisation of proton radiotherapy

Proton radiotherapy is an advanced treatment option compared with conventional x-ray treatment, delivering much lower doses of radiation to healthy tissues surrounding the tumour. However, proton therapy is currently not widely available. In this Review, we summarise the evolution of proton therapy to date, together with the benefits to patients and society. These developments have led to an exponential growth in the number of hospitals using proton radiotherapy worldwide. However, the gap between the number of patients who should be treated with proton radiotherapy and those who have access to it remains large. We summarise the ongoing research and development that is contributing to closing this gap, including the improvement of treatment efficiency and efficacy, and advances in fixed-beam treatments that do not require an enormously large, heavy, and costly gantry. The ultimate goal of decreasing the size of proton therapy machines to fit into standard treatment rooms appears to be within reach, and we discuss future research and development opportunities to achieve this goal.