Personalizing radiotherapy with adaptive radiotherapy: Interest and challenges.

Adaptive radiotherapy (ART) is a recent development in radiotherapy technology and treatment personalization that allows treatment to be tailored to the daily anatomical changes of patients. While it was until recently only performed "offline", i.e. between two radiotherapy sessions, it is now possible during ART to perform a daily online adaptive process for a given patient. Therefore, ART allows a daily customization to ensure optimal coverage of the treatment target volumes with minimized margins, taking into account only the uncertainties related to the adaptive process itself. This optimization appears particularly relevant in case of daily variations in the positioning of the target volume or of the organs at risk (OAR) associated with a proximity of these volumes and a tenuous therapeutic index. ART aims to minimize severe acute and late toxicity and allows tumor dose escalation. These new achievements have been possible thanks to technological development, the contribution of new multimodal and onboard imaging modalities and the integration of artificial intelligence tools for the contouring, planning and delivery of radiation therapy. Online ART is currently available on two types of radiotherapy machines: MR-linear accelerators and recently CBCT-linear accelerators. We will first describe the benefits, advantages, constraints and limitations of each of these two modalities, as well as the online adaptive process itself. We will then evaluate the clinical situations for which online adaptive radiotherapy is particularly indicated on MR- and CBCT-linear accelerators. Finally, we will detail some challenges and possible solutions in the development of online ART in the coming years.

Large Pleural Metastases With Significant Inter-fractional Volume Reduction During Online Adaptive Radiotherapy: A Case Report With Dosimetry Comparison.

Online adaptive radiotherapy (oART) dose calculation relies on synthetic computed tomography (sCT), which notably influences anatomical changes. This study elucidates how sCT may respond to significant inter-fractional tumor volume reduction and its subsequent impact on dose distribution. In this case report, we exported sCT and cone-beam CT (CBCT) images from each treatment session. We retrospectively analyzed 20 adaptive and scheduled plans of a patient receiving oART for large pleural metastases with notable inter-fractional tumor regression. By overriding the CT number of the dissipated tumor volume with that of the lungs on each sCT, we recalculated each plan. We compared the dose distribution between the adaptive and scheduled plans. Percentage dose difference and 3D gamma analysis were employed to assess dose variability. Results of the dose analysis showed that, compared to the online (non-overridden) plans, the recalculated plans using overridden sCT demonstrated right-shifted dose-volume histogram curves for the targets and right lung, with a slight but statistically significant increase of no less than 1.5% in D mean and D max for the targets and right lung. The location of hotspots shifted in alignment with tumor shrinkage and beam arrangement. Both recalculated adaptive and scheduled plans achieved ideal GTV, CTV, and PTV coverage, with adaptive plans significantly reducing the dose and irradiated volume to the right lung. In conclusion, as the pleural tumor volume decreased, online plans slightly underestimated the dose distribution and shifted the location of hotspots, though this remained clinically acceptable. Importantly, adaptive plans significantly minimized the irradiated volume of the critical OAR (right lung) while ensuring optimal dose coverage of the target volume, demonstrating the potential of sCT and adaptive oART to enhance treatment precision and efficacy in dynamically changing tumor environments.

Multiple Abdominal Desmoplastic Small Round-Cell Tumors Treated With Fan Beam Computed Tomography-Guided Adaptive Radiotherapy (FBCT-gART): A Case Report.

Desmoplastic small round cell tumor (DSRCT) is a rare and highly aggressive soft tissue tumor that predominantly affects the abdominal and pelvic regions of adolescent males. This case report presents our clinical experience of treating a 33-year-old male with multifocal peritoneal DSRCT using fan beam computed tomography-guided adaptive radiotherapy (FBCT-gART). The patient presented with abdominal pain and was diagnosed with DSRCT following imaging and biopsy. Despite initial treatment with surgery, chemotherapy, and targeted therapy, the patient experienced multifocal peritoneal recurrence. Due to the considerable mobility of the abdominal tumors and the associated risks to adjacent critical organs, the patient underwent daily online FBCT-gART. The prescribed dose regimen was 54 Gy delivered in 27 fractions at 2 Gy per fraction; however, the patient ultimately received only 25 treatments for personal reasons. This case report evaluates the technical workflow of using FBCT-gART for DSRCT and discusses its dosimetric advantages over non-adaptive radiotherapy.

Efficacy of Online Adaptive Radiotherapy Using Surface Guidance in Treatment of Tracheal Adenoid Cystic Carcinoma.

Primary tracheal tumors are rare, with adenoid cystic carcinoma (ACC) of the trachea being the second most common malignancy of the trachea. Radical surgical resection is found to have better survival outcomes in tracheal ACC. However, with higher submucosal spread rates in tracheal ACC and the inability to achieve clear margins, complete resection is not usually achievable. In these cases, the use of a 60-70 Gy radiation dose is deemed to be sufficient for definitive treatment with or without concurrent chemotherapy. We report a case of an unresectable ACC treated with online daily adaptive cone beam computed tomography (CBCT) radiotherapy on Ethos™ (Varian Medical Systems, Palo Alto, CA). She was planned to receive 59.4 Gy in 33 fractions in two phases. For daily treatment delivery, the patient was set up on the couch using the surface-guided radiotherapy (SGRT) system of AlignRT™ (Vision RT Ltd., London, UK) and translated to the treatment isocenter. A CBCT scan was acquired, followed by rigid registration with the planning scan and PET CT. Organs at risk (OAR) and primary targets were auto-generated by the AI in a two-step process, reviewed, and edited by the radiation oncologist. Adapted and scheduled plans were compared regarding planning target volume (PTV) coverage and dose to OAR. Better PTV coverage was seen in 26 of 33 fractions with the adapted plan. On the days with lesser coverage, adapted plans demonstrated improvement in the hotspot reduction and reduction in hard dose constraints of the esophagus and lungs. Hence, adapted plans were selected for all treatment days. Our results highlight the superior target coverage and improved OAR-sparing plans in daily online adaptive radiotherapy (o-ART) compared to image-guided radiotherapy (IGRT) plans. The system's ability to adapt to daily anatomical changes, improved target coverage, and better sparing of OARs make it an encouraging option for malignancies requiring motion management.

Incorporating patient-specific information for the development of rectal tumor auto-segmentation models for online adaptive magnetic resonance Image-guided radiotherapy.

Background and purpose: In online adaptive magnetic resonance image (MRI)-guided radiotherapy (MRIgRT), manual contouring of rectal tumors on daily images is labor-intensive and time-consuming. Automation of this task is complex due to substantial variation in tumor shape and location between patients. The aim of this work was to investigate different approaches of propagating patient-specific prior information to the online adaptive treatment fractions to improve deep-learning based auto-segmentation of rectal tumors. Materials and methods: 243 T2-weighted MRI scans of 49 rectal cancer patients treated on the 1.5T MR-Linear accelerator (MR-Linac) were utilized to train models to segment rectal tumors. As benchmark, an MRI_only auto-segmentation model was trained. Three approaches of including a patient-specific prior were studied: 1. include the segmentations of fraction 1 as extra input channel for the auto-segmentation of subsequent fractions, 2. fine-tuning of the MRI_only model to fraction 1 (PSF_1) and 3. fine-tuning of the MRI_only model on all earlier fractions (PSF_cumulative). Auto-segmentations were compared to the manual segmentation using geometric similarity metrics. Clinical impact was assessed by evaluating post-treatment target coverage. Results: All patient-specific methods outperformed the MRI_only segmentation approach. Median 95th percentile Hausdorff (95HD) were 22.0 (range: 6.1-76.6) mm for MRI_only segmentation, 9.9 (range: 2.5-38.2) mm for MRI+prior segmentation, 6.4 (range: 2.4-17.8) mm for PSF_1 and 4.8 (range: 1.7-26.9) mm for PSF_cumulative. PSF_cumulative was found to be superior to PSF_1 from fraction 4 onward (p = 0.014). Conclusion: Patient-specific fine-tuning of automatically segmented rectal tumors, using images and segmentations from all previous fractions, yields superior quality compared to other auto-segmentation approaches.

Clinical implementation of real time motion management for prostate SBRT: A radiation therapist's perspective.

Background and purpose: The adoption of hypo-fractionated stereotactic body radiotherapy (SBRT) for treating prostate cancer has led to an increase in specialised techniques for monitoring prostate motion. The aim of this study was to comprehensively review a radiation therapist (RTT) led treatment process in which two such systems were utilised, and present initial findings on their use within a SBRT prostate clinical trial. Materials and Methods: 18 patients were investigated, nine were fitted with the Micropos RayPilotTM (RP) system (Micropos Medical, Gothenburg, SE) and nine were fitted with the Micropos Raypilot Hypocath TM (HC) system. 36.25 Gray (Gy) was delivered in 5 fractions over 7 days with daily pre- and post-treatment cone beam computed tomography (CBCT) images acquired. Acute toxicity was reported on completion of treatment at six- and 12-weeks post-treatment, using the Radiation Therapy Oncology Group (RTOG) grading system and vertical (Vrt), longitudinal (Lng) and lateral (Lat) transmitter displacements recorded. Results: A significant difference was found in the Lat displacement between devices (P=0.003). A more consistent bladder volume was reported in the HC group (68.03 cc to 483.7 cc RP, 196.11 cc to 313.85 cc HC). No significant difference was observed in mean dose to the bladder, rectum and bladder dose maximum between the groups. Comparison of the rectal dose maximum between the groups reported a significant result (P=0.09). Comparing displacements with toxicity endpoints identified two significant correlations: Grade 2 Genitourinary (GU) at 6 weeks, P=0.029; and no toxicity, Gastrointestinal (GI) at 12 weeks P=0.013. Conclusion: Both the directly implanted RP device and the urinary catheter-based HC device are capable of real time motion monitoring. Here, the HC system was advantageous in the SBRT prostate workflow.

Dose tracking assessment for magnetic resonance guided adaptive radiotherapy of rectal cancers.

BACKGROUND: Magnetic resonance-guided adaptive radiotherapy (MRgART) at MR-Linac allows for plan optimisation on the MR-based synthetic CT (sCT) images, adjusting the target and organs at risk according to the patient's daily anatomy. Conversely, conventional linac image-guided radiotherapy (IGRT) involves rigid realignment of regions of interest to the daily anatomy, followed by the delivery of the reference computed tomography (CT) plan. This study aims to evaluate the effectiveness of MRgART versus IGRT for rectal cancer patients undergoing short-course radiotherapy, while also assessing the dose accumulation process to support the findings and determine its usefulness in enhancing treatment accuracy. METHODS: Nineteen rectal cancer patients treated with a 1.5 Tesla MR-Linac with a prescription dose of 25 Gy (5 Gy x 5) and undergoing daily adapted radiotherapy by plan optimization based on online MR-based sCT images, were included in this retrospective study. For each adapted plan ([Formula: see text]), a second plan ([Formula: see text]) was generated by recalculating the reference CT plan on the daily MR-based sCT images after rigid registration with the reference CT images to simulate the IGRT workflow. Dosimetry of [Formula: see text] and[Formula: see text]was compared for each fraction. Cumulative doses on the first and last fractions were evaluated for both workflows. The dosimetry per single fraction and the cumulative doses were compared using dose-volume histogram parameters. RESULTS: Ninety-five fractions delivered with MRgART were compared to corresponding simulated IGRT fractions. All MRgART fractions fulfilled the target clinical requirements. IGRT treatments did not meet the expected target coverage for 63 out of 94 fractions (67.0%), with 13 fractions showing a V95 median point percentage decrease of 2.78% (range, 1.65-4.16%), and 55 fractions exceeding the V107% threshold with a median value of 15.4 cc (range, 6.0-43.8 cc). For the bladder, the median [Formula: see text] values were 18.18 Gy for the adaptive fractions and 19.60 Gy for the IGRT fractions. Similarly the median [Formula: see text] values for the small bowel were 23.40 Gy and 25.69 Gy, respectively. No statistically significant differences were observed in the doses accumulated on the first or last fraction for the adaptive workflow, with results consistent with the single adaptive fractions. In contrast, accumulated doses in the IGRT workflow showed significant variations mitigating the high dose constraint, nevertheless, more than half of the patients still did not meet clinical requirements. CONCLUSIONS: MRgART for short-course rectal cancer treatments ensures that the dose delivered matches each fraction of the planned dose and the results are confirmed by the dose accumulation process, which therefore seems redundant. In contrast, IGRT may lead to target dose discrepancies and non-compliance with organs at risk constraints and dose accumulation can still highlight notable dosimetric differences.

Implementation of Cone Beam Computed Tomography-Guided Online Adaptive Radiotherapy for Challenging Trimodal Therapy in Bladder Preservation: A Report of Two Cases.

Muscle invasive bladder cancer (MIBC) is an aggressive disease with a high risk of metastasis. Bladder preservation with trimodality therapy (TMT) is an option for well-selected patients or poor cystectomy candidates. Cone beam computed tomography (CBCT)-guided online adaptive radiotherapy (oART) shows promise in improving the dose to treatment targets while better sparing organs at risk (OARs). The following series presents two cases in which the capabilities of a CBCT-guided oART platform were leveraged to meet clinical challenges. The first case describes a patient with synchronous MIBC and high-risk prostate cancer with challenging target-OAR interfaces. The second recounts the case of a patient with a history of low dose rate (LDR) brachytherapy to the prostate who was later diagnosed with MIBC and successfully treated with CBCT-guided oART with reduced high-dose volume bladder targeting. To date, both patients report minimal side effects and are without disease recurrence. These cases illustrate how CBCT-guided online adaptive systems may efficiently aid radiation oncologists in treating patients with more complex clinical scenarios who desire bladder-sparing therapy.

Enhancing Precision in Radiation Therapy for Locally Advanced Lung Cancer: A Case Study of Cone-Beam Computed Tomography (CBCT)-Based Online Adaptive Techniques and the Promise of HyperSight™ Iterative CBCT.

This study explores the dosimetric benefits of cone-beam computed tomography (CBCT)-based online adaptive radiation therapy (oART) for a non-small-cell lung cancer (NSCLC) patient exhibiting significant tumor shrinkage during ChemoRT. The patient was prescribed 60 Gray (Gy) in 30 fractions and was initially treated with conventional RT. After the delivery of the first four treatment fractions, the patient's treatment course was converted to oART due to tumor shrinkage seen on CBCT. Current oART dose calculations use a synthetic CT (sCT) image derived from deformable image registration (DIR) of the planning CT to the daily CBCT, and, as the tumor regressed, the discrepancy between the CBCT and the sCT increased, leading to a re-simulation after the delivery of the ninth fraction. In this case report, we first investigated dosimetric differences leveraged by converting this patient from conventional RT to oART. With oART using sCT, the patient's target coverage remained consistent with the reference plan while simultaneously changing lung V20 by 7.8 ± 1.4% and heart mean by 3.4 ± 1.5 Gy. Then, using this new simulation CT and comparing it with iterative CBCT (iCBCT) images acquired with the new HyperSight™ (HS) (Varian Medical Systems, Inc., Palo Alto, CA, USA) imaging system on the Ethos, we investigated the impact of direct dose calculation on HS-iCBCT as compared to sCT. The HS-iCBCT generated a dose distribution similar to the CT reference, achieving a 96.01% gamma passing rate using Task Group-218 (TG-218) criteria. Results indicate that HS-iCBCT has the potential to better reflect daily anatomical changes, resulting in improved dosimetric accuracy. This study highlights the advantages of oART in the presence of tumor response to therapy and underscores HS-iCBCT's potential to provide CT-level dose calculation accuracy in oART for NSCLC patients.

Feasibility of simulation free abdominal stereotactic adaptive radiotherapy using an expedited pre-plan workflow.

Background and Purpose: Improved hounsfield-unit accuracy of on-board imaging may lead to direct-to-unit treatment approaches We aimed to demonstrate the feasibility of using only a diagnostic (dx) computed tomography (CT)-defined target pre-plan in an in silico study of simulation-free abdominal stereotactic adaptive radiotherapy (ART). Materials and Methods: Eight patients with abdominal treatment sites (five pancreatic cancer, three oligometastases) were treated using an integrated adaptive O-Ring gantry system. Each patient's target was delineated on a dxCT. The target only pre-plan served primarily to seed the ART process. During the ART session, all structures were delineated. All simulated cases were treated to 50 Gy in 5 fractions to a planning target optimization structure (PTV_OPT) to allow for dose escalation within the planning target volume. Timing of steps during this workflow was recorded. Plan quality was compared between ART treatment plans and a plan created on a CT simulation scan using the traditional planning workflow. Results: The workflow was feasible in all attempts, with organ-at-risk (OAR) constraints met in all fractions despite lack of initial OAR contours. Median absolute difference between the adapted plan and simulation CT plan for the PTV_Opt V95% was 2.0 %. Median absolute difference in the D0.5 cm3 between the adapted plan and simulation CT plan was -0.9 Gy for stomach, 1.2 Gy for duodenum, -5.3 Gy for small bowel, and 0.3 Gy for large bowel. Median end-to-end workflow time was 63 min. Conclusion: The workflow was feasible for a dxCT-defined target-only pre-plan approach to stereotactic abdominal ART.

Efficacy and safety of MR-guided adaptive simultaneous integrated boost radiotherapy to primary lesions and positive lymph nodes in the neoadjuvant treatment of locally advanced rectal cancer: a randomized controlled phase III trial.

BACKGROUND: In locally advanced rectal cancer (LARC), optimizing neoadjuvant strategies, including the addition of concurrent chemotherapy and dose escalation of radiotherapy, is essential to improve tumor regression and subsequent implementation of anal preservation strategies. Currently, dose escalation studies in rectal cancer have focused on the primary lesions. However, a common source of recurrence in LARC is the metastasis of cancer cells to the proximal lymph nodes. In our trial, we implement simultaneous integrated boost (SIB) to both primary lesions and positive lymph nodes in the experimental group based on magnetic resonance-guided adaptive radiotherapy (MRgART), which allows for more precise (and consequently intense) targeting while sparing neighboring healthy tissue. The objective of this study is to evaluate the efficacy and safety of MRgART dose escalation to both primary lesions and positive lymph nodes, in comparison with the conventional radiotherapy of long-course concurrent chemoradiotherapy (LCCRT) group, in the neoadjuvant treatment of LARC. METHODS: This is a multi-center, randomized, controlled phase III trial (NCT06246344). 128 patients with LARC (cT3-4/N+) will be enrolled. During LCCRT, patients will be randomized to receive either MRgART with SIB (60-65 Gy in 25-28 fractions to primary lesions and positive lymph nodes; 50-50.4 Gy in 25-28 fractions to the pelvis) or intensity-modulated radiotherapy (50-50.4 Gy in 25-28 fractions). Both groups will receive concurrent chemotherapy with capecitabine and consolidation chemotherapy of either two cycles of CAPEOX or three cycles of FOLFOX between radiotherapy and surgery. The primary endpoints are pathological complete response (pCR) rate and surgical difficulty, while the secondary endpoints are clinical complete response (cCR) rate, 3-year and 5-year disease-free survival (DFS) and overall survival (OS) rates, acute and late toxicity and quality of life. DISCUSSION: Since dose escalation of both primary lesions and positive nodes in LARC is rare, we propose conducting a phase III trial to evaluate the efficacy and safety of SIB for both primary lesions and positive nodes in LARC based on MRgART. TRIAL REGISTRATION: The study was registered at ClinicalTrials.gov with the Identifier: NCT06246344 (Registered 7th Feb 2024).

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.

CT-Guided Online Adaptive Hypofractionated Radiotherapy for Primary Bladder Cancer: A Report of Two Cases.

Trimodality treatment for bladder cancer, consisting of maximal transurethral resection of the tumor followed by concurrent chemoradiotherapy, is an attractive management option with curative and organ-sparing intent. However, such treatment can be associated with acute toxicities related to the large treatment margins required due to daily variation in bladder filling, with resultant bladder, bowel, and rectal toxicity. Adaptive radiation, which accounts for inter-fraction variations in bladder size, allows the confident delivery of radiation to bladder cancer with smaller margins, with the potential to reduce toxicities without the associated risk of compromising the target coverage. Herein, we present a case series of two patients with primary bladder cancer who were treated with computed tomography (CT)-based online adaptive hypofractionated radiotherapy using the Ethos system (Varian Medical Systems, Palo Alto, CA, USA). The first is an 83-year-old male with a remote history of prostate cancer treated with radiotherapy, who received adaptive radiotherapy as a means of decreasing the required margin size and optimizing planning based on adjacent bowel to reduce the risk of re-irradiation. The second patient is a 78-year-old male with node-positive bladder cancer, which necessitated whole pelvis radiotherapy, who underwent adaptive treatment (25 fractions) as a means of sparing cumulative dose to the bowel while ensuring suitable target coverage. In both cases, the clinical target volume consisted of the entire bladder (± nodes) with a planning target volume expansion of 7 mm. During treatment, daily cone-beam CT scans were acquired and used to generate adapted plans. These plans were compared to the original plans, with attention to target coverage and dose to organs at risk. For all 45 fractions, the adaptive plan was selected, primarily as a means of improving target coverage. This case series demonstrates that the adaptive Ethos system effectively delivers treatment for primary bladder cancer. Further data are needed for clinical toxicity outcomes and the efficacy of this approach.

Prior-image-based low-dose CT reconstruction for adaptive radiation therapy.

OBJECTIVE: The study aims to reduce the imaging radiation dose in Adaptive Radiotherapy (ART) while maintaining high-quality CT images, critical for effective treatment planning and monitoring. APPROACH: We developed the Prior-aware Learned Primal-Dual Network (pLPD-UNet), which uses prior CT images to enhance reconstructions from low-dose scans. The network was separately trained on thorax and abdomen datasets to accommodate the unique imaging requirements of each anatomical region. MAIN RESULTS: The pLPD-UNet demonstrated improved reconstruction accuracy and robustness in handling sparse data compared to traditional methods. It effectively maintained image quality essential for precise organ delineation and dose calculation, while achieving a significant reduction in radiation exposure. SIGNIFICANCE: This method offers a significant advancement in the practice of ART by integrating prior imaging data, potentially setting a new standard for balancing radiation safety with the need for high-resolution imaging in cancer treatment planning.

Solution for the External Contour Changes in Cone Beam Computed Tomography-Guided On-demand Online Adaptive Radiotherapy for a Patient With Very Advanced Head and Neck Cancer: A Technical Case Report.

This article presents a case of a patient with advanced head and neck cancer, characterized by a large and protruding tumor. The patient was treated with an innovative on-demand online adaptive radiotherapy (ART) technology, guided by cone beam computed tomography (CBCT), on the Ethos adaptive radiotherapy platform (version 1.0, Varian Medical Systems, Palo Alto, CA). A solution was provided for this special case to address the issue where part of the target volume could not participate in the optimization due to exceeding the external contour boundary during online adaptive radiotherapy. The treatment outcome was satisfactory in terms of tumor regression, while only grade 1 radiodermatitis and grade 2 oral mucositis at the end of radiotherapy. This article discusses the clinical diagnosis, treatment process, and follow-up of this case, aiming to provide clinical references for a broader application of this technology.

Machine learning automated treatment planning for online magnetic resonance guided adaptive radiotherapy of prostate cancer.

Background and purpose: No best practices currently exist for achieving high quality radiation therapy (RT) treatment plan adaptation during magnetic resonance (MR) guided RT of prostate cancer. This study validates the use of machine learning (ML) automated RT treatment plan adaptation and benchmarks it against current clinical RT plan adaptation methods. Materials and methods: We trained an atlas-based ML automated treatment planning model using reference MR RT treatment plans (42.7 Gy in 7 fractions) from 46 patients with prostate cancer previously treated at our institution. For a held-out test set of 38 patients, retrospectively generated ML RT plans were compared to clinical human-generated adaptive RT plans for all 266 fractions. Differences in dose-volume metrics and clinical objective pass rates were evaluated using Wilcoxon tests (p < 0.05) and Exact McNemar tests (p < 0.05), respectively. Results: Compared to clinical RT plans, ML RT plans significantly increased sparing and objective pass rates of the rectum, bladder, and left femur. The mean ± standard deviation of rectum D20 and D50 in ML RT plans were 2.5 ± 2.2 Gy and 1.6 ± 1.3 Gy lower than clinical RT plans, respectively, with 14 % higher pass rates; bladder D40 was 4.6 ± 2.9 Gy lower with a 20 % higher pass rate; and the left femur D5 was 0.8 ± 1.8 Gy lower with a 7 % higher pass rate. Conclusions: ML automated RT treatment plan adaptation increases robustness to interfractional anatomical changes compared to current clinical adaptive RT practices by increasing compliance to treatment objectives.

Dosimetric advantages of adaptive IMPT vs. Enhanced workload and treatment time - A need for automation.

INTRODUCTION: In head-and-neck IMPT, trigger-based offline plan adaptation (Offlinetrigger-based) is often used. Our goal was to compare this to four alternative adaptive strategies for dosimetry, workload and treatment time, considering also foreseen further technological advancements, including anticipated automation. MATERIALS AND METHODS: Alternative strategies included weekly offline re-planning (Offlineweekly), daily plan selection from a library (Librarystatic and Libraryprogsressive) and a fast, approximate daily online re-optimization approach (Onlinere-opt). Impact on CTV coverage and NTCPs was assessed by simulations based on repeat-CTs from 15 patients. Full daily re-planning was used as dosimetric benchmark. Increases in workload and treatment time were estimated. RESULTS: Both for coverage and NTCPs, fast Onlinere-opt performed as well as full re-planning. Compared to current practice, Onlinere-opt showed enhanced probabilities for high coverage, and resulted in reductions in grade ≥ II NTCPs of 4.6 ±â€¯1.7 %-point for xerostomia and 4.2 ±â€¯2.3 %-point for dysphagia. Offlineweekly and library strategies did not show coverage enhancements and resulted in smaller NTCP improvements. Further automation can largely limit workload and treatment time increases. With anticipated further automation, adaptation-related workload of Offlineweekly, Librarystatic, Libraryprogressive, and Onlinere-opt was expected to increase by 3, 8, 21, and 66 h for 35 fraction treatment courses compared to Offlinetrigger-based. The corresponding adaptation-related prolonged treatment times were estimated to be 0, 4, 6, and 29 min/fraction. CONCLUSION: Online adaptive strategies could approach dosimetric quality of full re-planning at the cost of additional workload and prolonged treatment time compared to the current offline adaptive strategy. Automation needs to play a key role in making more complex adaptive approaches feasible.

A patient-specific auto-planning method for MRI-guided adaptive radiotherapy in prostate cancer.

BACKGROUND AND PURPOSE: Fast and automated generation of treatment plans is desirable for magnetic resonance imaging (MRI)-guided adaptive radiotherapy (MRIgART). This study proposed a novel patient-specific auto-planning method and validated its feasibility in improving the existing online planning workflow. MATERIALS AND METHODS: Data from 40 patients with prostate cancer were collected retrospectively. A patient-specific auto-planning method was proposed to generate adaptive treatment plans. First, a population dose-prediction model (M0) was trained using data from previous patients. Second, a patient-specific model (Mps) was created for each new patient by fine-tuning M0 with the patient's data. Finally, an auto plan was optimized using the parameters derived from the predicted dose distribution by Mps. The auto plans were compared with manual plans in terms of plan quality, efficiency, dosimetric verification, and clinical evaluation. RESULTS: The auto plans improved target coverage, reduced irradiation to the rectum, and provided comparable protection to other organs-at-risk. Target coverage for the planning target volume (+0.61 %, P = 0.023) and clinical target volume 4000 (+1.60 %, P < 0.001) increased. V2900cGy (-1.06 %, P = 0.004) and V1810cGy (-2.49 %, P < 0.001) to the rectal wall and V1810cGy (-2.82 %, P = 0.012) to the rectum were significantly reduced. The auto plans required less planning time (-3.92 min, P = 0.001), monitor units (-46.48, P = 0.003), and delivery time (-0.26 min, P = 0.004), and their gamma pass rates (3 %/2 mm) were higher (+0.47 %, P = 0.014). CONCLUSION: The proposed patient-specific auto-planning method demonstrated a robust level of automation and was able to generate high-quality treatment plans in less time for MRIgART in prostate cancer.

Potential anatomical triggers for plan adaptation of cervical cancer external beam radiotherapy.

This study aimed to identify potential anatomical variation triggers using magnetic resonance imaging for plan adaption of cervical cancer patients to ensure dose requirements were met over an external beam radiotherapy course. Magnetic resonance images (MRIs) acquired before and during treatment were rigidly registered to a pre-treatment computerised tomography (CT) image for 11 retrospective cervix cancer datasets. Target volumes (TVs) and organs at risk (OARs) were delineated on both MRIs and propagated onto the CT. Treatment plans were generated based on the pre-treatment contours and applied to the mid-treatment contours. Anatomical and dosimetric changes between each timepoint were assessed. The anatomical changes included the change in centroid position and volume size. Dosimetric changes included the V30Gy and V40Gy for the OARs, and V95%, V100%, D95% and D98% for the TVs. Correlation with dosimetric and anatomical changes were assessed to determine potential replan triggers. Changes in the bowel volume and position in the superior-inferior direction, and the high-risk CTV anterior posterior position were highly correlated with a change in dose to the bowel and target, respectively. Hence changes in bowel and high-risk CTV could be used as a potential replan triggers.

Harnessing the Power of Radiotherapy for Lung Cancer: A Narrative Review of the Evolving Role of Magnetic Resonance Imaging Guidance.

Compared with computed tomography (CT), magnetic resonance imaging (MRI) traditionally plays a very limited role in lung cancer management, although there is plenty of room for improvement in the current CT-based workflow, for example, in structures such as the brachial plexus and chest wall invasion, which are difficult to visualize with CT alone. Furthermore, in the treatment of high-risk tumors such as ultracentral lung cancer, treatment-associated toxicity currently still outweighs its benefits. The advent of MR-Linac, an MRI-guided radiotherapy (RT) that combines MRI with a linear accelerator, could potentially address these limitations. Compared with CT-based technologies, MR-Linac could offer superior soft tissue visualization, daily adaptive capability, real-time target tracking, and an early assessment of treatment response. Clinically, it could be especially advantageous in the treatment of central/ultracentral lung cancer, early-stage lung cancer, and locally advanced lung cancer. Increasing demands for stereotactic body radiotherapy (SBRT) for lung cancer have led to MR-Linac adoption in some cancer centers. In this review, a broad overview of the latest research on imaging-guided radiotherapy (IGRT) with MR-Linac for lung cancer management is provided, and development pertaining to artificial intelligence is also highlighted. New avenues of research are also discussed.