Minimizing human interference in an online fully automated daily adaptive radiotherapy workflow for bladder cancer.

PURPOSE: The aim was to study the potential for an online fully automated daily adaptive radiotherapy (RT) workflow for bladder cancer, employing a focal boost and fiducial markers. The study focused on comparing the geometric and dosimetric aspects between the simulated automated online adaptive RT (oART) workflow and the clinically performed workflow. METHODS: Seventeen patients with muscle-invasive bladder cancer were treated with daily Cone Beam CT (CBCT)-guided oART. The bladder and pelvic lymph nodes (CTVelective) received a total dose of 40 Gy in 20 fractions and the tumor bed received an additional simultaneously integrated boost (SIB) of 15 Gy (CTVboost). During the online sessions a CBCT was acquired and used as input for the AI-network to automatically delineate the bladder and rectum, i.e. influencers. These influencers were employed to guide the algorithm utilized in the delineation process of the target. Manual adjustments to the generated contours are common during this clinical workflow prior to plan reoptimization and RT delivery. To study the potential for an online fully automated workflow, the oART workflow was repeated in a simulation environment without manual adjustments. A comparison was made between the clinical and automatic contours and between the treatment plans optimized on these clinical (Dclin) and automatic contours (Dauto). RESULTS: The bladder and rectum delineated by the AI-network differed from the clinical contours with a median Dice Similarity Coefficient of 0.99 and 0.92, a Mean Distance to Agreement of 1.9 mm and 1.3 mm and a relative volume of 100% and 95%, respectively. For the CTVboost these differences were larger, namely 0.71, 7 mm and 78%. For the CTVboost the median target coverage was 0.42% lower for Dauto compared to Dclin. For CTVelective this difference was 0.03%. The target coverage of Dauto met the clinical requirement of the CTV-coverage in 65% of the sessions for CTVboost and 95% of the sessions for the CTVelective. CONCLUSIONS: While an online fully automated daily adaptive RT workflow shows promise for bladder treatment, its complexity becomes apparent when incorporating a focal boost, necessitating manual checks to prevent potential underdosage of the target.

Radio-opaque contrast agents for liver cancer targeting with KIM during radiation therapy (ROCK-RT): an observational feasibility study.

BACKGROUND: This observational study aims to establish the feasibility of using x-ray images of radio-opaque chemoembolisation deposits in patients as a method for real-time image-guided radiation therapy of hepatocellular carcinoma. METHODS: This study will recruit 50 hepatocellular carcinoma patients who have had or will have stereotactic ablative radiation therapy and have had transarterial chemoembolisation with a radio-opaque agent. X-ray and computed tomography images of the patients will be analysed retrospectively. Additionally, a deep learning method for real-time motion tracking will be developed. We hypothesise that: (i) deep learning software can be developed that will successfully track the contrast agent mass on two thirds of cone beam computed tomography (CBCT) projection and intra-treatment images (ii), the mean and standard deviation (mm) difference in the location of the mass between ground truth and deep learning detection are ≤ 2 mm and ≤ 3 mm respectively and (iii) statistical modelling of study data will predict tracking success in 85% of trial participants. DISCUSSION: Developing a real-time tracking method will enable increased targeting accuracy, without the need for additional invasive procedures to implant fiducial markers. TRIAL REGISTRATION: Registered to ClinicalTrials.gov (NCT05169177) 12th October 2021.

Modeling of artificial intelligence-based respiratory motion prediction in MRI-guided radiotherapy: a review.

The advancement of precision radiotherapy techniques, such as volumetric modulated arc therapy (VMAT), stereotactic body radiotherapy (SBRT), and particle therapy, highlights the importance of radiotherapy in the treatment of cancer, while also posing challenges for respiratory motion management in thoracic and abdominal tumors. MRI-guided radiotherapy (MRIgRT) stands out as state-of-art real-time respiratory motion management approach owing to the non-ionizing radiation nature and superior soft-tissue contrast characteristic of MR imaging. In clinical practice, MR imaging often operates at a frequency of 4 Hz, resulting in approximately a 300 ms system latency of MRIgRT. This system latency decreases the accuracy of respiratory motion management in MRIgRT. Artificial intelligence (AI)-based respiratory motion prediction has recently emerged as a promising solution to address the system latency issues in MRIgRT, particularly for advanced contour prediction and volumetric prediction. However, implementing AI-based respiratory motion prediction faces several challenges including the collection of training datasets, the selection of prediction methods, and the formulation of complex contour and volumetric prediction problems. This review presents modeling approaches of AI-based respiratory motion prediction in MRIgRT, and provides recommendations for achieving consistent and generalizable results in this field.

Scalp dose analysis for transient and permanent alopecia following conventional cranial irradiation using Image Guided Radiotherapy (IGRT): A prospective study.

PURPOSE: The dosimetry of scalp dose was prospectively studied and correlated with alopecia following conventional cranial irradiation in primary brain tumors patients. MATERIALS AND METHODS: Patients with primary brain tumors who required conventional radiotherapy were enrolled. A hairline marker was applied to the patient's scalp to identify the entire scalp region. The maximal dose to 2% volume of interest (D2) for the entire scalp region were obtained. The radiation dosages at the localized hair-loss areas were evaluated during the final week of RT (transient alopecia) and six months after completing RT (permanent alopecia). Kruskal-Wallis tests were used to compare the dosimetric parameter values with statistical significance set as p < 0.05. RESULTS: Forty-eight patients were included in the analysis. The prescribed radiation doses ranged from 50.4 to 60.0 Gy. Thirty-two patients experienced alopecia (27 transient and 5 permanent). The median D2 values adjusted for the entire scalp were higher in the alopecia group (38.40 Gy for transient alopecia and 47.84 Gy for permanent alopecia vs 11.90 Gy for no alopecia, p < 0.001). The D2 value was determined as a predictive parameter for alopecia. The threshold values for transient and permanent alopecia over the entire scalp were 22.15 Gy and 36.81 Gy, respectively. At the localized hair-loss areas, the D2 values for transient and permanent alopecia were higher at 44.82 Gy and 50.00 Gy, respectively. The radiation intensity at the localized hair-loss areas was also related to the severity of alopecia, with D2 values of 35.14 Gy and 46.39 Gy for clinically assigned grade 1 and grade 2 transient alopecia, respectively, with the D2 value being even higher for permanent alopecia. CONCLUSIONS: The D2 parameter value could be used to predict the type and severity of alopecia.

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.

Weekly Image Guidance in Patients With Cervical Cancer Treated With Intensity-Modulated Radiation Therapy: Results of a Large Cohort Study.

BACKGROUND: Image guidance is recommended for patients undergoing intensity-modulated radiation therapy (IMRT) for cervical cancer. In this study, we evaluated the feasibility of a weekly image guidance pattern and analyzed the long-term outcomes in a large cohort of patients. METHODS: The study enrolled patients with Stage IB-IVA cervical cancer who received definitive radiotherapy or concurrent chemoradiotherapy. IMRT was delivered at a dose of 50.4 Gy in 28 fractions, with weekly cone-beam computed tomography (CBCT). Physicians advised patients on rectum and bladder preparation to help them prepare on nonimaging guidance days. When significant tumor regression was observed, a second computed tomography simulation and replanning were performed. RESULTS: The median follow-up periods were 63.4 months. The incidence rates of loco-regional and distant failure were 9.9% and 13.6%. The 5-year overall survival (OS), disease-free survival (DFS), loco-regional relapse-free survival (LRFS), and distant metastasis-free survival (DMFS) rates were 80.1%, 72.9%, 78.3%, and 74.8%, respectively. For patients with different stages, the 5-year OS, DFS, LRFS, and DMFS rates were statistically significant. For patients with and without positive regional lymph nodes, the 5-year OS, DFS, LRFS, and DMFS rates were 64.5% and 86.0%, 56.8% and 78.8%, 62.7% and 84.3%, and 58.8% and 81.0%, respectively. Multivariate analysis showed that age, histology, tumor size, cancer stage, pretreatment squamous cell carcinoma antigen level, and para-aortic metastatic lymph nodes were independent prognostic factors of OS. Fifty-six (4.0%) patients experienced late Grade 3/4 chronic toxicities. CONCLUSIONS: IMRT with weekly CBCT is an acceptable image guidance strategy in countries with limited medical resources.

Clinical outcomes analysis of image-guided brachytherapy as definitive treatment for inoperable endometrial cancer.

OBJECTIVES: This study evaluates the efficacy and toxicity of image-guided brachytherapy combined with or without external beam radiotherapy (IGBT ± EBRT) as definitive treatment for patients with inoperable endometrial cancer (IOEC), in addition to establishing a risk classification to predict prognosis. METHODS: Fifty-one IOEC patients who underwent IGBT ± EBRT at Peking Union Medical College Hospital from January 2012 to December 2021 were retrospectively analyzed, of which 42 patients (82.4%) were treated with IGBT + EBRT and 9 patients (17.6%) with IGBT alone. Establishing risk classification based on FIGO 2009 staging and biopsy pathology, stage III/IV, non-endometrioid, or Grade 3 endometrioid cancer were included in the high-risk group (n = 25), and stage I/II with Grade 1-2 endometrioid cancer was included in the low-risk group (n = 26). RESULTS: The median follow-up time was 58.0 months (IQR, 37.0-69.0). Clinical complete remission (CR) was achieved in 92.2% of patients after radiotherapy (n = 47). The cumulative incidences of locoregional and distant failure were 19.6% (n = 10) and 7.8% (n = 4), respectively. A total of 20 patients died (39.2%), including 10 cancer-related deaths (19.6%) and 10 comorbidity-related deaths (19.6%). The 5-year locoregional control (LRC), time to progression (TTP), overall survival (OS), and cancer-specific survival (CSS) were 76.9%, 71.2%, 59.4%, and 77.0%, respectively. No Grade 3 or above acute or late toxicities were reported. In univariate analysis, LRC, TTP, and CSS were significantly higher in the low-risk group than in the high-risk group (P < 0.05). After adjusting for age, number of comorbidities, radiotherapy modality, and chemotherapy, the low-risk group was still significantly better than the high-risk group in terms of LRC (HR = 6.10, 95% CI: 1.18-31.45, P = 0.031), TTP (HR = 8.07, 95% CI: 1.64-39.68, P = 0.010) and CSS (HR = 6.29, 95% CI: 1.19-33.10, P = 0.030). CONCLUSIONS: IGBT ± EBRT is safe and effective as definitive treatment for IOEC patients, achieving satisfactory locoregional control, favorable survival outcomes, and low toxicity. Risk classification based on FIGO 2009 staging and biopsy pathology is an independent prognostic factor for LRC, TTP, and CSS.

The accuracy of cone beam computed tomography (CBCT) technique as an image-guided radiation therapy (IGRT) technique.

OBJECTIVE: To measure the setup error of the patient's positioning using cone-beam computed tomography during radiation therapy treatment fractions by finding systematic, random errors and the planned target volume errors. METHODS: The observational, longitudinal cohort study was conducted at the Al-Warith International Cancer Institute, Karbala, Iraq, from January to May 2022, and comprised patients with head and neck cancer who underwent radiation therapy. The oncologist delineated and the medical physicist planned. Then the medical physicist modified the positioning system using the cone beam computed tomography option workstation. The vertical value was taken in anteroposterior site, longitudinal in superoinferior, and lateral in e mediolateral. The SPSS 25 were used to analyse data. RESULTS: Of the 31 patients, 17(54.8%) were females and 14(45.2%) were males. The overall mean age was 48.3 ± 10.22 (range: 4-77 years), and 22(70.96%) patients had been treated previously with chemotherapy. The lateral shifting inaccuracy 2.501mm was above the limit, whereas the vertical shifting 1.164mm was within acceptable limits (±2mm). The longitudinal shifting had the smallest displacement 0.436mm. Random error displayed longitudinal moving 1.965mm, lateral shifting 0.623mm and vertical shifting 0.276mm. The planned target volume margins were too wide in longitudinal shifting 3.333mm. Vertical shifting 0.481mm was greater than lateral 1.092mm, but both were within limits (±2mm). CONCLUSIONS: Radiation-induced errors in normal tissues must be reduced by reducing planned target volume margins, especially for longitudinal and lateral directions.

Dual convolution-transformer UNet (DCT-UNet) for organs at risk and clinical target volume segmentation in MRI for cervical cancer brachytherapy.

Objective. MRI is the standard imaging modality for high-dose-rate brachytherapy of cervical cancer. Precise contouring of organs at risk (OARs) and high-risk clinical target volume (HR-CTV) from MRI is a crucial step for radiotherapy planning and treatment. However, conventional manual contouring has limitations in terms of accuracy as well as procedural time. To overcome these, we propose a deep learning approach to automatically segment OARs (bladder, rectum, and sigmoid colon) and HR-CTV from female pelvic MRI.Approach. In the proposed pipeline, a coarse multi-organ segmentation model first segments all structures, from which a region of interest is computed for each structure. Then, each organ is segmented using an organ-specific fine segmentation model separately trained for each organ. To account for variable sizes of HR-CTV, a size-adaptive multi-model approach was employed. For coarse and fine segmentations, we designed a dual convolution-transformer UNet (DCT-UNet) which uses dual-path encoder consisting of convolution and transformer blocks. To evaluate our model, OAR segmentations were compared to the clinical contours drawn by the attending radiation oncologist. For HR-CTV, four sets of contours (clinical + three additional sets) were obtained to produce a consensus ground truth as well as for inter/intra-observer variability analysis.Main results. DCT-UNet achieved dice similarity coefficient (mean ± SD) of 0.932 ± 0.032 (bladder), 0.786 ± 0.090 (rectum), 0.663 ± 0.180 (sigmoid colon), and 0.741 ± 0.076 (HR-CTV), outperforming other state-of-the-art models. Notably, the size-adaptive multi-model significantly improved HR-CTV segmentation compared to a single-model. Furthermore, significant inter/intra-observer variability was observed, and our model showed comparable performance to all observers. Computation time for the entire pipeline per subject was 12.59 ± 0.79 s, which is significantly shorter than the typical manual contouring time of >15 min.Significance. These experimental results demonstrate that our model has great utility in cervical cancer brachytherapy by enabling fast and accurate automatic segmentation, and has potential in improving consistency in contouring. DCT-UNet source code is available athttps://github.com/JHU-MICA/DCT-UNet.

Investigation of intrafractional spinal cord and spinal canal movement during stereotactic MR-guided online adaptive radiotherapy for kidney cancer.

BACKGROUND AND PURPOSE: This study aimed to investigate the intrafractional movement of the spinal cord and spinal canal during MR-guided online adaptive radiotherapy (MRgART) for kidney cancer. MATERIALS AND METHODS: All patients who received stereotactic MRgART for kidney cancer between February 2022 and February 2024 were included in this study. Patients received 30-42 Gy in 3-fraction MRgART for kidney cancer using the Elekta Unity, which is equipped with a linear accelerator and a 1.5 Tesla MRI. MRI scans were performed at three points during each fraction: for online planning, position verification, and posttreatment assessment. The spinal cord was contoured from the upper edge of Th12 to the medullary cone, and the spinal canal was contoured from Th12 to L3, using the first MRI. These contours were adjusted to the second and third MR images via deformable image registration, and movements were measured. Margins were determined via the formula "1.3×Σ+0.5×σ" and 95% prediction intervals. RESULTS: A total of 22 patients (66 fractions) were analyzed. The median interval between the first and third MRI scans were 38 minutes. The mean ± standard deviation of the spinal cord movements after this interval were -0.01 ± 0.06 for the x-axis (right-left), 0.01 ± 0.14 for the y-axis (caudal-cranial), 0.07 ± 0.05 for the z-axis (posterior-anterior), and 0.15 ± 0.08 for the 3D distance, respectively. The correlation coefficients of the 3D distance between the spinal cord and the spinal canal was high (0.92). The calculated planning organ at risk volume margin for all directions was 0.11 cm for spinal cord. The 95% prediction intervals for the x-axis, y-axis, and z-axis were -0.11-0.09 cm, -0.23-0.25 cm and -0.14-0.03 cm, respectively. CONCLUSIONS: Margins are necessary in MRgART to compensate for intrafractional movement and ensure safe treatment delivery.

Optimisation of cone beam CT radiotherapy imaging protocols using a novel 3D printed head and neck anthropomorphic phantom.

Objective.This study aimed to optimise Cone Beam Computed Tomography (CBCT) protocols for head and neck (H&N) radiotherapy treatments using a 3D printed anthropomorphic phantom. It focused on precise patient positioning in conventional treatment and adaptive radiotherapy (ART).Approach.Ten CBCT protocols were evaluated with the 3D-printed H&N anthropomorphic phantom, including one baseline protocol currently used at our centre and nine new protocols. Adjustments were made to milliamperage and exposure time to explore their impact on radiation dose and image quality. Additionally, the effect on image quality of varying the scatter correction parameter for each of the protocols was assessed. Each protocol was compared against a reference CT scan. Usability was assessed by three Clinical Scientists using a Likert scale, and statistical validation was performed on the findings.Main results. The work revealed variability in the effectiveness of protocols. Protocols optimised for lower radiation exposure maintained sufficient image quality for patient setup in a conventional radiotherapy pathway, suggesting the potential for reducing patient radiation dose by over 50% without compromising efficacy. Optimising ART protocols involves balancing accuracy across brain, bone, and soft tissue, as no single protocol or scatter correction parameter achieves optimal results for all simultaneously.Significance.This study underscores the importance of optimising CBCT protocols in H&N radiotherapy. Our findings highlight the potential to maintain the usability of CBCT for bony registration in patient setup while significantly reducing the radiation dose, emphasizing the significance of optimising imaging protocols for the task in hand (registering to soft tissue or bone) and aligning with the as low as reasonably achievable principle. More studies are needed to assess these protocols for ART, including CBCT dose measurements and CT comparisons. Furthermore, the novel 3D printed anthropomorphic phantom demonstrated to be a useful tool when optimising CBCT protocols.

Deep learning-based automatic contour quality assurance for auto-segmented abdominal MR-Linac contours.

Objective.Deep-learning auto-segmentation (DLAS) aims to streamline contouring in clinical settings. Nevertheless, achieving clinical acceptance of DLAS remains a hurdle in abdominal MRI, hindering the implementation of efficient clinical workflows for MR-guided online adaptive radiotherapy (MRgOART). Integrating automated contour quality assurance (ACQA) with automatic contour correction (ACC) techniques could optimize the performance of ACC by concentrating on inaccurate contours. Furthermore, ACQA can facilitate the contour selection process from various DLAS tools and/or deformable contour propagation from a prior treatment session. Here, we present the performance of novel DL-based 3D ACQA models for evaluating DLAS contours acquired during MRgOART.Approach.The ACQA model, based on a 3D convolutional neural network (CNN), was trained using pancreas and duodenum contours obtained from a research DLAS tool on abdominal MRIs acquired from a 1.5 T MR-Linac. The training dataset contained abdominal MR images, DL contours, and their corresponding quality ratings, from 103 datasets. The quality of DLAS contours was determined using an in-house contour classification tool, which categorizes contours as acceptable or edit-required based on the expected editing effort. The performance of the 3D ACQA model was evaluated using an independent dataset of 34 abdominal MRIs, utilizing confusion matrices for true and predicted classes.Main results.The ACQA predicted 'acceptable' and 'edit-required' contours at 72.2% (91/126) and 83.6% (726/868) accuracy for pancreas, and at 71.2% (79/111) and 89.6% (772/862) for duodenum contours, respectively. The model successfully identified false positive (extra) and false negative (missing) DLAS contours at 93.75% (15/16) and %99.7 (438/439) accuracy for pancreas, and at 95% (57/60) and 98.9% (91/99) for duodenum, respectively.Significance.We developed 3D-ACQA models capable of quickly evaluating the quality of DLAS pancreas and duodenum contours on abdominal MRI. These models can be integrated into clinical workflow, facilitating efficient and consistent contour evaluation process in MRgOART for abdominal malignancies.

Preliminary study of feasibility of surface-guided radiotherapy with concurrent tumor treating fields for glioblastoma: region of interest.

OBJECTIVE: To evaluate the impact of the residual setup errors from differently shaped region of interest (ROI) and investigate if surface-guided setup can be used in radiotherapy with concurrent tumor treating fields (TTFields) for glioblastoma. METHODS: Fifteen patients undergone glioblastoma radiotherapy with concurrent TTFields were involved. Firstly, four shapes of region of interest (ROI) (strip-shaped, T-shaped, ⊥ -shaped and cross-shaped) with medium size relative to the whole face were defined dedicate for patients wearing TTFields transducer arrays. Then, ROI-shape-dependent residual setup errors in six degrees were evaluated using an anthropomorphic head and neck phantom taking CBCT data as reference. Finally, the four types of residual setup errors were converted into corresponding dosimetry deviations (including the target coverage and the organ at risk sparing) of the fifteen radiotherapy plans using a feasible and robust geometric-transform-based method. RESULTS: The algebraic sum of the average residual setup errors in six degrees (mm in translational directions and ° in rotational directions) of the four types were 6.9, 1.1, 4.1 and 3.5 respectively. In terms of the ROI-shape-dependent dosimetry deviations, the D98% of PTV dropped off by (3.4 ± 2.0)% (p < 0.05), (0.3 ± 0.5)% (p < 0.05), (0.9 ± 0.9)% (p < 0.05) and (1.1 ± 0.8)% (p < 0.05). The D98% of CTV dropped off by (0.5 ± 0.6)% (p < 0.05) for the strip-shaped ROI while remained unchanged for others. CONCLUSION: Surface-guided setup is feasible in radiotherapy with concurrent TTFields and a medium-sized T-shaped ROI is appropriate for the surface-based guidance.

Magnetic Resonance-Guided Cancer Therapy Radiomics and Machine Learning Models for Response Prediction.

Magnetic resonance imaging (MRI) is known for its accurate soft tissue delineation of tumors and normal tissues. This development has significantly impacted the imaging and treatment of cancers. Radiomics is the process of extracting high-dimensional features from medical images. Several studies have shown that these extracted features may be used to build machine-learning models for the prediction of treatment outcomes of cancer patients. Various feature selection techniques and machine models interrogate the relevant radiomics features for predicting cancer treatment outcomes. This study aims to provide an overview of MRI radiomics features used in predicting clinical treatment outcomes with machine learning techniques. The review includes examples from different disease sites. It will also discuss the impact of magnetic field strength, sample size, and other characteristics on outcome prediction performance.

Adapting outside the box: Simulation-free MR-guided stereotactic ablative radiotherapy for prostate cancer.

BACKGROUND AND PURPOSE: Magnetic resonance (MR)-guided radiotherapy (MRgRT) enhances treatment precision and adaptive capabilities, potentially supporting a simulation-free (sim-free) workflow. This work reports the first clinical implementation of a sim-free workflow using the MR-Linac for prostate cancer patients treated with stereotactic ablative radiotherapy (SABR). MATERIALS AND METHODS: Fifteen patients who had undergone a prostate-specific membrane antigen positron emission tomography/CT (PSMA-PET/CT) scan as part of diagnostic workup were included in this work. Two reference plans were generated per patient: one using PSMA-PET/CT (sim-free plan) and the other using standard simulation CT (simCT plan). Dosimetric evaluations included comparisons between simCT, sim-free, and first fraction plans. Timing measurements were conducted to assess durations for both simCT and sim-free pre-treatment workflows. RESULTS: All 15 patients underwent successful treatment using a sim-free workflow. Dosimetric differences between simCT, sim-free, and first fraction plans were minor and within acceptable clinical limits, with no major violations of standardised criteria. The sim-free workflow took on average 130 min, while the simCT workflow took 103 min. CONCLUSION: This work demonstrates the feasibility and benefits of sim-free MR-guided adaptive radiotherapy for prostate SABR, representing the first reported clinical experience in an ablative setting. By eliminating traditional simulation scans, this approach reduces patient burden by minimising hospital visits and enhances treatment accessibility.

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.

The Dose Difference of Dominant Intraprostatic Lesions (DILs) Defined by Magnetic Resonance-Guided and arc-based Intensity Modulated Radiation Therapy (IMRT), and the Association between Dose Difference and Recurrent Prostate Cancer.

BACKGROUND: There is growing evidence that local recurrence after radiotherapy often occurs within the dominant intraprostatic lesions (DILs) in prostate cancer. This study aimed to evaluate the dose difference between DILs defined by Magnetic Resonance-guided and arc-based Intensity Modulated Radiation Therapy (IMRT) and to assess the association between the dose difference and biochemical recurrence-free survival. MATERIALS AND METHODS: Between 2015 and 2019, 48 prostate cancer patients with DILs visible from multiparametric Magnetic Resonance Imaging (mpMRI) underwent arc-based IMRT with 70 Gy (2.5 Gy each fraction) to the prostate gland. Pretreatment mpMRI DILs contoured the prostate gland retrospectively. RESULTS: Biochemical recurrence was 8.3%. There was a significant difference between the median dose of DILs from MRI-guided imaging, 69.22 Gy, and the median dose of the whole prostate from arc-based IMRT which was 67.09 Gy (p < 0.001*). The Kaplan-Meier survival curve compared by log-rank test showed an escalation dose of at least 2 Gy tends to improve biochemical recurrence-free survival. However, this tendency did not reach statistical significance (p = 0.2). CONCLUSIONS: The dose distribution within DILs defined by mpMRI is significantly higher than the whole prostate dose from arc-based IMRT. Escalation doses in DILs tend to improve biochemical recurrence-free survival, further validation in larger patient cohorts with extended follow-up is warranted.

Proton dose calculation with LSTM networks in presence of a magnetic field.

Objective.To present a long short-term memory (LSTM) network-based dose calculation method for magnetic resonance (MR)-guided proton therapy.Approach.35 planning computed tomography (CT) images of prostate cancer patients were collected for Monte Carlo (MC) dose calculation under a perpendicular 1.5 T magnetic field. Proton pencil beams (PB) at three energies (150, 175, and 200 MeV) were simulated (7560 PBs at each energy). A 3D relative stopping power cuboid covering the extent of the PB dose was extracted and given as input to the LSTM model, yielding a 3D predicted PB dose. Three single-energy (SE) LSTM models were trained separately on the corresponding 150/175/200 MeV datasets and a multi-energy (ME) LSTM model with an energy embedding layer was trained on either the combined dataset with three energies or a continuous energy (CE) dataset with 1 MeV steps ranging from 125 to 200 MeV. For each model, training and validation involved 25 patients and 10 patients were for testing. Two single field uniform dose prostate treatment plans were optimized and recalculated with MC and the CE model.Results.Test results of all PBs from the three SE models showed a mean gamma passing rate (2%/2 mm, 10% dose cutoff) above 99.9% with an average center-of-mass (COM) discrepancy below 0.4 mm between predicted and simulated trajectories. The ME model showed a mean gamma passing rate exceeding 99.8% and a COM discrepancy of less than 0.5 mm at the three energies. Treatment plan recalculation by the CE model yielded gamma passing rates of 99.6% and 97.9%. The inference time of the models was 9-10 ms per PB.Significance.LSTM models for proton dose calculation in a magnetic field were developed and showed promising accuracy and efficiency for prostate cancer patients.

Clinical Outcome Comparison between CT-Guided Versus all MRI-Guided Scenarios in Brachytherapy for Cervical Cancer: A Single-Institute Experience.

OBJECTIVES: Image-guided adaptive brachytherapy (IGABT) is the standard of care for patients with cervical cancer. The objective of this study was to compare the treatment outcomes and adverse effects of computed tomography (CT)-guided and magnetic resonance imaging (MRI)-guided scenarios. MATERIALS AND METHODS: Data of patients with cervical cancer treated using external beam radiotherapy followed by IGABT from 2012 to 2016 were retrospectively reviewed. CT-guided IGABT was compared with the three modes of MRI-guided IGABT: pre-brachytherapy (MRI Pre-BT) without applicator insertion for fusion, planning MRI with applicator in-place in at least 1 fraction (MRI ≥1Fx), and MRI in every fraction (MRI EveryFx). Patient characteristics, oncologic outcomes, and late radiation toxicity were analyzed using descriptive, survival, and correlation statistics. RESULTS: Overall, 354 patients were evaluated with a median follow-up of 60 months. The 5-year overall survival (OS) rates were 61.5%, 65.2%, 54.4%, and 63.7% with CT-guided, MRI PreBT, MRI ≥1Fx, and MRI EveryFx IGABT, respectively with no significant differences (p = 0.522). The 5-year local control (LC) rates were 92.1%, 87.8%, 80.7%, and 76.5% (p = 0.133), respectively, with a significant difference observed between the CT-guided and MRI ≥1Fx (p = 0.018). The grade 3-4 late gastrointestinal toxicity rates were 6% in the CT-guided, MRI ≥1Fx, and MRI EveryFx, and 8% in MRI PreBT. The grade 3-4 late genitourinary toxicity rates were 4% in the CT-guided, 2% in MRI PreBT, 1% in MRI ≥1Fx, and none in MRI EveryFx. No significant differences were observed in the oncologic and toxicity outcomes among MRI PreBT, MRI ≥1Fx, and MRI EveryFx. CONCLUSIONS: CT-guided IGABT yielded an acceptable 5-year OS, LC, and toxicity profile compared with all MRI scenarios and is a potentially feasible option in resource-limited settings.

A Machine Learning Approach for Predicting Biochemical Outcome After PSMA-PET-Guided Salvage Radiotherapy in Recurrent Prostate Cancer After Radical Prostatectomy: Retrospective Study.

BACKGROUND: Salvage radiation therapy (sRT) is often the sole curative option in patients with biochemical recurrence after radical prostatectomy. After sRT, we developed and validated a nomogram to predict freedom from biochemical failure. OBJECTIVE: This study aims to evaluate prostate-specific membrane antigen-positron emission tomography (PSMA-PET)-based sRT efficacy for postprostatectomy prostate-specific antigen (PSA) persistence or recurrence. Objectives include developing a random survival forest (RSF) model for predicting biochemical failure, comparing it with a Cox model, and assessing predictive accuracy over time. Multinational cohort data will validate the model's performance, aiming to improve clinical management of recurrent prostate cancer. METHODS: This multicenter retrospective study collected data from 13 medical facilities across 5 countries: Germany, Cyprus, Australia, Italy, and Switzerland. A total of 1029 patients who underwent sRT following PSMA-PET-based assessment for PSA persistence or recurrence were included. Patients were treated between July 2013 and June 2020, with clinical decisions guided by PSMA-PET results and contemporary standards. The primary end point was freedom from biochemical failure, defined as 2 consecutive PSA rises >0.2 ng/mL after treatment. Data were divided into training (708 patients), testing (271 patients), and external validation (50 patients) sets for machine learning algorithm development and validation. RSF models were used, with 1000 trees per model, optimizing predictive performance using the Harrell concordance index and Brier score. Statistical analysis used R Statistical Software (R Foundation for Statistical Computing), and ethical approval was obtained from participating institutions. RESULTS: Baseline characteristics of 1029 patients undergoing sRT PSMA-PET-based assessment were analyzed. The median age at sRT was 70 (IQR 64-74) years. PSMA-PET scans revealed local recurrences in 43.9% (430/979) and nodal recurrences in 27.2% (266/979) of patients. Treatment included dose-escalated sRT to pelvic lymphatics in 35.6% (349/979) of cases. The external outlier validation set showed distinct features, including higher rates of positive lymph nodes (47/50, 94% vs 266/979, 27.2% in the learning cohort) and lower delivered sRT doses (<66 Gy in 57/979, 5.8% vs 46/50, 92% of patients; P<.001). The RSF model, validated internally and externally, demonstrated robust predictive performance (Harrell C-index range: 0.54-0.91) across training and validation datasets, outperforming a previously published nomogram. CONCLUSIONS: The developed RSF model demonstrates enhanced predictive accuracy, potentially improving patient outcomes and assisting clinicians in making treatment decisions.