Diffeomorphic transformer-based abdomen MRI-CT deformable image registration.

BACKGROUND: Stereotactic body radiotherapy (SBRT) is a well-established treatment modality for liver metastases in patients unsuitable for surgery. Both CT and MRI are useful during treatment planning for accurate target delineation and to reduce potential organs-at-risk (OAR) toxicity from radiation. MRI-CT deformable image registration (DIR) is required to propagate the contours defined on high-contrast MRI to CT images. An accurate DIR method could lead to more precisely defined treatment volumes and superior OAR sparing on the treatment plan. Therefore, it is beneficial to develop an accurate MRI-CT DIR for liver SBRT. PURPOSE: To create a new deep learning model that can estimate the deformation vector field (DVF) for directly registering abdominal MRI-CT images. METHODS: The proposed method assumed a diffeomorphic deformation. By using topology-preserved deformation features extracted from the probabilistic diffeomorphic registration model, abdominal motion can be accurately obtained and utilized for DVF estimation. The model integrated Swin transformers, which have demonstrated superior performance in motion tracking, into the convolutional neural network (CNN) for deformation feature extraction. The model was optimized using a cross-modality image similarity loss and a surface matching loss. To compute the image loss, a modality-independent neighborhood descriptor (MIND) was used between the deformed MRI and CT images. The surface matching loss was determined by measuring the distance between the warped coordinates of the surfaces of contoured structures on the MRI and CT images. To evaluate the performance of the model, a retrospective study was carried out on a group of 50 liver cases that underwent rigid registration of MRI and CT scans. The deformed MRI image was assessed against the CT image using the target registration error (TRE), Dice similarity coefficient (DSC), and mean surface distance (MSD) between the deformed contours of the MRI image and manual contours of the CT image. RESULTS: When compared to only rigid registration, DIR with the proposed method resulted in an increase of the mean DSC values of the liver and portal vein from 0.850 ± 0.102 and 0.628 ± 0.129 to 0.903 ± 0.044 and 0.763 ± 0.073, a decrease of the mean MSD of the liver from 7.216 ± 4.513 mm to 3.232 ± 1.483 mm, and a decrease of the TRE from 26.238 ± 2.769 mm to 8.492 ± 1.058 mm. CONCLUSION: The proposed DIR method based on a diffeomorphic transformer provides an effective and efficient way to generate an accurate DVF from an MRI-CT image pair of the abdomen. It could be utilized in the current treatment planning workflow for liver SBRT.

Diffeomorphic Transformer-based Abdomen MRI-CT Deformable Image Registration.

Background: Stereotactic body radiotherapy (SBRT) is a well-established treatment modality for liver metastases in patients unsuitable for surgery. Both CT and MRI are useful during treatment planning for accurate target delineation and to reduce potential organs-at-risk (OAR) toxicity from radiation. MRI-CT deformable image registration (DIR) is required to propagate the contours defined on high-contrast MRI to CT images. An accurate DIR method could lead to more precisely defined treatment volumes and superior OAR sparing on the treatment plan. Therefore, it is beneficial to develop an accurate MRI-CT DIR for liver SBRT. Purpose: To create a new deep learning model that can estimate the deformation vector field (DVF) for directly registering abdominal MRI-CT images. Methods: The proposed method assumed a diffeomorphic deformation. By using topology-preserved deformation features extracted from the probabilistic diffeomorphic registration model, abdominal motion can be accurately obtained and utilized for DVF estimation. The model integrated Swin transformers, which have demonstrated superior performance in motion tracking, into the convolutional neural network (CNN) for deformation feature extraction. The model was optimized using a cross-modality image similarity loss and a surface matching loss. To compute the image loss, a modality-independent neighborhood descriptor (MIND) was used between the deformed MRI and CT images. The surface matching loss was determined by measuring the distance between the warped coordinates of the surfaces of contoured structures on the MRI and CT images. To evaluate the performance of the model, a retrospective study was carried out on a group of 50 liver cases that underwent rigid registration of MRI and CT scans. The deformed MRI image was assessed against the CT image using the target registration error (TRE), Dice similarity coefficient (DSC), and mean surface distance (MSD) between the deformed contours of the MRI image and manual contours of the CT image. Results: When compared to only rigid registration, DIR with the proposed method resulted in an increase of the mean DSC values of the liver and portal vein from 0.850±0.102 and 0.628±0.129 to 0.903±0.044 and 0.763±0.073, a decrease of the mean MSD of the liver from 7.216±4.513 mm to 3.232±1.483 mm, and a decrease of the TRE from 26.238±2.769 mm to 8.492±1.058 mm. Conclusion: The proposed DIR method based on a diffeomorphic transformer provides an effective and efficient way to generate an accurate DVF from an MRI-CT image pair of the abdomen. It could be utilized in the current treatment planning workflow for liver SBRT.

Adaptive Proton Therapy Using CBCT-Guided Digital Twins.

This study aims to develop a digital twin (DT) framework to enhance adaptive proton stereotactic body radiation therapy (SBRT) for prostate cancer. 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, with the goal of improving treatment quality, potentially revolutionizing prostate radiotherapy to offer personalized treatment solutions. Our study presented a pioneering approach that leverages DT technology to enhance adaptive proton SBRT. The framework improves treatment plans by utilizing patient-specific CTV setup uncertainty, which is usually smaller than conventional clinical setups. This research contributes to the ongoing efforts to enhance the efficiency and efficacy of prostate radiotherapy, with ultimate goals of improving patient outcomes and life quality.

Implementation of a Novel Chart Rounds Application to Facilitate Peer Review in a Virtual Academic Environment.

Purpose: Peer review in the form of chart rounds is a critical component of quality assurance and safety in radiation therapy treatments. Radiation therapy departments have undergone significant changes that impose challenges to meaningful review, including institutional growth and increasing use of virtual environment. We discuss the implementation of a novel chart rounds (NCR) format and application adapted to modern peer review needs at a single high-volume multisite National Cancer Institute designated cancer center. Methods and Materials: A working group was created to improve upon the prior institutional chart rounds format (standard chart rounds or SCR). Using a novel in-house application and format redesign, an NCR was created and implemented to accomplish stated goals. Data regarding the SCR and NCR system were then extracted for review. Results: SCR consisted of 2- 90-minute weekly sessions held to review plans across all disease sites, review of 49 plans per hour on average. NCR uses 1-hour long sessions divided by disease site, enabling additional time to be spent per patient (11 plans per hour on average) and more robust discussion. The NCR application is able to automate a list of plans requiring peer review from the institutional treatment planning system. The novel application incorporates features that enable efficient and accurate review of plans in the virtual setting across multiple sites. A systematic scoring system is integrated into the application to record feedback. Over 5 months of use of the NCR, 1160 plans have been reviewed with 143 scored as requiring minor changes, 32 requiring major changes and 307 with comments. Major changes triggered treatment replan. Feedback from scoring is incorporated into physician workflow to ensure changes are addressed. Conclusion: The presented NCR format and application enables standardized and highly reliable peer review of radiation therapy plans that is robust across a variety of complex planning scenarios and could be implemented globally.

Streamlined pin-ridge-filter design for single-energy proton FLASH planning.

BACKGROUND: FLASH radiotherapy (FLASH-RT) with ultra-high dose rate has yielded promising results in reducing normal tissue toxicity while maintaining tumor control. Planning with single-energy proton beams modulated by ridge filters (RFs) has been demonstrated feasible for FLASH-RT. PURPOSE: This study explored the feasibility of a streamlined pin-shaped RF (pin-RF) design, characterized by coarse resolution and sparsely distributed ridge pins, for single-energy proton FLASH planning. METHODS: An inverse planning framework integrated within a treatment planning system was established to design streamlined pin RFs for single-energy FLASH planning. The framework involves generating a multi-energy proton beam plan using intensity-modulated proton therapy (IMPT) planning based on downstream energy modulation strategy (IMPT-DS), followed by a nested pencil-beam-direction-based (PBD-based) spot reduction process to iteratively reduce the total number of PBDs and energy layers along each PBD for the IMPT-DS plan. The IMPT-DS plan is then translated into the pin-RFs and the single-energy beam configurations for IMPT planning with pin-RFs (IMPT-RF). This framework was validated on three lung cases, quantifying the FLASH dose of the IMPT-RF plan using the FLASH effectiveness model. The FLASH dose was then compared to the reference dose of a conventional IMPT plan to measure the clinical benefit of the FLASH planning technique. RESULTS: The IMPT-RF plans closely matched the corresponding IMPT-DS plans in high dose conformity (conformity index of <1.2), with minimal changes in V7Gy and V7.4 Gy for the lung (<3%) and small increases in maximum doses (Dmax) for other normal structures (<3.4 Gy). Comparing the FLASH doses to the doses of corresponding IMPT-RF plans, drastic reductions of up to nearly 33% were observed in Dmax for the normal structures situated in the high-to-moderate-dose regions, while negligible changes were found in Dmax for normal structures in low-dose regions. Positive clinical benefits were seen in comparing the FLASH doses to the reference doses, with notable reductions of 21.4%-33.0% in Dmax for healthy tissues in the high-dose regions. However, in the moderate-to-low-dose regions, only marginal positive or even negative clinical benefit for normal tissues were observed, such as increased lung V7Gy and V7.4 Gy (up to 17.6%). CONCLUSIONS: A streamlined pin-RF design was developed and its effectiveness for single-energy proton FLASH planning was validated, revealing positive clinical benefits for the normal tissues in the high dose regions. The coarsened design of the pin-RF demonstrates potential advantages, including cost efficiency and ease of adjustability, making it a promising option for efficient production.

Deep learning-based synthetic dose-weighted LET map generation for intensity modulated proton therapy.

The advantage of proton therapy as compared to photon therapy stems from the Bragg peak effect, which allows protons to deposit most of their energy directly at the tumor while sparing healthy tissue. However, even with such benefits, proton therapy does present certain challenges. The biological effectiveness differences between protons and photons are not fully incorporated into clinical treatment planning processes. In current clinical practice, the relative biological effectiveness (RBE) between protons and photons is set as constant 1.1. Numerous studies have suggested that the RBE of protons can exhibit significant variability. Given these findings, there is a substantial interest in refining proton therapy treatment planning to better account for the variable RBE. Dose-average linear energy transfer (LETd) is a key physical parameter for evaluating the RBE of proton therapy and aids in optimizing proton treatment plans. Calculating precise LETddistributions necessitates the use of intricate physical models and the execution of specialized Monte-Carlo simulation software, which is a computationally intensive and time-consuming progress. In response to these challenges, we propose a deep learning based framework designed to predict the LETddistribution map using the dose distribution map. This approach aims to simplify the process and increase the speed of LETdmap generation in clinical settings. The proposed CycleGAN model has demonstrated superior performance over other GAN-based models. The mean absolute error (MAE), peak signal-to-noise ratio and normalized cross correlation of the LETdmaps generated by the proposed method are 0.096 ± 0.019 keVµm-1, 24.203 ± 2.683 dB, and 0.997 ± 0.002, respectively. The MAE of the proposed method in the clinical target volume, bladder, and rectum are 0.193 ± 0.103, 0.277 ± 0.112, and 0.211 ± 0.086 keVµm-1, respectively. The proposed framework has demonstrated the feasibility of generating synthetic LETdmaps from dose maps and has the potential to improve proton therapy planning by providing accurate LETdinformation.

CBCT-Based synthetic CT image generation using conditional denoising diffusion probabilistic model.

BACKGROUND: Daily or weekly cone-beam computed tomography (CBCT) scans are commonly used for accurate patient positioning during the image-guided radiotherapy (IGRT) process, making it an ideal option for adaptive radiotherapy (ART) replanning. However, the presence of severe artifacts and inaccurate Hounsfield unit (HU) values prevent its use for quantitative applications such as organ segmentation and dose calculation. To enable the clinical practice of online ART, it is crucial to obtain CBCT scans with a quality comparable to that of a CT scan. PURPOSE: This work aims to develop a conditional diffusion model to perform image translation from the CBCT to the CT distribution for the image quality improvement of CBCT. METHODS: The proposed method is a conditional denoising diffusion probabilistic model (DDPM) that utilizes a time-embedded U-net architecture with residual and attention blocks to gradually transform the white Gaussian noise sample to the target CT distribution conditioned on the CBCT. The model was trained on deformed planning CT (dpCT) and CBCT image pairs, and its feasibility was verified in brain patient study and head-and-neck (H&N) patient study. The performance of the proposed algorithm was evaluated using mean absolute error (MAE), peak signal-to-noise ratio (PSNR) and normalized cross-correlation (NCC) metrics on generated synthetic CT (sCT) samples. The proposed method was also compared to four other diffusion model-based sCT generation methods. RESULTS: In the brain patient study, the MAE, PSNR, and NCC of the generated sCT were 25.99 HU, 30.49 dB, and 0.99, respectively, compared to 40.63 HU, 27.87 dB, and 0.98 of the CBCT images. In the H&N patient study, the metrics were 32.56 HU, 27.65 dB, 0.98 and 38.99 HU, 27.00, 0.98 for sCT and CBCT, respectively. Compared to the other four diffusion models and one Cycle generative adversarial network (Cycle GAN), the proposed method showed superior results in both visual quality and quantitative analysis. CONCLUSIONS: The proposed conditional DDPM method can generate sCT from CBCT with accurate HU numbers and reduced artifacts, enabling accurate CBCT-based organ segmentation and dose calculation for online ART.

Synthetic CT generation from MRI using 3D transformer-based denoising diffusion model.

BACKGROUND AND PURPOSE: Magnetic resonance imaging (MRI)-based synthetic computed tomography (sCT) simplifies radiation therapy treatment planning by eliminating the need for CT simulation and error-prone image registration, ultimately reducing patient radiation dose and setup uncertainty. In this work, we propose a MRI-to-CT transformer-based improved denoising diffusion probabilistic model (MC-IDDPM) to translate MRI into high-quality sCT to facilitate radiation treatment planning. METHODS: MC-IDDPM implements diffusion processes with a shifted-window transformer network to generate sCT from MRI. The proposed model consists of two processes: a forward process, which involves adding Gaussian noise to real CT scans to create noisy images, and a reverse process, in which a shifted-window transformer V-net (Swin-Vnet) denoises the noisy CT scans conditioned on the MRI from the same patient to produce noise-free CT scans. With an optimally trained Swin-Vnet, the reverse diffusion process was used to generate noise-free sCT scans matching MRI anatomy. We evaluated the proposed method by generating sCT from MRI on an institutional brain dataset and an institutional prostate dataset. Quantitative evaluations were conducted using several metrics, including Mean Absolute Error (MAE), Peak Signal-to-Noise Ratio (PSNR), Multi-scale Structure Similarity Index (SSIM), and Normalized Cross Correlation (NCC). Dosimetry analyses were also performed, including comparisons of mean dose and target dose coverages for 95% and 99%. RESULTS: MC-IDDPM generated brain sCTs with state-of-the-art quantitative results with MAE 48.825 ± 21.491 HU, PSNR 26.491 ± 2.814 dB, SSIM 0.947 ± 0.032, and NCC 0.976 ± 0.019. For the prostate dataset: MAE 55.124 ± 9.414 HU, PSNR 28.708 ± 2.112 dB, SSIM 0.878 ± 0.040, and NCC 0.940 ± 0.039. MC-IDDPM demonstrates a statistically significant improvement (with p < 0.05) in most metrics when compared to competing networks, for both brain and prostate synthetic CT. Dosimetry analyses indicated that the target dose coverage differences by using CT and sCT were within ± 0.34%. CONCLUSIONS: We have developed and validated a novel approach for generating CT images from routine MRIs using a transformer-based improved DDPM. This model effectively captures the complex relationship between CT and MRI images, allowing for robust and high-quality synthetic CT images to be generated in a matter of minutes. This approach has the potential to greatly simplify the treatment planning process for radiation therapy by eliminating the need for additional CT scans, reducing the amount of time patients spend in treatment planning, and enhancing the accuracy of treatment delivery.

Integration of Radiation Oncology Into the Preclinical Curriculum Through Problem-Based Learning.

PURPOSE: Early exposure to oncology care during the preclinical years of medical school may translate to increased student interest in oncology-related fields and improved understanding of oncologic treatment modalities, including radiation oncology. Many schools incorporate problem-based learning (PBL) into the medical school curriculum; this is an opportunity to immerse students in oncologic case management. We describe the effective incorporation of one course into the medical school curriculum that may be replicated at other institutions. METHODS AND MATERIALS: A PBL case regarding pancreatic cancer was created by a radiation oncology resident and faculty member in collaboration with the gastrointestinal course director for first-year medical students at a single institution. Pancreatic cancer was chosen based on curricular needs. Learning objectives were discussed to guide the creation of the case. RESULTS: All 140 first-year medical students participated in the 1-hour small group case focused on oncologic work up, multidisciplinary care, and radiation therapy concepts. Students were provided with a case prompt and resources to review prior to the PBL session. Volunteer radiation oncology facilitators attended a 30-minute educational meeting and were provided a detailed case guide 1 week before the PBL session. During the PBL case, facilitators guided students to achieve desired learning objectives. Among the 76 (54%) medical students who completed an optional post-PBL survey, the majority reported that the case motivated them to learn more about oncology (89%) and radiation oncology (82%). There was an increase in the number of subscribers to the Oncology Interest Group (43% increase from previous year) and preclinical students shadowing in the radiation oncology department. The PBL case was continued in future years for all first-year students and extended to 2 hours to promote additional discussion in response to student and facilitator feedback. CONCLUSIONS: A cancer-specific PBL case facilitated by radiation oncology educators is an effective avenue to integrate radiation oncology into the preclinical curriculum and stimulate interest in oncology among first-year medical students.

Proton liver stereotactic body radiation therapy: Treatment techniques and dosimetry feasibility from a single institution.

Purpose: To assess the resulting dosimetry characteristics of simulation and planning techniques for proton stereotactic body radiation therapy (SBRT) of primary and secondary liver tumors. Methods: Consecutive patients treated under volumetric daily image guidance with liver proton SBRT between September 2019 and March 2022 at Emory Proton Therapy Center were included in this study. Prescriptions ranged from 40 Gy to 60 Gy in 3- or 5-fraction regimens, and motion management techniques were used when target motion exceeded 5 mm. 4D robust optimization was used when necessary. Dosimetry evaluation was conducted for ITV V100, D99, Dmax, and liver-ITV mean dose and D700cc. Statistical analysis was performed using independent-samples Mann-Whitney U tests. Results: Thirty-six tumors from 29 patients were treated. Proton therapy for primary and secondary liver tumors using motion management techniques and robust optimization resulted in high target coverage and low doses to critical organs. The median ITV V100% was 100.0%, and the median ITV D99% was 111.3%. The median liver-ITV mean dose and D700cc were 499 cGy and 5.7 cGy, respectively. The median conformity index (CI) was 1.03, and the median R50 was 2.56. Except for ITV D99% (primary 118.1% vs. secondary 107.2%, p = 0.005), there were no significant differences in age, ITV volume, ITV V100%, ITV maximum dose, liver-ITV mean dose, or D700cc between primary and secondary tumor groups. Conclusion: The study demonstrated that proton therapy with motion management techniques and robust optimization achieves excellent target coverage with low normal liver doses for primary and secondary liver tumors. The results showed high target coverage, high conformality, and low doses to the liver.

Long-term risk of carotid stenosis and cerebrovascular disease after radiation therapy for head and neck cancer.

BACKGROUND: Recipients of radiation therapy (RT) for head and neck cancer (HNC) are at significantly increased risk for carotid artery stenosis (CAS) and cerebrovascular disease (CVD). We sought to determine (1) cumulative incidences of CAS and CVD among HNC survivors after RT and (2) whether CAS is associated with a RT dose response effect. METHODS: This single-institution retrospective cohort study examined patients with nonmetastatic HNC who completed (chemo)RT from January 2000 through October 2020 and subsequently received carotid imaging surveillance ≤2 years following RT completion and, in the absence of CAS, every 3 years thereafter. Exclusion criteria included history of known CAS/CVD. Asymptomatic CAS was defined as ≥50% reduction of luminal diameter, symptomatic CAS as stroke or transient ischemic attack, and composite CAS as asymptomatic or symptomatic CAS. RESULTS: Of 628 patients undergoing curative intent RT for HNC, median follow-up was 4.8 years (interquartile range, 2.6-8.3), with 97 patients followed ≥10 years. Median age was 61 years and 69% of patients received concurrent chemotherapy and 28% were treated postoperatively. Actuarial 10-year incidences of asymptomatic, symptomatic, and composite CAS were 29.6% (95% CI, 23.9-35.5), 10.1% (95% CI, 7.0-13.9), and 27.2% (95% CI, 22.5-32.1), respectively. Multivariable Cox models significant association between asymptomatic CAS and absolute carotid artery volume receiving ≥10 Gy (per mL: hazard ratio, 1.09; 95% CI, 1.02-1.16). CONCLUSIONS: HNC survivors are at high risk for post-RT CAS. A dose response effect was observed for asymptomatic CAS at doses as low as 10 Gy. PLAIN LANGUAGE SUMMARY: Recipients of radiation therapy for head and neck cancer are at significantly increased risk for carotid artery stenosis and cerebrovascular disease. However, carotid artery screening is not routinely performed among head and neck survivors following radiation therapy. In this single-institution retrospective cohort study, patients with head and neck cancer were initially screened for carotid artery stenosis ≤2 years following radiation therapy completion, then every 3 years thereafter. The 10-year actuarial incidence of carotid artery stenosis was >25% and stroke/transient ischemic attack >10%. Multivariable analysis demonstrated significant associations between asymptomatic carotid artery stenosis and artery volumes receiving ≥10 Gy.

Streamlined Pin-Ridge-Filter Design for Single-energy Proton FLASH Planning.

PURPOSE: This study explored the feasibility of a streamlined pin-shaped ridge filter (pin-RF) design for single-energy proton FLASH planning. METHODS: An inverse planning framework integrated within a TPS was established for FLASH planning. The framework involves generating a IMPT plan based on downstream energy modulation strategy (IMPT-DS), followed by a nested spot reduction process to iteratively reduce the total number of pencil beam directions (PBDs) and energy layers along each PBD for the IMPT-DS plan. The IMPT-DS plan is then translated into the pin-RFs for a single-energy IMPT plan (IMPT-RF). The framework was validated on three lung cases, quantifying the FLASH dose of the IMPT-RF plan using the FLASH effectiveness model and comparing it with the reference dose of a conventional IMPT plan to assess the clinical benefit of the FLASH planning technique. RESULTS: The IMPT-RF plans closely matched the corresponding IMPT-DS plans in high dose conformity, with minimal changes in V7Gy and V7.4Gy for the lung (< 5%) and small increases in Dmax for other OARs (< 3.2 Gy). Comparing the FLASH doses to the doses of corresponding IMPT-RF plans, drastic reductions of up to ~33% were observed in Dmax for OARs in the high-to-moderate-dose regions with negligible changes in Dmax for OARs in low-dose regions. Positive clinical benefits were observed with notable reductions of 18.4-33.0% in Dmax for OARs in the high-dose regions. However, in the moderate-to-low-dose regions, only marginal positive or even negative clinical benefit for OARs were observed, such as increased lung V7Gy and V7.4Gy (16.4-38.9%). CONCLUSIONS: A streamlined pin-RF design for single-energy proton FLASH planning was validated, revealing positive clinical benefits for OARs in the high dose regions. The coarsened design of the pin-RF demonstrates potential cost efficiency and efficient production.

Associations Between Social Determinants of Health and Psychoneurologic Symptom Clusters in Women With Gynecologic Cancers: A Longitudinal Study.

OBJECTIVES: To evaluate the associations between social determinants of health (SDOH) and psychoneurologic symptom (PNS) clusters in women with gynecologic cancers during cancer treatment. SAMPLE & SETTING: 67 women with gynecologic cancers who received radiation therapy were assessed at baseline, six to eight weeks after treatment, and six months after treatment at oncology clinics in Georgia. METHODS & VARIABLES: Fatigue, pain, sleep disturbances, cognitive impairment, and depressive symptoms were measured to determine a PNS cluster score. Associations between SDOH and PNS cluster scores were assessed using mixed-effect models. RESULTS: Larger mean PNS cluster scores were reported in individuals with less education, lower income, and unemployment, as well as in those living in more disadvantaged neighborhoods. IMPLICATIONS FOR NURSING: Individual- and community-level SDOH and their interactions were associated with more PNS clusters. Studying SDOH at multiple levels depicts how various social disadvantages can exacerbate poor health outcomes.

Plan Quality Analysis of Automated Treatment Planning Workflow With Commercial Auto-Segmentation Tools and Clinical Knowledge-Based Planning Models for Prostate Cancer.

This study evaluated the feasibility of using artificial intelligence (AI) segmentation software for volume-modulated arc therapy (VMAT) prostate planning in conjunction with knowledge-based planning to facilitate a fully automated workflow. Two commercially available AI software programs, Radformation AutoContour (Radformation, New York, NY) and Siemens AI-Rad Companion (Siemens Healthineers, Malvern, PA) were used to auto-segment the rectum, bladder, femoral heads, and bowel bag on 30 retrospective clinical cases (10 intact prostate, 10 prostate bed, and 10 prostate and lymph node). Physician-segmented target volumes were transferred to AI structure sets. In-house RapidPlan models were used to generate plans using the original, physician-segmented structure sets as well as Radformation and Siemens AI-generated structure sets. Thus, there were three plans for each of the 30 cases, totaling 90 plans. Following RapidPlan optimization, planning target volume (PTV) coverage was set to 95%. Then, the plans optimized using AI structures were recalculated on the physician structure set with fixed monitor units. In this way, physician contours were used as the gold standard for identifying any clinically relevant differences in dose distributions. One-way analysis of variation (ANOVA) was used for statistical analysis. No statistically significant differences were observed across the three sets of plans for intact prostate, prostate bed, or prostate and lymph nodes. The results indicate that an automated volumetric modulated arc therapy (VMAT) prostate planning workflow can consistently achieve high plan quality. However, our results also show that small but consistent differences in contouring preferences may lead to subtle differences in planning results. Therefore, the clinical implementation of auto-contouring should be carefully validated.

Radiation Facility Volume and Survival for Men With Very High-Risk Prostate Cancer Treated with Radiation and Androgen Deprivation Therapy.

Importance: Very high-risk (VHR) prostate cancer is an aggressive substratum of high-risk prostate cancer, characterized by high prostate-specific antigen levels, high Gleason score, and/or advanced T category. Contemporary management paradigms involve advanced molecular imaging and multimodal treatment with intensified prostate-directed or systemic treatment-resources more readily available at high-volume centers. Objective: To examine radiation facility case volume and overall survival (OS) in men with VHR prostate cancer. Design, Setting, and Participants: A retrospective cohort study was performed from November 11, 2022, to March 4, 2023, analyzing data from US facilities reporting to the National Cancer Database. Patients included men diagnosed with nonmetastatic VHR prostate cancer by National Comprehensive Cancer Network criteria (clinical T3b-T4 category, primary Gleason pattern 5, >4 cores with grade group 4-5, and/or 2-3 high-risk features) and treated with curative-intent radiotherapy and androgen deprivation therapy between January 1, 2004, to December 31, 2016. Exposures: Treatment at high- vs low-average cumulative facility volume (ACFV), defined as the total number of prostate radiotherapy cases at an individual patient's treatment facility from 2004 until the year of their diagnosis. The nonlinear association between a continuous ACFV and OS was examined through a Martingale residual plot; an optimal ACFV cutoff was identified that maximized the separation between high vs low ACFV via a bias-adjusted log rank test. Main Outcomes and Measures: Overall survival was assessed between high vs low ACFV using Kaplan-Meier analysis with and without inverse probability score weighted adjustment and multivariable Cox proportional hazards. Results: A total of 25 219 men (median age, 71 [IQR, 64-76] years; 78.7% White) with VHR prostate cancer were identified, 6438 (25.5%) of whom were treated at high ACFV facilities. Median follow-up was 57.4 (95% CI, 56.7-58.1) months. Median OS for patients treated at high ACFV centers was 123.4 (95% CI, 116.6-127.4) months vs 109.0 (95% CI, 106.5-111.2) months at low ACFV centers (P < .001). On multivariable analysis, treatment at a high ACFV center was associated with lower risk of death (hazard ratio, 0.89; 95% CI, 0.84-0.95; P < .001). These results were also significant after inverse probability score weighted-based adjustment. Conclusions and Relevance: In this cohort study of patients with VHR prostate cancer who underwent definitive radiotherapy and androgen deprivation therapy, facility case volume was independently associated with longer OS. Further studies are needed to identify which factors unique to high-volume centers may be responsible for this benefit.

A novel direction modulated brachytherapy technique for urethra sparing in high-dose-rate brachytherapy of prostate cancer.

PURPOSE: Image-guided high-dose-rate (HDR) prostate brachytherapy is a safe and effective treatment option for prostate cancer patients; however, some patients still experience acute and late genitourinary (GU) toxicity. Studies have shown that urethral dose is associated with the incidence and severity of GU toxicity. Therefore, a technique that can further spare the urethra while ensuring adequate target coverage is highly desirable. Intensity modulated brachytherapy (IMBT) designs, such as rotating shield brachytherapy (RSBT), offer ideal dosimetry theoretically but are challenging to implement clinically due to the need for high precision in moving the treatment delivery mechanisms synchronized with the source loading. In this study, we propose a novel relatively easy-to-implement solution based on the direction modulated brachytherapy (DMBT) design concept, which does not involve moving parts and works effectively with the ubiquitous 192Ir source. MATERIALS AND METHODS: The popular Varian VS2000 (VS) and GammaMedPlus (GMP) 192Ir sources, with outer diameters of 0.6 mm and 0.9 mm, respectively, were simulated using the GEANT4 Monte Carlo (MC) simulation code. The novel DMBT needle concept consists of a 14-gauge nitinol needle, which houses a platinum shield inside. A single groove, consistent with the outer diameter of each source, was incorporated inside the platinum shield to accommodate the HDR source. The maximum thickness of the shield was 1.1 mm (0.8 mm) for the VS (GMP) source. To evaluate the effectiveness of the DMBT needle concept in reducing urethral dose, 6 patient cases were studied and DMBT plans were created by replacing two needles close to the urethra with the DMBT needles. The dosimetric comparisons between the DMBT and reference clinical plans were done by assessing the dose-volume histogram (DVH) planning criteria for the target coverage and organs-at-risk. RESULTS: The MC results showed that the use of the novel DMBT needle design with the VS source (GMP source) could reduce the dose by 49.6% (39.2%) at 1 cm from the needle behind the platinum shield, as compared to the unshielded side. Additionally, when using the same DVH planning criteria as the original plan, the DMBT plan with the VS (GMP) source reduced the maximum urethral dose by 10.3% ± 5.6% (8.1% ± 5.0%) and 17.7% ± 14.2% (16.6% ± 13.3%) for 0 mm and 2 mm margins, respectively, while maintaining equivalent V90% and D100 target coverage. CONCLUSION: The novel DMBT technique offers a promising clinically implementable solution for sparing urethra, particularly in pre-apical region, without compromising the target coverage or increasing treatment time.

An optimized framework for cone-beam computed tomography-based online evaluation for proton therapy.

BACKGROUND: Clinical evidence has demonstrated that proton therapy can achieve comparable tumor control probabilities compared to conventional photon therapy but with the added benefit of sparing healthy tissues. However, proton therapy is sensitive to inter-fractional anatomy changes. Online pre-fraction evaluation can effectively verify proton dose before delivery to patients, but there is a lack of guidelines for implementing this workflow. PURPOSE: The purpose of this study is to develop a cone-beam CT-based (CBCT) online evaluation framework for proton therapy that enables knowledge transparency and evaluates the efficiency and accuracy of each essential component. METHODS: Twenty-three patients with various lesion sites were included to conduct a retrospective study of implementing the proposed CBCT evaluation framework for the clinic. The framework was implemented on the RayStation 11B Research platform. Two synthetic CT (sCT) methods, corrected CBCT (cCBCT), and virtual CT (vCT), were used, and the ground truth images were acquired from the same-day deformed quality assurance CT (dQACT) for the comparisons. The evaluation metrics for the framework include time efficiency, dose-difference distributions (gamma passing rates), and water equivalent thickness (WET) distributions. RESULTS: The mean online CBCT evaluation times were 1.6 ± 0.3 min and 1.9 ± 0.4 min using cCBCT and vCT, respectively. The dose calculation and deformable image registration dominated the evaluation efficiency, and accounted for 33% and 30% of the total evaluation time, respectively. The sCT generation took another 19% of the total time. Gamma passing rates were greater than 91% and 97% using 1%/1 mm and 2%/2 mm criteria, respectively. When the appropriate sCT was chosen, the target mean WET difference from the reference were less than 0.5 mm. The appropriate sCT method choice determined the uncertainty for the framework, with the cCBCT being superior for head-and-neck patient evaluation and vCT being better for lung patient evaluation. CONCLUSIONS: An online CBCT evaluation framework was proposed to identify the use of the optimal sCT algorithm regarding efficiency and dosimetry accuracy. The framework is extendable to adopt advanced imaging methods and has the potential to support online adaptive radiotherapy to enhance patient benefits. It could be implemented into clinical use in the future.

Rapid unpaired CBCT-based synthetic CT for CBCT-guided adaptive radiotherapy.

In this work, we demonstrate a method for rapid synthesis of high-quality CT images from unpaired, low-quality CBCT images, permitting CBCT-based adaptive radiotherapy. We adapt contrastive unpaired translation (CUT) to be used with medical images and evaluate the results on an institutional pelvic CT dataset. We compare the method against cycleGAN using mean absolute error, structural similarity index, root mean squared error, and Frèchet Inception Distance and show that CUT significantly outperforms cycleGAN while requiring less time and fewer resources. The investigated method improves the feasibility of online adaptive radiotherapy over the present state-of-the-art.

Inter-fraction deformable image registration using unsupervised deep learning for CBCT-guided abdominal radiotherapy.

Objective. CBCTs in image-guided radiotherapy provide crucial anatomy information for patient setup and plan evaluation. Longitudinal CBCT image registration could quantify the inter-fractional anatomic changes, e.g. tumor shrinkage, and daily OAR variation throughout the course of treatment. The purpose of this study is to propose an unsupervised deep learning-based CBCT-CBCT deformable image registration which enables quantitative anatomic variation analysis.Approach.The proposed deformable registration workflow consists of training and inference stages that share the same feed-forward path through a spatial transformation-based network (STN). The STN consists of a global generative adversarial network (GlobalGAN) and a local GAN (LocalGAN) to predict the coarse- and fine-scale motions, respectively. The network was trained by minimizing the image similarity loss and the deformable vector field (DVF) regularization loss without the supervision of ground truth DVFs. During the inference stage, patches of local DVF were predicted by the trained LocalGAN and fused to form a whole-image DVF. The local whole-image DVF was subsequently combined with the GlobalGAN generated DVF to obtain the final DVF. The proposed method was evaluated using 100 fractional CBCTs from 20 abdominal cancer patients in the experiments and 105 fractional CBCTs from a cohort of 21 different abdominal cancer patients in a holdout test.Main Results. Qualitatively, the registration results show good alignment between the deformed CBCT images and the target CBCT image. Quantitatively, the average target registration error calculated on the fiducial markers and manually identified landmarks was 1.91 ± 1.18 mm. The average mean absolute error, normalized cross correlation between the deformed CBCT and target CBCT were 33.42 ± 7.48 HU, 0.94 ± 0.04, respectively.Significance. In summary, an unsupervised deep learning-based CBCT-CBCT registration method is proposed and its feasibility and performance in fractionated image-guided radiotherapy is investigated. This promising registration method could provide fast and accurate longitudinal CBCT alignment to facilitate inter-fractional anatomic changes analysis and prediction.

Immune niches in brain metastases contain TCF1+ stem-like T cells, are associated with disease control and are modulated by preoperative SRS.

The CD8+ T-cell response is prognostic for survival outcomes in several tumor types. However, whether this extends to tumors in the brain, an organ with barriers to T cell entry, remains unclear. Here, we analyzed immune infiltration in 67 brain metastasis (BrM) and found high frequencies of PD1+ TCF1+ stem-like CD8+ T-cells and TCF1- effector-like cells. Importantly, the stem-like cells aggregate with antigen presenting cells in immune niches, and niches were prognostic for local disease control. Standard of care for BrM is resection followed by stereotactic radiosurgery (SRS), so to determine SRS's impact on the BrM immune response, we examined 76 BrM treated with pre-operative SRS (pSRS). pSRS acutely reduced CD8+ T cells at 3 days. However, CD8+ T cells rebounded by day 6, driven by increased frequency of effector-like cells. This suggests that the immune response in BrM can be regenerated rapidly, likely by the local TCF1+ stem-like population.