RESUMO
PURPOSE: Artificial intelligence (AI)-aided methods have made significant progress in the auto-delineation of normal tissues. However, these approaches struggle with the auto-contouring of radiotherapy target volume. Our goal is to model the delineation of target volume as a clinical decision-making problem, resolved by leveraging large language model-aided multimodal learning approaches. METHODS AND MATERIALS: A vision-language model, termed Medformer, has been developed, employing the hierarchical vision transformer as its backbone, and incorporating large language models to extract text-rich features. The contextually embedded linguistic features are seamlessly integrated into visual features for language-aware visual encoding through the visual language attention module. Metrics, including Dice similarity coefficient (DSC), intersection over union (IOU), and 95th percentile Hausdorff distance (HD95), were used to quantitatively evaluate the performance of our model. The evaluation was conducted on an in-house prostate cancer dataset and a public oropharyngeal carcinoma (OPC) dataset, totaling 668 subjects. RESULTS: Our Medformer achieved a DSC of 0.81 ± 0.10 versus 0.72 ± 0.10, IOU of 0.73 ± 0.12 versus 0.65 ± 0.09, and HD95 of 9.86 ± 9.77 mm versus 19.13 ± 12.96 mm for delineation of gross tumor volume (GTV) on the prostate cancer dataset. Similarly, on the OPC dataset, it achieved a DSC of 0.77 ± 0.11 versus 0.72 ± 0.09, IOU of 0.70 ± 0.09 versus 0.65 ± 0.07, and HD95 of 7.52 ± 4.8 mm versus 13.63 ± 7.13 mm, representing significant improvements (p < 0.05). For delineating the clinical target volume (CTV), Medformer achieved a DSC of 0.91 ± 0.04, IOU of 0.85 ± 0.05, and HD95 of 2.98 ± 1.60 mm, comparable to other state-of-the-art algorithms. CONCLUSIONS: Auto-delineation of the treatment target based on multimodal learning outperforms conventional approaches that rely purely on visual features. Our method could be adopted into routine practice to rapidly contour CTV/GTV.
RESUMO
Historically, total body irradiation (TBI) has been delivered using static, parallel opposed photon beams (2D-TBI). Recently, centers have increasingly used intensity-modulated radiation therapy (IMRT) techniques for TBI. Relative to 2D-TBI, IMRT can reduce doses to critical organs (i.e., lungs and kidneys) while delivering myeloablative doses to the rest of the body, so it may decrease the risk of toxicity while maintaining oncologic outcomes. Despite these potential benefits, delivering TBI using IMRT introduces new challenges in treatment planning and delivery. We describe the extensive experience with IMRT-based TBI at Stanford University and City of Hope Cancer Center. These groups, and others, have reported favorable clinical outcomes and have developed methods to optimize treatment planning and delivery. A critical next step is to evaluate the broader adoption of this approach. Therefore, IMRT-based TBI will be incorporated into a prospective, multi-institutional Children's Oncology Group study with careful procedures and safeguards in place.
RESUMO
BACKGROUND: Biology-guided radiotherapy (BgRT) is a novel radiotherapy delivery technique that utilizes the tumor itself to guide dynamic delivery of treatment dose to the tumor. The RefleXion X1 system is the first radiotherapy system developed to deliver SCINTIX® BgRT. The X1 is characterized by its split arc design, employing two 90-degree positron emission tomography (PET) arcs to guide therapeutic radiation beams in real time, currently cleared by FDA to treat bone and lung tumors. PURPOSE: This study aims to comprehensively evaluate the capabilities of the SCINTIX radiotherapy delivery system by evaluating its sensitivity to changes in PET contrast, its adaptability in the context of patient motion, and its performance across a spectrum of prescription doses. METHODS: A series of experimental scenarios, both static and dynamic, were designed to assess the SCINTIX BgRT system's performance, including an end-to-end test. These experiments involved a range of factors, including changes in PET contrast, motion, and prescription doses. Measurements were performed using a custom-made ArcCHECK insert which included a 2.2 cm spherical target and a c-shape structure that can be filled with a PET tracer with varying concentrations. Sinusoidal and cosine4 motion patterns, simulating patient breathing, was used to test the SCINTIX system's ability to deliver BgRT during motion-induced challenges. Each experiment was evaluated against specific metrics, including Activity Concentration (AC), Normalized Target Signal (NTS), and Biology Tracking Zone (BTZ) bounded dose-volume histogram (bDVH) pass rates. The accuracy of the delivered BgRT doses on ArcCHECK and EBT-XD film were evaluated using gamma 3%/2 mm and 3%/3 mm analysis. RESULTS: In static scenarios, the X1 system consistently demonstrated precision and robustness in SCINTIX dose delivery. The end-to-end delivery to the spherical target yielded good results, with AC and NTS values surpassing the critical thresholds of 5 kBq/mL and 2, respectively. Furthermore, bDVH analysis consistently confirmed 100% pass rates. These results were reaffirmed in scenarios involving changes in PET contrast, emphasizing the system's ability to adapt to varying PET avidities. Gamma analysis with 3%/2 mm (10% dose threshold) criteria consistently achieved pass rates > 91.5% for the static tests. In dynamic SCINTIX delivery scenarios, the X1 system exhibited adaptability under conditions of motion. Sinusoidal and cosine4 motion patterns resulted in 3%/3 mm gamma pass rates > 87%. Moreover, the comparison with gated stereotactic body radiotherapy (SBRT) delivery on a conventional c-arm Linac resulted in 93.9% gamma pass rates and used as comparison to evaluate the interplay effect. The 1 cm step shift tests showed low overall gamma pass rates of 60.3% in ArcCHECK measurements, while the doses in the PTV agreed with the plan with 99.9% for 3%/3 mm measured with film. CONCLUSIONS: The comprehensive evaluation of the X1 radiotherapy delivery system for SCINTIX BgRT demonstrated good agreement for the static tests. The system consistently achieved critical metrics and delivered the BgRT doses per plan. The motion tests demonstrated its ability to co-localize the dose where the PET signal is and deliver acceptable BgRT dose distributions.
Assuntos
Tomografia por Emissão de Pósitrons , Radioterapia Guiada por Imagem , Tomografia por Emissão de Pósitrons/instrumentação , Radioterapia Guiada por Imagem/instrumentação , Radioterapia Guiada por Imagem/métodos , Aceleradores de Partículas , Humanos , Dosagem RadioterapêuticaRESUMO
Purpose: Create a comprehensive automated solution for pediatric and adult VMAT-CSI including contouring, planning, and plan check to reduce planning time and improve plan quality. Methods: Seventy-seven previously treated CSI patients (age, 2-67 years) were used for creation of an auto-contouring model to segment 25 organs at risk (OARs). The auto-contoured OARs were evaluated using the Dice Similarity Coefficient (DSC), 95% Hausdorff Distance (HD95), and a qualitative ranking by one physician and one physicist (scale: 1-acceptable, 2-minor edits, 3-major edits). The auto-planning script was developed using the Varian Eclipse Scripting API and tested with 20 patients previously treated with either low-dose VMAT-CSI (12 Gy) or high-dose VMAT-CSI (36 Gy + 18 Gy boost). Clinically relevant metrics, planning time, and blinded physician review were used to evaluate significance of differences between the auto and manual plans. Finally, the plan preparation for treatment and plan check processes were automated to improve efficiency and safety of VMAT-CSI. Results: The auto-contours achieved an average DSC of 0.71 ± 0.15, HD95 of 4.81 ± 4.68, and reviewers' ranking of 1.22 ± 0.39, indicating close to "acceptable-as-is" contours. Compared to the manual CSI plans, the auto-plans for both dose regimens achieved statistically significant reductions in body V50% and Dmean for parotids, submandibular, and thyroid glands. The variance in the dosimetric parameters decreased for the auto-plans as compared to the manual plans indicating better plan consistency. From the blinded review, the auto-plans were marked as equivalent or superior to the manual-plans 88.3% of the time. The required time for the auto-contouring and planning was consistently between 1-2 hours compared to an estimated 5-6 hours for manual contouring and planning. Conclusions: Reductions in contouring and planning time without sacrificing plan quality were obtained using the developed auto-planning process. The auto-planning scripts and documentation will be made freely available to other institutions and clinics.
RESUMO
PURPOSE: This study explores the feasibility of employing Generative Adversarial Networks (GANs) to model the RefleXion X1 Linac. The aim is to investigate the accuracy of dose simulation and assess the potential computational benefits. METHODS: The X1 Linac is a new radiotherapy machine with a binary multi-leaf collimation (MLC) system, facilitating innovative biology-guided radiotherapy. A total of 34 GAN generators, each representing a desired MLC aperture, were developed. Each generator was trained using a phase space file generated underneath the corresponding aperture, enabling the generation of particles and serving as a beam source for Monte Carlo simulation. Dose distributions in water were simulated for each aperture using both the GAN and phase space sources. The agreement between dose distributions was evaluated. The computational time reduction from bypassing the collimation simulation and storage space savings were estimated. RESULTS: The percentage depth dose at 10 cm, penumbra, and full-width half maximum of the GAN simulation agree with the phase space simulation, with differences of 0.4 % ± 0.2 %, 0.32 ± 0.66 mm, and 0.26 ± 0.44 mm, respectively. The gamma passing rate (1 %/1mm) for the planar dose exceeded 90 % for all apertures. The estimated time-saving for simulating an plan using 5766 beamlets was 530 CPU hours. The storage usage was reduced by a factor of 102. CONCLUSION: The utilization of the GAN in simulating the X1 Linac demonstrated remarkable accuracy and efficiency. The reductions in both computational time and storage requirements make this approach highly valuable for future dosimetry studies and beam modeling.
Assuntos
Planejamento da Radioterapia Assistida por Computador , Radioterapia de Intensidade Modulada , Planejamento da Radioterapia Assistida por Computador/métodos , Método de Monte Carlo , Simulação por Computador , Dosagem Radioterapêutica , Radioterapia de Intensidade Modulada/métodos , Aceleradores de PartículasRESUMO
Purpose: The aim of this study was to present the first-year experience of treating patients using intensity modulated radiation therapy (IMRT) and stereotactic body radiation therapy (SBRT) with a biology-guided radiation therapy machine, the RefleXion X1 system, installed in a clinical setting. Methods and Materials: A total of 78 patients were treated on the X1 system using IMRT and SBRT from May 2021 to May 2022. Clinical and technical data including treatment sites, number of pretreatment kilovoltage computed tomography (kVCT) scans, beam-on time, patient setup time, and imaging time were collected and analyzed. Machine quality assurance (QA) results, machine performance, and user satisfactory survey were also collected and reported. Results: The most commonly treated site was the head and neck (63%), followed by the pelvis (23%), abdomen (8%), and thorax (6%). Except for 5 patients (6%) who received SBRT treatments for bony metastases in the pelvis, all treatments were conventionally fractionated IMRT. The number of kVCT scans per fraction was 1.2 ± 0.5 (mean ± standard deviation). The beam-on time was 9.2 ± 3.5 minutes. The patient setup time and imaging time per kVCT was 4.8 ± 2.6 minutes and 4.6 ± 1.5 minutes, respectively. The daily machine output deviation was 0.4 ± 1.2% from the baseline. The patient QA had a passing rate of 97.4 ± 2.8% at 3%/2 mm gamma criteria. The machine uptime was 92% of the total treatment time. The daily QA and kVCT image quality received the highest level of satisfaction. The treatment workflow for therapists received the lowest level of satisfaction. Conclusions: One year after the installation, 78 patients were successfully treated with the X1 system using IMRT and/or SBRT. With the recent Food and Drug Administration clearance of biology-guided radiation therapy, our department is preparing to treat patients using positron emission tomography-guidance via a new product release, which will address deficiencies in the current image-guided radiation therapy workflow.
RESUMO
PURPOSE/OBJECTIVES: Adoption of hypofractionated accelerated radiation therapy (HART) with concurrent chemotherapy has been limited by toxicity concerns. We aimed to describe outcomes of patients treated with HART and concurrent chemotherapy and to evaluate dosimetry to organs at risk to guide patient selection. MATERIALS/METHODS: We evaluated a retrospective cohort of NSCLC patients treated with concurrent chemotherapy with HART (>2.2 Gy per fraction) or standard fractionated radiation therapy (SFRT; 2-2.2 Gy fractions). Dosimetric parameters to key organs at risk were compared, and toxicity, patterns of recurrence and survival were calculated for the cohorts. RESULTS: Fifty-three patients treated with HART were compared with 100 patients treated with SFRT. Median dose per fraction for the HART cohort was 2.75 Gy (range 2.4-3 Gy). HART patients had significantly lower doses to the lung, heart, and esophagus due to patient selection. The HART group and had rates of grade 2+ pneumonitis (9.4 vs. 19%, P = .16) and grade 2+ esophagitis (20.8 vs. 45%, P < .01) that compared favorably to SFRT. Cumulative incidence of in-field recurrence trended lower in the HART cohort (7.6% vs. 23.1%, P = .058). Among the HART group, 88.7% (47/53) met the newly proposed lung constraints based on the degree of hypofractionation CONCLUSION: In select patients with favorable dosimetry to organs at risk, definitive HART with concurrent chemotherapy achieved excellent local control with low toxicity. These results are being used to inform a prospective study on the safety and efficacy of HART with concurrent chemotherapy for select NSCLC patients.
Assuntos
Carcinoma Pulmonar de Células não Pequenas , Neoplasias Pulmonares , Humanos , Carcinoma Pulmonar de Células não Pequenas/tratamento farmacológico , Neoplasias Pulmonares/tratamento farmacológico , Neoplasias Pulmonares/radioterapia , Hipofracionamento da Dose de Radiação , Estudos Retrospectivos , Estudos Prospectivos , Seleção de PacientesRESUMO
INTRODUCTION: Prior attempts to escalate radiation dose for non-small cell lung cancer (NSCLC) have not improved survival. Given the high risk for cardiopulmonary toxicity with treatment and heterogenous presentation of locally advanced NSCLC, it is unlikely that a single dose regimen is optimal for all patients. This phase I/II trial aims to evaluate a novel treatment approach where the level of accelerated hypofractionation is determined by the predicted toxicity from dose to organs at risk (OARs). METHODS: Patients ≥ 18 years old with lung cancer planned for fractionated radiotherapy to the lung with concurrent chemotherapy will be eligible. Radiation therapy (RT) will be delivered to a total dose of 60 to 66 Gy in 30, 25, or 20 fractions depending on the ability to meet constraints to key organs at risk including the lungs, heart, and esophagus. The primary endpoint is high grade pulmonary, esophageal, or cardiac toxicity. A Bayesian optimized design is used to determine stopping boundaries and evaluate the primary endpoint. CONCLUSION: PACER will evaluate the safety and feasibility of personalized accelerated chemoradiotherapy for lung cancer.
Assuntos
Carcinoma Pulmonar de Células não Pequenas , Neoplasias Pulmonares , Humanos , Adolescente , Neoplasias Pulmonares/tratamento farmacológico , Carcinoma Pulmonar de Células não Pequenas/tratamento farmacológico , Teorema de Bayes , Quimiorradioterapia/métodos , Pulmão , Protocolos de Quimioterapia Combinada Antineoplásica/uso terapêutico , Ensaios Clínicos Fase II como Assunto , Ensaios Clínicos Fase I como AssuntoRESUMO
PURPOSE: The purpose of this work is to develop a method to automate the treatment planning process of craniospinal irradiation (CSI) using volumetric modulated arc therapy. METHODS AND MATERIALS: Two scripts were developed using the Eclipse Scripting Application Programming Interface to perform auto-plan preparation and optimization. Ten patients (age, 5-44 years) previously treated at our institution with low dose volumetric modulated arc therapy CSI (prescription of 12 Gy) before total body irradiation were selected to evaluate the efficacy of the proposed auto-planning process. Paired t tests compared the dosimetric indices of the auto-plans to the manually generated clinical plans. All plans were normalized to 95% of planning target volume (PTV) coverage with the prescription dose. Two physicians and one physicist were asked to evaluate the manual plans and auto-plans of each patient in a blinded retrospective review and to indicate clinical acceptability and which plans were preferred for treatment. RESULTS: Compared with the manual CSI plans, the auto plans obtained significant reductions in Dmean to the parotids, submandibular glands, larynx, thyroid, and significant reduction in the plan PTV Dmax and D0.03 cc. The standard deviation range of the dosimetric parameters was greatly reduced for auto plans (range, 0.1-1.3 Gy) relative to manual plans (range, 0.4-5.9 Gy) indicating better plan consistency. Among the 10 patients, the auto-plans were preferred over the manual plans 90% of the time by the reviewing experts. The required time for auto-planning was approximately 1 hour compared with estimated 4 or more hours for manual planning. CONCLUSIONS: Reductions in planning time without sacrifices in plan quality were obtained using the auto-planning process compared with manual planning. Variation in plan quality was also reduced. The auto-planning scripts will be made freely available to other institutions and clinics.
Assuntos
Radiação Cranioespinal , Médicos , Radioterapia de Intensidade Modulada , Humanos , Pré-Escolar , Criança , Adolescente , Adulto Jovem , Adulto , Instalações de Saúde , Glândula ParótidaRESUMO
PURPOSE: Positron emission tomography (PET)-guided radiation therapy is a novel tracked dose delivery modality that uses real-time PET to guide radiation therapy beamlets. The BIOGUIDE-X study was performed with sequential cohorts of participants to (1) identify the fluorodeoxyglucose (FDG) dose for PET-guided therapy and (2) confirm that the emulated dose distribution was consistent with a physician-approved radiation therapy plan. METHODS AND MATERIALS: This prospective study included participants with at least 1 FDG-avid targetable primary or metastatic tumor (2-5 cm) in the lung or bone. For cohort I, a modified 3 + 3 design was used to determine the FDG dose that would result in adequate signal for PET-guided therapy. For cohort II, PET imaging data were collected on the X1 system before the first and last fractions among patients undergoing conventional stereotactic body radiation therapy. PET-guided therapy dose distributions were modeled on the patient's computed tomography anatomy using the collected PET data at each fraction as input to an "emulated delivery" and compared with the physician-approved plan. RESULTS: Cohort I demonstrated adequate FDG activity in 6 of 6 evaluable participants (100.0%) with the first injected dose level of 15 mCi FDG. In cohort II, 4 patients with lung tumors and 5 with bone tumors were enrolled, and evaluable emulated delivery data points were collected for 17 treatment fractions. Sixteen of the 17 emulated deliveries resulted in dose distributions that were accurate with respect to the approved PET-guided therapy plan. The 17th data point was just below the 95% threshold for accuracy (dose-volume histogram score = 94.6%). All emulated fluences were physically deliverable. No toxicities were attributed to multiple FDG administrations. CONCLUSIONS: PET-guided therapy is a novel radiation therapy modality in which a radiolabeled tumor can act as its own fiducial for radiation therapy targeting. Emulated therapy dose distributions calculated from continuously acquired real-time PET data were accurate and machine-deliverable in tumors that were 2 to 5 cm in size with adequate FDG signal characteristics.
Assuntos
Fluordesoxiglucose F18 , Neoplasias Pulmonares , Humanos , Estudos Prospectivos , Tomografia por Emissão de Pósitrons , Neoplasias Pulmonares/diagnóstico por imagem , Neoplasias Pulmonares/radioterapia , Neoplasias Pulmonares/patologia , Tomografia Computadorizada por Raios X/métodos , Compostos RadiofarmacêuticosRESUMO
Silicon nitride, silicon oxide, and silicon oxynitride thin films were deposited on the Si substrate by inductively coupled plasma chemical vapor deposition and annealed at 1100 °C for 3 min in an Ar environment. Silicon nitride and silicon oxide films deposited at ratios of the reactant flow rates of SiH4/N2 = 1.875 and SiH4/N2O = 3, respectively, were Si-rich, while Si excess for the oxynitride film (SiH4/N2/N2O = 3:2:2) was not found. Annealing resulted in a thickness decrease and structural transformation for SiOx and SiNx films. Nanocrystalline phases of Si as well as α- and ß-Si3N4 were found in the annealed silicon nitride film. Compared to oxide and nitride films, the oxynitride film is the least susceptible to change during annealing. The relationship between the structure, composition, and optical properties of the Si-based films has been revealed. It has been shown that the calculated optical parameters (refractive index, extinction coefficient) reflect structural peculiarities of the as-deposited and annealed films.
RESUMO
PURPOSE/OBJECTIVES: To evaluate dosimetric differences between auto-planned volumetric modulated arc therapy (VMAT) total body irradiation (TBI) technique and two-dimensional radiotherapy using anterior-posterial/posterio-anterial beams (2D AP/PA) TBI technique. METHODS: Ten pediatric patients treated with VMAT-TBI on Varian c-arm linac were included in this study. VMAT-TBI plans were generated using our in-house developed and publicly shared auto-planning scripts. For each VMAT-TBI plan, a 2D AP/PA plan was created replicating the institution's clinical setup with the patient positioned at extended source to skin distance (SSD) with a compensator to account for differences in patient thickness, 50% transmission daily lung blocks, and electron chest wall boosts prescribed to 50% of the photon prescription. Clinically relevant metrics were analyzed and compared between the VMAT and 2D plans. RESULTS: All VMAT-TBI plans achieved planned target volume (PTV) D90% ≥ 100% of prescription. VMAT-TBI PTV D90% significantly increased (7.1% ± 2.9%, p < .001) compared to the 2D technique, whereas no differences were observed in global Dmax (p < .2) and PTV V110% (p < .4). Compared to the 2D plans, significant decreases in the Dmean to the lungs (-25.6% ± 11.5%, p < .001) and lungs-1 cm (-34.1% ± 10.1%, p < .001) were observed with the VMAT plans. The VMAT technique also enabled decrease of dose to other organs: kidneys Dmean (-32.5% ± 5.0%, p < .001) and lenses Dmax (-5.3% ± 8.1%, p = .03); and in addition, for 2 Gy prescription: testes/ovaries Dmean (-41.5% ± 11.5%, p < .001), brain Dmean (-22.6% ± 5.4%, p = .002), and thyroid Dmean (-18.2% ± 16.0%, p = .03). CONCLUSIONS: Superior lung sparing with improved target coverage and similar global Dmax were observed with the VMAT plans as compared to 2D plans. In addition, VMAT-TBI plans provided greater dose reductions in gonads, kidneys, brain, thyroid, and lenses.
Assuntos
Radioterapia de Intensidade Modulada , Humanos , Criança , Radioterapia de Intensidade Modulada/métodos , Planejamento da Radioterapia Assistida por Computador/métodos , Irradiação Corporal Total , Dosagem Radioterapêutica , Órgãos em Risco/efeitos da radiaçãoRESUMO
Defining the loss function is an important part of neural network design and critically determines the success of deep learning modeling. A significant shortcoming of the conventional loss functions is that they weight all regions in the input image volume equally, despite the fact that the system is known to be heterogeneous (i.e., some regions can achieve high prediction performance more easily than others). Here, we introduce a region-specific loss to lift the implicit assumption of homogeneous weighting for better learning. We divide the entire volume into multiple sub-regions, each with an individualized loss constructed for optimal local performance. Effectively, this scheme imposes higher weightings on the sub-regions that are more difficult to segment, and vice versa. Furthermore, the regional false positive and false negative errors are computed for each input image during a training step and the regional penalty is adjusted accordingly to enhance the overall accuracy of the prediction. Using different public and in-house medical image datasets, we demonstrate that the proposed regionally adaptive loss paradigm outperforms conventional methods in the multi-organ segmentations, without any modification to the neural network architecture or additional data preparation.
Assuntos
Algoritmos , Redes Neurais de Computação , Processamento de Imagem Assistida por Computador/métodosRESUMO
PURPOSE: This study explored deep-learning-based patient-specific auto-segmentation using transfer learning on daily RefleXion kilovoltage computed tomography (kVCT) images to facilitate adaptive radiation therapy, based on data from the first group of patients treated with the innovative RefleXion system. METHODS AND MATERIALS: For head and neck (HaN) and pelvic cancers, a deep convolutional segmentation network was initially trained on a population data set that contained 67 and 56 patient cases, respectively. Then the pretrained population network was adapted to the specific RefleXion patient by fine-tuning the network weights with a transfer learning method. For each of the 6 collected RefleXion HaN cases and 4 pelvic cases, initial planning computed tomography (CT) scans and 5 to 26 sets of daily kVCT images were used for the patient-specific learning and evaluation separately. The performance of the patient-specific network was compared with the population network and the clinical rigid registration method and evaluated by the Dice similarity coefficient (DSC) with manual contours being the reference. The corresponding dosimetric effects resulting from different auto-segmentation and registration methods were also investigated. RESULTS: The proposed patient-specific network achieved mean DSC results of 0.88 for 3 HaN organs at risk (OARs) of interest and 0.90 for 8 pelvic target and OARs, outperforming the population network (0.70 and 0.63) and the registration method (0.72 and 0.72). The DSC of the patient-specific network gradually increased with the increment of longitudinal training cases and approached saturation with more than 6 training cases. Compared with using the registration contour, the target and OAR mean doses and dose-volume histograms obtained using the patient-specific auto-segmentation were closer to the results using the manual contour. CONCLUSIONS: Auto-segmentation of RefleXion kVCT images based on the patient-specific transfer learning could achieve higher accuracy, outperforming a common population network and clinical registration-based method. This approach shows promise in improving dose evaluation accuracy in RefleXion adaptive radiation therapy.
Assuntos
Processamento de Imagem Assistida por Computador , Planejamento da Radioterapia Assistida por Computador , Humanos , Planejamento da Radioterapia Assistida por Computador/métodos , Processamento de Imagem Assistida por Computador/métodos , Órgãos em Risco/diagnóstico por imagem , Órgãos em Risco/efeitos da radiação , Radiometria , Tomografia Computadorizada por Raios XRESUMO
PURPOSE: Artificial intelligence-based tools can be leveraged to improve detection and segmentation of brain metastases for stereotactic radiosurgery (SRS). VBrain by Vysioneer Inc. is a deep learning algorithm with recent FDA clearance to assist in brain tumor contouring. We aimed to assess the performance of this tool by various demographic and clinical characteristics among patients with brain metastases treated with SRS. MATERIALS AND METHODS: We randomly selected 100 patients with brain metastases who underwent initial SRS on the CyberKnife from 2017 to 2020 at a single institution. Cases with resection cavities were excluded from the analysis. Computed tomography (CT) and axial T1-weighted post-contrast magnetic resonance (MR) image data were extracted for each patient and uploaded to VBrain. A brain metastasis was considered "detected" when the VBrain- "predicted" contours overlapped with the corresponding physician contours ("ground-truth" contours). We evaluated performance of VBrain against ground-truth contours using the following metrics: lesion-wise Dice similarity coefficient (DSC), lesion-wise average Hausdorff distance (AVD), false positive count (FP), and lesion-wise sensitivity (%). Kruskal-Wallis tests were performed to assess the relationships between patient characteristics including sex, race, primary histology, age, and size and number of brain metastases, and performance metrics such as DSC, AVD, FP, and sensitivity. RESULTS: We analyzed 100 patients with 435 intact brain metastases treated with SRS. Our cohort consisted of patients with a median number of 2 brain metastases (range: 1 to 52), median age of 69 (range: 19 to 91), and 50% male and 50% female patients. The primary site breakdown was 56% lung, 10% melanoma, 9% breast, 8% gynecological, 5% renal, 4% gastrointestinal, 2% sarcoma, and 6% other, while the race breakdown was 60% White, 18% Asian, 3% Black/African American, 2% Native Hawaiian or other Pacific Islander, and 17% other/unknown/not reported. The median tumor size was 0.112 c.c. (range: 0.010-26.475 c.c.). We found mean lesion-wise DSC to be 0.723, mean lesion-wise AVD to be 7.34% of lesion size (0.704 mm), mean FP count to be 0.72 tumors per case, and lesion-wise sensitivity to be 89.30% for all lesions. Moreover, mean sensitivity was found to be 99.07%, 97.59%, and 96.23% for lesions with diameter equal to and greater than 10 mm, 7.5 mm, and 5 mm, respectively. No other significant differences in performance metrics were observed across demographic or clinical characteristic groups. CONCLUSION: In this study, a commercial deep learning algorithm showed promising results in segmenting brain metastases, with 96.23% sensitivity for metastases with diameters of 5 mm or higher. As the software is an assistive AI, future work of VBrain integration into the clinical workflow can provide further clinical and research insights.
Assuntos
Neoplasias Encefálicas , Aprendizado Profundo , Radiocirurgia , Feminino , Humanos , Masculino , Algoritmos , Inteligência Artificial , Neoplasias Encefálicas/diagnóstico por imagem , Neoplasias Encefálicas/radioterapia , Neoplasias Encefálicas/cirurgia , Radiocirurgia/métodos , Estudos Retrospectivos , Adulto Jovem , Adulto , Pessoa de Meia-Idade , Idoso , Idoso de 80 Anos ou maisRESUMO
Purpose: The aim of this study was to apply the Six Sigma methodology and failure mode and effect analysis (FMEA) to mitigate errors in intensity modulated radiation therapy (IMRT) and stereotactic body radiation therapy (SBRT) treatment planning with the first clinical installation of RefleXion X1. Methods and Materials: The Six Sigma approach consisted of 5 phases: define, measure, analyze, improve, and control. The define, measure, and analyze phases consisted of process mapping and an FMEA of IMRT and SBRT treatment planning on the X1. The multidisciplinary team outlined the workflow process and identified and ranked the failure modes associated with the plan check items using the American Association of Physicists in Medicine Task Group 100 recommendations. Items with the highest average risk priority numbers (RPNs) and severity ≥7 were prioritized for automation using the Eclipse Scripting Application Programming Interface (ESAPI). The "improve" phase consisted of developing ESAPI scripts before the clinical launch of X1 to improve efficiency and safety. In the "control" phase, the FMEA ranking was re-evaluated 1 year after clinical launch. Results: Overall, 100 plan check items were identified in which the RPN values ranged from 10.2 to 429.0. Fifty of these items (50%) were suitable for automation within ESAPI. Of the 10 highest-risk items, 8 were suitable for automation. Based on the results of the FMEA, 2 scripts were developed: Planning Assistant, used by the planner during preparation for planning, and Automated Plan Check, used by the planner and the plan checker during plan preparation for treatment. After 12 months of clinical use of the X1 and developed scripts, only 3 errors were reported. The average prescript RPN was 138.0, compared with the average postscript RPN of 47.8 (P < .05), signifying a safer process. Conclusions: Implementing new technology in the clinic can be an error-prone process in which the likelihood of errors increases with increasing pressure to implement the technology quickly. To limit errors in clinical implementation of the novel RefleXion X1 system, the Six Sigma method was used to identify failure modes, establish quality control checks, and re-evaluate these checks 1 year after clinical implementation.
RESUMO
OBJECTIVES: In this study, we characterise the imaging-mode performance of the positron emission tomography (PET) subsystem of the RefleXion X1 machine using the NEMA NU-2 2018 standard. METHODS: The X1 machine consists of two symmetrically opposing 900 arcs of PET detectors incorporated into the architecture of a ring-gantry linear accelerator rotating up to 60 RPM. PET emissions from a tumour are detected by the PET detectors and used to guide the delivery of radiation beam. Imaging performance of the PET subsystem on X1 machine was evaluated based on sensitivity of the PET detectors, spatial resolution, count-loss performance, image quality, and daily system performance check. RESULTS: PET subsystem sensitivity was measured as 0.183 and 0.161 cps/kBq at the center and off-center positions, respectively. Spatial resolution: average FWHM values of 4.3, 5.1, and 6.7 mm for the point sources at 1, 10, and 20 cm off center, respectively were recorded. For count loss, max NECR: 2.63 kcps, max true coincidence rate: 5.56 kcps, and scatter fraction: 39.8%. The 10 mm sphere was not visible. Image-quality contrast values were: 29.6%, 64.9%, 66.5%, 81.8%, 81.2%, and background variability: 14.8%, 12.4%, 10.3%, 8.8%, 8.3%, for the 13, 17, 22, 28, 37 mm sphere sizes, respectively. CONCLUSIONS: When operating in an imaging mode, the spatial resolution and image contrast of the X1 PET subsystem were comparable to those of typical diagnostic imaging systems for large spheres, while the sensitivity and count rate were lower due to the significantly smaller PET detector area in the X1 system. Clinical efficacy when used in BgRT remains to be validated. ADVANCES IN KNOWLEDGE: This is the first performance evaluation of the PET subsystem on the novel BgRT machine. The dual arcs rotating PET subsystem on RefleXion X1 machine performance is comparable to those of the typical diagnostic PET system based on the spatial resolution and image contrast for larger spheres.