Search

Contains fulltext : 296077.pdf (Publisher’s version ) (Open Access), PURPOSE: To compare transarterial chemoembolization delivered with drug eluting beads (TACE-DEB) with stereotactioc body radiation therapy (SBRT) in patients with hepatocellular carcinoma (HCC) in a multicenter randomized trial. METHODS AND MATERIALS: Patients were included if they were eligible for TACE. They could also be recruited if they required treatment prior to liver transplantation. A maximum of four TACE-DEB procedures and ablation after incomplete TACE-DEB were both allowed. SBRT was delivered in six fractions of 8-9Gy. Primary end point was time to progression (TTP). Secondary endpoints were local control (LC), overall survival (OS), response rate (RR), toxicity, and quality of life (QoL). The calculated sample size was 100 patients. RESULTS: Between May 2015 and April 2020, 30 patients were randomized to the study. Due to slow accrual the trial was closed prematurely. Two patients in the SBRT arm were considered ineligible leaving 16 patients in the TACE-DEB arm and 12 in the SBRT arm. Median follow-up was 28.1 months. Median TTP was 12 months for TACEDEB and 19 months for SBRT (p=0.15). Median LC was 12 months for TACE-DEB and >40 months (not reached) for SBRT (p=0.075). Median OS was 36.8 months for TACEDEB and 44.1 months for SBRT (p=0.36). A post-hoc analysis showed 100% for SBRT 1- and 2-year LC, and 54.4% and 43.6% for TACE-DEB (p=0.019). Both treatments resulted in RR>80%. Three episodes of possibly related toxicity grade ≥3 were observed after TACE-DEB. No episodes were observed after SBRT. QoL remained stable after both treatment arms. CONCLUSIONS: In this trial, TTP after TACE-DEB was not significantly improved by SBRT, while SBRT showed higher local antitumoral activity than TACE-DEB, without detrimental effects on OS, toxicity and QoL. To overcome poor accrual in randomized trials that include SBRT, and to generate evidence for including SBRT in treatment guidelines, international cooperation is needed.

Deep learning models benefit from training with a large dataset (labeled or unlabeled). Following this motivation, we present an approach to learn a deep learning model for the automatic segmentation of Organs at Risk (OARs) in cervical cancer radiation treatment from a large clinically available dataset of Computed Tomography (CT) scans containing data inhomogeneity, label noise, and missing annotations. We employ simple heuristics for automatic data cleaning to minimize data inhomogeneity and label noise. Further, we develop a semi-supervised learning approach utilizing a teacher-student setup, annotation imputation, and uncertainty-guided training to learn in presence of missing annotations. Our experimental results show that learning from a large dataset with our approach yields a significant improvement in the test performance despite missing annotations in the data. Further, the contours generated from the segmentation masks predicted by our model are found to be equally clinically acceptable as manually generated contours.

Purpose: This prospective study evaluates our first clinical experiences with the novel ‘‘BRachytherapy via artificial Intelligent GOMEA-Heuristic based Treatment planning'' (BRIGHT) applied to high-dose-rate prostate brachytherapy. MethodS AND MATERIALs: Between March 2020 and October 2021, 14 prostate cancer patients were treated in our center with a 15Gy HDR-brachytherapy boost. BRIGHT was used for bi-objective treatment plan optimization and selection of the most desirable plans from a coverage-sparing trade-off curve. Selected BRIGHT plans were imported into the commercial treatment planning system Oncentra Brachy. In Oncentra Brachy a dose distribution comparison was performed for clinical plan choice, followed by manual fine-tuning of the preferred BRIGHT plan when deemed necessary. The reasons for plan selection, clinical plan choice, and fine-tuning, as well as process speed were monitored. For each patient, the dose-volume parameters of the (fine-tuned) clinical plan were evaluated. Results: In all patients, BRIGHT provided solutions satisfying all protocol values for coverage and sparing. In four patients not all dose-volume criteria of the clinical plan were satisfied after manual fine-tuning. Detailed information on tumour coverage, dose-distribution, dwell time pattern, and insight provided by the patient-specific trade-off curve, were used for clinical plan choice. Median time spent on treatment planning was 42 min, consisting of 16 min plan optimization and selection, and 26 min undesirable process steps. ConclusionS: BRIGHT is implemented in our clinic and provides automated prostate high-dose-rate brachytherapy planning with trade-off based plan selection. Based on our experience, additional optimization aims need to be implemented to further improve direct clinical applicability of treatment plans and process efficiency.

Purpose: Deformable image registration (DIR) can benefit from additional guidance using corresponding landmarks in the images. However, the benefits thereof are largely understudied, especially due to the lack of automatic landmark detection methods for three-dimensional (3D) medical images. Approach: We present a deep convolutional neural network (DCNN), called DCNN-Match, that learns to predict landmark correspondences in 3D images in a self-supervised manner. We trained DCNN-Match on pairs of computed tomography (CT) scans containing simulated deformations. We explored five variants of DCNN-Match that use different loss functions and assessed their effect on the spatial density of predicted landmarks and the associated matching errors. We also tested DCNN-Match variants in combination with the open-source registration software Elastix to assess the impact of predicted landmarks in providing additional guidance to DIR. Results: We tested our approach on lower abdominal CT scans from cervical cancer patients: 121 pairs containing simulated deformations and 11 pairs demonstrating clinical deformations. The results showed significant improvement in DIR performance when landmark correspondences predicted by DCNN-Match were used in the case of simulated (p = 0e0) as well as clinical deformations (p = 0.030). We also observed that the spatial density of the automatic landmarks with respect to the underlying deformation affect the extent of improvement in DIR. Finally, DCNN-Match was found to generalize to magnetic resonance imaging scans without requiring retraining, indicating easy applicability to other datasets. Conclusions: DCNN-match learns to predict landmark correspondences in 3D medical images in a self-supervised manner, which can improve DIR performance.

Deep learning models benefit from training with a large dataset (labeled or unlabeled). Following this motivation, we present an approach to learn a deep learning model for the automatic segmentation of Organs at Risk (OARs) in cervical cancer radiation treatment from a large clinically available dataset of Computed Tomography (CT) scans containing data inhomogeneity, label noise, and missing annotations. We employ simple heuristics for automatic data cleaning to minimize data inhomogeneity and label noise. Further, we develop a semi-supervised learning approach utilizing a teacher-student setup, annotation imputation, and uncertainty-guided training to learn in presence of missing annotations. Our experimental results show that learning from a large dataset with our approach yields a significant improvement in the test performance despite missing annotations in the data. Further, the contours generated from the segmentation masks predicted by our model are found to be equally clinically acceptable as manually generated contours.

Contains fulltext : 232797.pdf (Publisher’s version ) (Open Access), PURPOSE: Although various studies have reported that stereotactic body radiation therapy (SBRT) for liver metastases has high local control rates and relatively low toxicity, most series included a small number of patients. We aimed to validate these outcomes in a large multi-institution patient cohort treated in accordance with a common protocol. METHODS AND MATERIALS: A shared web-based registry of patients with liver metastases treated with SBRT was developed by 13 centers (12 in the Netherlands and 1 in Belgium). All the centers had previously agreed on the items to be collected, the fractionation schemes, and the organs-at-risk constraints to be applied. Follow-up was performed at the discretion of the centers. Patient, tumor, and treatment characteristics were entered in the registry. Only liver metastases treated individually as independent targets and with at least 1 radiologic follow-up examination were considered for local control analysis. Toxicity of grade 3 or greater was scored according to the Common Terminology Criteria of Adverse Events (v4.03). RESULTS: Between January 1, 2013, and July 31, 2019, a total of 515 patients were entered in the web-based registry. The median age was 71 years. In total, 668 liver metastases were registered, and 447 were included for local control analysis. The most common primary tumor origin was colorectal cancer (80.3%), followed by lung cancer (8.9%) and breast cancer (4%). The most-used fractionation scheme was 3x18-20 Gy (36.0%), followed by 8x7.5 Gy (31.8%), 5x11-12 Gy (25.5%), and 12x5 Gy (6.7%). The median follow-up time was 1.1 years for local control and 2.3 years for survival. Actuarial 1-year local control was 87%; 1-year overall survival was 84%. Toxicity of grade 3 or greater was found in 3.9% of the patients. CONCLUSIONS: This multi-institutional study confirms the high rates of local control and limited toxicity in a large patient cohort. Stereotactic body radiation therapy should be considered a valuable

Purpose: Although various studies have reported that stereotactic body radiation therapy (SBRT) for liver metastases has high local control rates and relatively low toxicity, most series included a small number of patients. We aimed to validate these outcomes in a large multi-institution patient cohort treated in accordance with a common protocol. Methods and Materials: A shared web-based registry of patients with liver metastases treated with SBRT was developed by 13 centers (12 in the Netherlands and 1 in Belgium). All the centers had previously agreed on the items to be collected, the fractionation schemes, and the organs-at-risk constraints to be applied. Follow-up was performed at the discretion of the centers. Patient, tumor, and treatment characteristics were entered in the registry. Only liver metastases treated individually as independent targets and with at least 1 radiologic follow-up examination were considered for local control analysis. Toxicity of grade 3 or greater was scored according to the Common Terminology Criteria of Adverse Events (v4.03). Results: Between January 1, 2013, and July 31, 2019, a total of 515 patients were entered in the web-based registry. The median age was 71 years. In total, 668 liver metastases were registered, and 447 were included for local control analysis. The most common primary tumor origin was colorectal cancer (80.3%), followed by lung cancer (8.9%) and breast cancer (4%). The most-used fractionation scheme was 3x18-20 Gy (36.0%), followed by 8x7.5 Gy (31.8%), 5x11-12 Gy (25.5%), and 12x5 Gy (6.7%). The median follow-up time was 1.1 years for local control and 2.3 years for survival. Actuarial 1-year local control was 87%; 1-year overall survival was 84%. Toxicity of grade 3 or greater was found in 3.9% of the patients. Conclusions: This multi-institutional study confirms the high rates of local control and limited toxicity in a large patient cohort. Stereotactic body radiation therapy should be considered a valuable

Purpose: Bi-objective treatment planning for high-dose-rate prostate brachytherapy is a novel treatment planning method with two separate objectives that represent target coverage and organ-at-risk sparing. In this study, we investigated the feasibility and plan quality of this method by means of a retrospective observer study.Methods and Materials: Current planning sessions were recorded to configure a bi-objective optimization model and to assess its applicability to our clinical practice. Optimization software, GOMEA, was then used to automatically generate a large set of plans with different trade-offs in the two objectives for each of 18 patients treated with high-dose-rate prostate brachytherapy. From this set, five plans per patient were selected for comparison to the clinical plan in terms of satisfaction of planning criteria and in a retrospective observer study. Three brachytherapists were asked to evaluate the blinded plans and select the preferred one.Results: Recordings demonstrated applicability of the bi-objective optimization model to our clinical practice. For 14/18 patients, GOMEA plans satisfied all planning criteria, compared with 4/18 clinical plans. In the observer study, in 53/54 cases, a GOMEA plan was preferred over the clinical plan. When asked for consensus among observers, this ratio was 17/18 patients. Observers highly appreciated the insight gained from comparing multiple plans with different trade-offs simultaneously.Conclusions: The bi-objective optimization model adapted well to

Item does not contain fulltext, BACKGROUND AND PURPOSE: The TRENDY trial is an international multi-center phase-II study, randomizing hepatocellular carcinoma (HCC) patients between transarterial chemoembolization (TACE) and stereotactic body radiation therapy (SBRT) with a target dose of 48-54Gy in six fractions. The radiotherapy quality assurance (QA) program, including prospective plan feedback based on automated treatment planning, is described and results are reported. MATERIALS AND METHODS: Scans of a single patient were used as a benchmark case. Contours submitted by nine participating centers were compared with reference contours. The subsequent planning round was based on a single set of contours. A total of 20 plans from participating centers, including 12 from the benchmark case, 5 from a clinical pilot and 3 from the first study patients, were compared to automatically generated VMAT plans. RESULTS: For the submitted liver contours, Dice Similarity Coefficients (DSC) with the reference delineation ranged from 0.925 to 0.954. For the GTV, the DSC varied between 0.721 and 0.876. For the 12 plans on the benchmark case, healthy liver normal-tissue complication probabilities (NTCPs) ranged from 0.2% to 22.2% with little correlation between NCTP and PTV-D95% (R(2)<0.3). Four protocol deviations were detected in the set of 20 treatment plans. Comparison with co-planar autoVMAT QA plans revealed these were due to too high target dose and suboptimal planning. Overall, autoVMAT resulted in an average liver NTCP reduction of 2.2 percent point (range: 16.2 percent point to -1.8 percent point, p=0.03), and lower doses to the healthy liver (p<0.01) and gastrointestinal organs at risk (p<0.001). CONCLUSIONS: Delineation variation resulted in feedback to participating centers. Automated treatment planning can play an important role in clinical trials for prospective plan QA as suboptimal plans were detected.