Adaptive MRI-guided radiotherapy (MRIgRT) requires accurate and efficient segmentation of organs and targets on MRI scans. Manual segmentation is time-consuming and variable, while deformable image registration (DIR)-based contour propagation may not account for large anatomical changes. Therefore, we developed and evaluated an automatic segmentation method using the nnU-net framework.The network was trained on 38 patients (76 scans) with localized prostate cancer and tested on 30 patients (60 scans) with localized prostate, metastatic prostate, or bladder cancer treated at a 1.5 T MRI-linac at our institution. The performance of the network was compared with the current clinical workflow based on DIR. The segmentation accuracy was evaluated using the Dice similarity coefficient (DSC), mean surface distance (MSD), and Hausdorff distance (HD) metrics.The trained network successfully segmented all 600 structures in the test set. High similarity was obtained for most structures, with 90% of the contours having a DSC above 0.9 and 86% having an MSD below 1 mm. The largest discrepancies were found in the sigmoid and colon structures. Stratified analysis on cancer type showed that the best performance was seen in the same type of patients that the model was trained on (localized prostate). Especially in patients with bladder cancer, the performance was lower for the bladder and the surrounding organs. A complete automatic delineation workflow took approximately 1 minute. Compared with contour transfer based on the clinically used DIR algorithm, the nnU-net performed statistically better across all organs, with the most significant gain in using the nnU-net seen for organs subject to more considerable volumetric changes due to variation in the filling of the rectum, bladder, bowel, and sigmoid.We successfully trained and tested a network for automatically segmenting organs and targets for MRIgRT in the male pelvis region. Good test results were seen for the trained nnU-net, with test results outperforming the current clinical practice using DIR-based contour propagation at the 1.5 T MRI-linac. The trained network is sufficiently fast and accurate for clinical use in an online setting for MRIgRT. The model is provided as open-source.
With daily, MR-guided online adapted radiotherapy (MRgART) it may be possible to reduce the PTV in pelvic RT. This study investigated the potential reduction in normal tissue complication probability (NTCP) of MRgART compared to standard radiotherapy for high-risk prostate cancer.Twenty patients treated with 78 Gy to the prostate and 56 Gy to elective pelvic lymph nodes were included. VMAT plans were generated with standard clinical PTV margins. Additionally to the planning MR, patients had three MRI scans during treatment to simulate an MRgART. A reference plan with PTV margins determined for MRgART was created per patient and adapted to each of the following MRs. Adapted plans were warped to the planning MR for dose accumulation. The standard plan was rigidly registered to each adaptation MR before it was warped to the planning MR for dose accumulation. Dosimetric impact was compared by DVH analysis and potential clinical effects were assessed by NTCP modeling.MRgART yielded statistically significant lower doses for the bladder wall, rectum and peritoneal cavity, compared to the standard RT, which translated into reduced median risks of urine incontinence (ΔNTCP 2.8%), urine voiding pain (ΔNTCP 2.8%) and acute gastrointestinal toxicity (ΔNTCP 17.4%). Mean population accumulated doses were as good or better for all investigated OAR when planned for MRgART as standard RT.Online adapted radiotherapy may reduce the dose to organs at risk in high-risk prostate cancer patients, due to reduced PTV margins. This potentially translates to significant reductions in the risks of acute and late adverse effects.
5041 Background: Approximately 20% of patients with clinical stage I testicular seminoma will relapse after orchiectomy. No robust prognostic factors for relapse exist which challenges risk assessment and counselling for patients. Previous studies have been hampered by selection bias and variable pathology reporting that limit interpretation and generalization of results. We therefore assessed prognostic factors for relapse in a large unselected nationwide population-based setting with centralized pathology review. Methods: Patients with clinical stage I seminoma diagnosed in Denmark between 2013 and 2018 were identified in the prospective Danish Testicular Cancer database. By linkage to the Danish National Pathology Registry, microscopic slides from the orchiectomy specimens were retrieved and reviewed blinded to the clinical outcome. Clinical data were obtained from medical records with follow-up until July 2022. The association between prespecified clinical and histopathological prognostic factors and relapse were assessed by use of Cox regression analysis. Potential prognostic factors included age, pre-orchiectomy values of β-human chorionic gonadotropin (β-hCG) and lactate dehydrogenase (LDH), tumor size, tumor multifocality, tumor necrosis, lymphovascular invasion, pagetoid rete involvement, and invasion of rete testis, hilar soft tissue, epididymis, spermatic cord, tunica albuginea, and tunica vaginalis. Results: In total, 924 patients were included. During a median follow-up of 6.3 years, 148 (16%) patients relapsed. Invasion of the testicular hilum (rete testis and hilar soft tissue), lymphovascular invasion, and elevated pre-orchiectomy levels of β-hCG and LDH were independent predictors of relapse. The estimated 5-year risk of relapse ranged from 6% in patients with no risk factors, to 64% in patients with all four risk factors with tumor extension into the hilar soft tissue of the testicular hilum. After internal model validation, the model had an overall concordance statistic of 0.70. Conclusions: The provided prognostic factors allow a long-awaited opportunity to make more informed treatment decisions about post-orchiectomy management in patients with clinical stage I seminoma. These should replace current risk factors in guidelines and be used in future studies investigating risk-adapted follow-up and treatment strategies. [Table: see text]
Data related to the article: Front. Oncol. Sec. Radiation Oncology Volume 13 - 2023 | doi: 10.3389/fonc.2023.1285725 An open-source nnU-net algorithm for automatic segmentation of MRI scans in the male pelvis for adaptive radiotherapy Ebbe Laugaard Lorenzen 1,2*, Bahar Celik 1, Nis Sarup1, Lars Dysager3, Rasmus Lübeck Christiansen1, Anders Smedegaard Bertelsen1, Uffe Bernchou1,2, Søren Nielsen Agergaard1, Maximilian Lukas Konrad1, Carsten Brink1,2*, Faisal Mahmood1,2, Tine Schytte2,3, Christina Junker Nyborg3 1 Laboratory of Radiation Physics, Department of Oncology, Odense University Hospital, J. B. Winsløws Vej 4, 5000 Odense C, Denmark 2 Department of Clinical Research, University of Southern Denmark, J.B. Winsløws Vej 19 3., 5000 Odense C, Denmark 3 Department of Oncology, Odense University Hospital, J. B. Winsløws Vej 4, 5000 Odense C, Denmark * Correspondence: Ebbe Laugaard Lorenzen ebbe.lorenzen@rsyd.dk Carsten Brink carsten.brink@rsyd.dk
BackgroundApproximately 30% of patients with clinical stage I non-seminoma (CSI-NS) relapse. Current risk stratification is based on lymphovascular invasion (LVI) alone. The extent to which additional tumor characteristics can improve risk prediction remains unclear.ObjectiveTo determine the most important prognostic factors for relapse in CSI-NS patients. Design, setting, and participants Population-based cohort study including all patients with CSI-NS diagnosed in Denmark between 2013 and 2018 with follow-up until 2022. Patients were identified in the prospective Danish Testicular Cancer database. By linkage to the Danish National Pathology Registry, histological slides from the orchiectomy specimens were retrieved. Outcome measurements and statistical analysis Histological slides were reviewed blinded to the clinical outcome. Clinical data were obtained from medical records. The association between prespecified potential prognostic factors and relapse was assessed using Cox regression analysis. Model performance was evaluated by discrimination (Harrell's C-index) and calibration.ResultsOf 453 patients included, 139 patients (30.6%) relapsed during a median follow-up of 6.3 years. Tumor invasion into the hilar soft tissue of the testicular hilum, tumor size, LVI and embryonal carcinoma were independent predictors of relapse. The estimated 5-year risk of relapse ranged from <5% to >85%, depending on the number of risk factors. After internal model validation, the model had an overall concordance statistic of 0.75. Model calibration was excellent.Conclusion and RelevanceThe identified prognostic factors provide a much more accurate risk stratification than current clinical practice, potentially aiding clinical decision-making.
'%3e%3cpath fill='%23012169' d='M0 0v30h60V0z'/%3e%3cpath stroke='%23fff' stroke-width='6' d='m0 0 60 30m0-30L0 30'/%3e%3cpath stroke='%23C8102E' stroke-width='4' d='m0 0 60 30m0-30L0 30' clip-path='url(%23b)'/%3e%3cpath stroke='%23fff' stroke-width='10' d='M30 0v30M0 15h60'/%3e%3cpath stroke='%23C8102E' stroke-width='6' d='M30 0v30M0 15h60'/%3e%3c/g%3e%3c/svg%3e)