Search

Abstract Background Pelvic morphological parameters on magnetic resonance imaging (MRI), such as the membranous urethral length (MUL), can predict urinary incontinence after radical prostatectomy but are prone to interobserver disagreement. Our objective was to improve interobserver agreement among radiologists in measuring pelvic parameters using deep learning (DL)-based segmentation of pelvic structures on MRI scans. Methods Preoperative MRI was collected from 167 prostate cancer patients undergoing radical prostatectomy within our regional multicentric cohort. Two DL networks (nnU-Net) were trained on coronal and sagittal scans and evaluated on a test cohort using an 80/20% train-test split. Pelvic parameters were manually measured by three abdominal radiologists on raw MRI images and with the use of DL-generated segmentations. Automated measurements were also performed for the pelvic parameters. Interobserver agreement was evaluated using the intraclass correlation coefficient (ICC) and the Bland–Altman plot. Results The DL models achieved median Dice similarity coefficient (DSC) values of 0.85–0.97 for coronal structures and 0.87–0.98 for sagittal structures. When radiologists used DL-generated segmentations of pelvic structures, the interobserver agreement for sagittal MUL improved from 0.64 (95% confidence interval 0.28–0.83) to 0.91 (95% CI 0.84–0.95). Furthermore, there was an increase in ICC values for the obturator internus muscle from 0.74 (95% CI 0.42–0.87) to 0.86 (95% CI 0.75–0.92) and for the levator ani muscle from 0.40 (95% CI 0.05–0.66) to 0.61 (95% CI 0.31–0.78). Conclusions DL-based automated segmentation of pelvic structures improved interobserver agreement in measuring pelvic parameters on preoperative MRI scans. Relevance statement The implementation of deep learning segmentations allows for more consistent measurements of pelvic parameters by radiologists. Standardized measurements are crucial for incorporating these parameters into urinary continence prediction models. Key points • DL-generated segmentations improve interobserver agreement for pelvic measurements among radiologists. • Membranous urethral length measurement improved from substantial to almost perfect agreement. • Artificial intelligence enhances objective pelvic parameter assessment for continence prediction models. Graphical Abstract

Abstract Background Prostate cancer patients with locoregional lymph node disease at diagnosis (N1M0) still have a limited prognosis despite the improvements provided by aggressive curative intent multimodal locoregional external beam radiation therapy (EBRT) with systemic androgen deprivation therapy (ADT). Although some patients can be cured and the majority of patients have a long survival, the 5-year biochemical failure rate is currently 29–47%. [177Lu]Lu-PSMA-617 has shown impressive clinical and biochemical responses with low toxicity in salvage setting in metastatic castration-resistant prostate cancer. This study aims to explore the combination of standard EBRT and ADT complemented with a single administration of [177Lu]Lu-PSMA-617 in curative intent treatment for N1M0 prostate cancer. Hypothetically, this combined approach will enhance EBRT to better control macroscopic tumour localizations, and treat undetected microscopic disease locations inside and outside EBRT fields. Methods The PROQURE-I study is a multicenter prospective phase I study investigating standard of care treatment (7 weeks EBRT and 3 years ADT) complemented with one concurrent cycle (three, six, or nine GBq) of systemic [177Lu]Lu-PSMA-617 administered in week two of EBRT. A maximum of 18 patients with PSMA-positive N1M0 prostate cancer will be included. The tolerability of adding [177Lu]Lu-PSMA-617 will be evaluated using a Bayesian Optimal Interval (BOIN) dose-escalation design. The primary objective is to determine the maximum tolerated dose (MTD) of a single cycle [177Lu]Lu-PSMA-617 when given concurrent with EBRT + ADT, defined as the occurrence of Common Terminology Criteria for Adverse Events (CTCAE) v 5.0 grade three or higher acute toxicity. Secondary objectives include: late toxicity at 6 months, dosimetric assessment, preliminary biochemical efficacy at 6 months, quality of life questionnaires, and pharmacokinetic modelling of [177Lu]Lu-PSMA-617. Discussion This is the first prospective study to combine EBRT and ADT with [177Lu]Lu-PSMA-617 in treatment naïve men with N1M0 prostate cancer, and thereby explores the novel application of [177Lu]Lu-PSMA-617 in curative intent treatment. It is considered likely that this study will confirm tolerability as the combined toxicity of these treatments is expected to be limited. Increased efficacy is considered likely since both individual treatments have proven high anti-tumour effect as mono-treatments. Trial registration ClinicalTrials, NCT05162573 . Registered 7 October 2021.

Abstract Objectives To assess the patient preferences and utility scores for the different conventional and innovative treatment modalities for localised prostate cancer (PCa). Subjects and Methods Patients treated for localised PCa and healthy volunteers were invited to fill out a treatment‐outcome scenario questionnaire. Participants ranked six different treatments for localised PCa from most to least favourable, prior to information. In a next step, treatment procedures, toxicity, risk of biochemical recurrence and follow‐up regimen were comprehensibly described for each of the six treatments (i.e. treatment‐outcome scenarios), after which patients re‐ranked the six treatments. Additionally, participants gave a visual analogue scale (VAS) and time trade‐off (TTO) score for each scenario. Differences between utility scores were tested by Friedman tests with post hoc Wilcoxon signed‐rank tests. Results Eighty patients and twenty‐nine healthy volunteers were included in the study. Before receiving treatment‐outcome scenario information, participants ranked magnetic resonance‐guided adaptive radiotherapy most often as their first choice (35%). After treatment information was received, active surveillance was most often ranked as the first choice (41%). Utility scores were significantly different between the six treatment‐outcome scenarios, and active surveillance, non‐ and minimal‐invasive treatments received higher scores. Conclusions Active surveillance and non‐invasive treatment for localised PCa were the most preferred options by PCa patients and healthy volunteers and received among the highest utility scores. Treatment preferences change after treatment information is received.

Abstract Background Structure delineation is a necessary, yet time-consuming manual procedure in radiotherapy. Recently, convolutional neural networks have been proposed to speed-up and automatise this procedure, obtaining promising results. With the advent of magnetic resonance imaging (MRI)-guided radiotherapy, MR-based segmentation is becoming increasingly relevant. However, the majority of the studies investigated automatic contouring based on computed tomography (CT). Purpose In this study, we investigate the feasibility of clinical use of deep learning-based automatic OARs delineation on MRI. Materials and methods We included 150 patients diagnosed with prostate cancer who underwent MR-only radiotherapy. A three-dimensional (3D) T1-weighted dual spoiled gradient-recalled echo sequence was acquired with 3T MRI for the generation of the synthetic-CT. The first 48 patients were included in a feasibility study training two 3D convolutional networks called DeepMedic and dense V-net (dV-net) to segment bladder, rectum and femurs. A research version of an atlas-based software was considered for comparison. Dice similarity coefficient, 95% Hausdorff distances (HD95), and mean distances were calculated against clinical delineations. For eight patients, an expert RTT scored the quality of the contouring for all the three methods. A choice among the three approaches was made, and the chosen approach was retrained on 97 patients and implemented for automatic use in the clinical workflow. For the successive 53 patients, Dice, HD95 and mean distances were calculated against the clinically used delineations. Results DeepMedic, dV-net and the atlas-based software generated contours in 60 s, 4 s and 10-15 min, respectively. Performances were higher for both the networks compared to the atlas-based software. The qualitative analysis demonstrated that delineation from DeepMedic required fewer adaptations, followed by dV-net and the atlas-based software. DeepMedic was clinically implemented. After retraining DeepMedic and testing on the successive patients, the performances slightly improved. Conclusion High conformality for OARs delineation was achieved with two in-house trained networks, obtaining a significant speed-up of the delineation procedure. Comparison of different approaches has been performed leading to the succesful adoption of one of the neural networks, DeepMedic, in the clinical workflow. DeepMedic maintained in a clinical setting the accuracy obtained in the feasibility study.

Background: Deep learning‐based unsupervised image registration has recently been proposed, promising fast registration. However, it has yet to be adopted in the online adaptive magnetic resonance imaging‐guided radiotherapy (MRgRT) workflow. Purpose: In this paper, we design an unsupervised, joint rigid, and deformable registration framework for contour propagation in MRgRT of prostate cancer. Methods: Three‐dimensional pelvic T2‐weighted MRIs of 143 prostate cancer patients undergoing radiotherapy were collected and divided into 110, 13, and 20 patients for training, validation, and testing. We designed a framework using convolutional neural networks (CNNs) for rigid and deformable registration. We selected the deformable registration network architecture among U‐Net, MS‐D Net, and LapIRN and optimized the training strategy (end‐to‐end vs. sequential). The framework was compared against an iterative baseline registration. We evaluated registration accuracy (the Dice and Hausdorff distance of the prostate and bladder contours), structural similarity index, and folding percentage to compare the methods. We also evaluated the framework's robustness to rigid and elastic deformations and bias field perturbations. Results: The end‐to‐end trained framework comprising LapIRN for the deformable component achieved the best median (interquartile range) prostate and bladder Dice of 0.89 (0.85–0.91) and 0.86 (0.80–0.91), respectively. This accuracy was comparable to the iterative baseline registration: prostate and bladder Dice of 0.91 (0.88–0.93) and 0.86 (0.80–0.92). The best models complete rigid and deformable registration in 0.002 (0.0005) and 0.74 (0.43) s (Nvidia Tesla V100‐PCIe 32 GB GPU), respectively. We found that the models are robust to translations up to 52 mm, rotations up to 15∘$^\circ$, elastic deformations up to 40 mm, and bias fields. Conclusions: Our proposed unsupervised, deep learning‐based registration framework can perform rigid and deformable registration in less than a second with contour propagation accuracy comparable with iterative registration. [ABSTRACT FROM AUTHOR]

The new radiotherapy high field, 1.5 Tesla MRI-guided linear accelerator (MR-Linac) is being clinically introduced. Sensing and evaluating opportunities and barriers at an early stage will facilitate its eventual scale-up. This study investigates the opportunities and barriers to the implementation of MR-Linac into prostate cancer care based on 43 semi-structured interviews with Dutch oncology care professionals, hospital and division directors, patients, payers and industry. The analysis was guided by the Non-adoption, Abandonment, Scale-up, Spread, and Sustainability framework of new medical technologies and services. Opportunities included: the acquirement of (1) advanced MRI-guided radiotherapy technology with (2) the potential for improved patient outcomes and (3) economic benefits, as well as (4) professional development and (5) a higher hospital quality profile. Barriers included: (1) technical complexities, (2) substantial staffing and structural investments, (3) the current lack of empirical evidence of clinical benefits, (4) professional silos, and (5) the presence of patient referral patterns. While our study confirms the expected technical and clinical prospects from the literature, it also reveals economic, organizational, and socio-political challenges.

Abstract Background The use of intraprostatic gold fiducial markers (FMs) ensures highly accurate and precise image-guided radiation therapy for patients diagnosed with prostate cancer thanks to the ease of localising FMs on photon-based imaging, like Computed Tomography (CT) images. Recently, Magnetic Resonance (MR)-only radiotherapy has been proposed to simplify the workflow and reduce possible systematic uncertainties. A critical, determining factor in the accuracy of such an MR-only simulation will be accurate FM localisation using solely MR images. Purpose The aim of this study is to evaluate the performances of manual MR-based FM localisation within a clinical environment. Methods We designed a study in which 5 clinically involved radiation therapy technicians (RTTs) independently localised the gold FMs implanted in 16 prostate cancer patients in two scenarios: employing a single MR sequence or a combination of sequences. Inter-observer precision and accuracy were assessed for the two scenarios for localisation in terms of 95% limit of agreement on single FMs (LoA)/ centre of mass (LoA CM) and inter-marker distances (IDs), respectively. Results The number of precisely located FMs (LoA