Prostate Cancer Treatment Planning Research Articles

Abstract LB390: Enhancing prostate cancer diagnosis: A deep learning approach for DNA ploidy prediction from whole slide images

Abstract Prostate cancer is distinguished by unique histological alterations in glandular architecture, observable in Whole Slide Images (WSIs). The disease is further characterized by pronounced genomic instability, exemplified by biomarkers such as DNA ploidy. While the Gleason Score effectively assesses the histological changes, the manual evaluation of DNA ploidy is subjective and time-consuming. Addressing the need for an objective diagnostic tool, our study developed a deep learning model aimed at accurately predicting DNA ploidy using publicly available WSI from the Cancer Genome Atlas (TCGA). Utilizing a ResNet-18 convolutional neural network, we trained the model on WSIs from 200 TCGA patients to extract features and predict total mRNA expression. The model was further refined using data from 19 TCGA patients, focusing on ploidy number prediction. Comparative analysis against a random reference model revealed significant improvements of ploidy prediction in Mean Absolute Error (MAE) by 43.52%, Mean Absolute Percentage Error (MAPE) by 43.59%, and Mean Squared Error (MSE) by 67.86%. These enhancements were statistically validated (p-values: MAE - 7.07E-06, MAPE - 7.69E-06, MSE - 3.14E-05) and substantiated by large Cohen's d values (MAE - 2.88, MAPE - 2.86, MSE - 2.42), confirming the model's advanced predictive accuracy and practical utility. This approach, validated further on a separate TCGA hold-out test set, signifies a major leap in prostate cancer diagnostics. By integrating mRNA prediction checkpoints, our model not only refines ploidy assessment but also sets the stage for correlating these predictions with patient clinical outcomes. These developments promise to enhance existing diagnostic methods, offering a more objective and efficient tool for DNA ploidy assessment in prostate cancer prognosis and treatment planning. Citation Format: Josselyn Sofia Vergara Cobos, Francisco Carrillo-Perez, Marija Pizurica, Noemi Andor, Olivier Gevaert. Enhancing prostate cancer diagnosis: A deep learning approach for DNA ploidy prediction from whole slide images [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 2 (Late-Breaking, Clinical Trial, and Invited Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(7_Suppl):Abstract nr LB390.

Deep learning based automatic segmentation of the Internal Pudendal Artery in definitive radiotherapy treatment planning of localized prostate cancer

Background and purposeRadiation-induced erectile dysfunction (RiED) commonly affects prostate cancer patients, prompting clinical trials across institutions to explore dose-sparing to internal-pudendal-arteries (IPA) for preserving sexual potency. IPA, challenging to segment, isn't conventionally considered an organ-at-risk (OAR). This study proposes a deep learning (DL) auto-segmentation model for IPA, using Computed Tomography (CT) and Magnetic Resonance Imaging (MRI) or CT alone to accommodate varied clinical practices. Materials and methodsA total of 86 patients with CT and MRI images and noisy IPA labels were recruited in this study. We split the data into 42/14/30 for model training, testing, and a clinical observer study, respectively. There were three major innovations in this model: 1) we designed an architecture with squeeze-and-excite blocks and modality attention for effective feature extraction and production of accurate segmentation, 2) a novel loss function was used for training the model effectively with noisy labels, and 3) modality dropout strategy was used for making the model capable of segmentation in the absence of MRI. ResultsTest dataset metrics were DSC 61.71 ± 7.7 %, ASD 2.5 ± .87 mm, and HD95 7.0 ± 2.3 mm. AI segmented contours showed dosimetric similarity to expert physician’s contours. Observer study indicated higher scores for AI contours (mean = 3.7) compared to inexperienced physicians’ contours (mean = 3.1). Inexperienced physicians improved scores to 3.7 when starting with AI contours. ConclusionThe proposed model achieved good quality IPA contours to improve uniformity of segmentation and to facilitate introduction of standardized IPA segmentation into clinical trials and practice.

CycleSeg: Simultaneous synthetic CT generation and unsupervised segmentation for MR-only radiotherapy treatment planning of prostate cancer.

MR-only radiotherapy treatment planning is an attractive alternative to conventional workflow, reducing scan time and ionizing radiation. It is crucial to derive the electron density map or synthetic CT (sCT) from MR data to perform dose calculations to enable MR-only treatment planning. Automatic segmentation of relevant organs in MR images can accelerate the process by preventing the time-consuming manual contouring step. However, the segmentation label is available only for CT data in many cases. We propose CycleSeg, a unified framework that generates sCT and corresponding segmentation from MR images without access to MR segmentation labels METHODS: CycleSeg utilizes the CycleGAN formulation to perform unpaired synthesis of sCT and image alignment. To enable MR (sCT) segmentation, CycleSeg incorporates unsupervised domain adaptation by using a pseudo-labeling approach with feature alignment in semantic segmentation space. In contrast to previous approaches that perform segmentation on MR data, CycleSeg could perform segmentation on both MR and sCT. Experiments were performed with data from prostate cancer patients, with 78/7/10 subjects in the training/validation/test sets, respectively. CycleSeg showed the best sCT generation results, with the lowest mean absolute error of 102.2 and the lowest Fréchet inception distance of 13.0. CycleSeg also performed best on MR segmentation, with the highest average dice score of 81.0 and 81.1 for MR and sCT segmentation, respectively. Ablation experiments confirmed the contribution of the proposed components of CycleSeg. CycleSeg effectively synthesized CT and performed segmentation on MR images of prostate cancer patients. Thus, CycleSeg has the potential to expedite MR-only radiotherapy treatment planning, reducing the prescribed scans and manual segmentation effort, and increasing throughput.

Understanding Relative Biological Effectiveness and Clinical Outcome of Prostate Cancer Therapy Using Particle Irradiation: Analysis of Tumor Control Probability With the Modified Microdosimetric Kinetic Model

Purpose: Recent experimental studies and clinical trial results might indicate that - at least for some indications - continued use of the mechanistic model for relative biological effectiveness (RBE) applied at carbon ion therapy facilities in Europe for several decades (LEM-I) may be unwarranted. We present a novel clinical framework for prostate cancer treatment planning and tumor control probability (TCP) prediction based on the modified microdosimetric kinetic model (mMKM) for particle therapy. Methods: Treatment plans of 91 prostate tumor patients (proton: 46, carbon ions: 45) applying 66GyRBE [RBE=1.1 for protons and LEM-I, (α/β)x=2.0Gy, for carbon ions] in 20 fractions were recalculated using mMKM ((α/β)x=3.1Gy). Based solely on the response data of photon-irradiated patient groups stratified according to risk and usage of ADT, we derived parameters for an mMKM-based Poisson-TCP model. Subsequently, new carbon and helium ion plans, adhering to prescribed biological dose criteria, were generated. These were systematically compared to the clinical experience of Japanese centers employing an analogous fractionation scheme and existing proton plans. Results: mMKM predictions suggested significant biological dose deviation between proton and carbon ion arms. Patients irradiated with protons received 3.25±0.08GyRBEmMKM/Fx, while patients treated with carbon ions received 2.51±0.05GyRBEmMKM/Fx. TCP predictions were 86±3% for protons and 52±4% for carbon ions, matching the clinical outcome of 85% and 50%. Newly optimized carbon ion plans, guided by the mMKM/TCP model, effectively replicated clinical data from Japanese centers. Using mMKM, helium ions exhibited similar target coverage as proton and carbon ions and an improved rectum and bladder sparing compared to proton. Conclusions: Our mMKM-based model for prostate cancer treatment planning and TCP prediction was validated against clinical data for proton and carbon ion therapy and its application was extended to helium ion therapy. Based on the data presented in this work, mMKM seems to be a good candidate for clinical biological calculations in carbon ion therapy for prostate cancer.

Impact of 68Ga-PSMA PET/CT on Survival and Management in Prostate Cancer.

68Ga-labeled prostate-specific membrane antigen positron emission tomography-computed tomography (68Ga-PSMA PET/CT) has led to altered treatment plans for prostate cancer (PCa) patients. This study aimed to investigate the impact of 68Ga-PSMA PET/CT on overall survival (OS) and management in PCa. Consecutive 100 patients who had 68Ga-PSMA PET/CT and conventional imaging (CI) were included in this retrospective study. Disease stages and treatment plans according to both CI and 68Ga-PSMA PET/CT were compared. The effect of 68Ga-PSMA PET/CT on OS was assessed. After 68Ga-PSMA PET/CT, the stage changed in 64 patients (64%). By the reason of 68Ga-PSMA PET/CT findings, treatment plans based on CI were changed in 73 patients (73%). According to the ROC analysis, patients with a PSA value below 8 had higher rates of change in staging (p<0.0001) and treatment (p=0.034). Both a PSA below 8 (OR 8.79 95% CI (2.72-28.43), p<0.001), and having a hormone-sensitive disease at the time of imaging (OR 5.6 95% CI (1.35-23.08), p=0.017) were significant independent factors predicting change in staging with 68Ga-PSMA PET/CT. The results of a phi correlation coefficient analysis showed a significant relationship between therapy and changes in staging (ϕ=0.638, p<0.0001). Two-year OS was statistically different in hormone-sensitive patients with and without treatment change (95% vs 81%, p=0.006). 68Ga-PSMA PET/CT has the effect of changing the treatment in 73% of PCa patients. There is a positive correlation between the changes in staging and treatment. Survival of hormone sensitive patients has improved due to treatment changes based on PET/CT findings.

Different aspects of plan complexity in prostate VMAT plans

In this work we evaluated VMAT plan complexity by using different methods and approaches: complexity related to the aperture shape, the nature of the dynamic delivery, the impact of delivery variations as well as complexity analyses based on measurements. Prostate cancer treatment plans with different levels of complexity were created for three different patient cases. The plans intended to be most complex were also scored to be the most complex according to the evaluation methods used. The results for the other plans were more diverse. The methods that included 3D spatial information on complexity gave additional information important for the analysis of clinical relevance. In order to use specific complexity estimation methods for taking clinical decisions it is essential to understand how different aspects of complexity are incorporated in each method.

Artificial Intelligence-Based Organ Delineation for Radiation Treatment Planning of Prostate Cancer on Computed Tomography

Meticulous manual delineations of the prostate and the surrounding organs at risk are necessary for prostate cancer radiation therapy to avoid side effects to the latter. This process is time consuming and hampered by inter- and intraobserver variability, all of which could be alleviated by artificial intelligence (AI). This study aimed to evaluate the performance of AI compared with manual organ delineations on computed tomography (CT) scans for radiation treatment planning. Manual delineations of the prostate, urinary bladder, and rectum of 1530 patients with prostate cancer who received curative radiation therapy from 2006 to 2018 were included. Approximately 50% of those CT scans were used as a training set, 25% as a validation set, and 25% as a test set. Patients with hip prostheses were excluded because of metal artifacts. After training and fine-tuning with the validation set, automated delineations of the prostate and organs at risk were obtained for the test set. Sørensen-Dice similarity coefficient, mean surface distance, and Hausdorff distance were used to evaluate the agreement between the manual and automated delineations. The median Sørensen-Dice similarity coefficient between the manual and AI delineations was 0.82, 0.95, and 0.88 for the prostate, urinary bladder, and rectum, respectively. The median mean surface distance and Hausdorff distance were 1.7 and 9.2 mm for the prostate, 0.7 and 6.7 mm for the urinary bladder, and 1.1 and 13.5 mm for the rectum, respectively. Automated CT-based organ delineation for prostate cancer radiation treatment planning is feasible and shows good agreement with manually performed contouring.

Dosimetric Plan Evaluation of Biology Guided Radiotherapy Using [18F]-DCFPyL PSMA Radiotracer in Patients with Prostate Cancer

The X1 system represents a cutting-edge solution in radiotherapy delivery, with its capability to perform Biology Guided Radiotherapy (BgRT). The system utilizes real-time positron emission tomography (PET) signal as biological fiducials to provide tracked dose delivery and is initially available for use with [18F]-Fluorodeoxyglucose (FDG). The aim of this research study is to assess the quality of BgRT treatment plans for prostate cancer using patients' PSMA PET images obtained on the X1 system. Sixteen patients with at least one PET-avid tumor identified on their whole-body diagnostic PSMA PET scan were selected. These patients were scanned on X1 following their diagnostic scan without additional radiotracer administration. Based on the X1 PET images, a BgRT plan was created for each patient, with the prescription dose determined by the location of treatment sites. The planning objectives of organs-at-risk (OARs) were established in accordance with the 2018 Timmerman guidelines. Target coverage objective was the dose covering 95% (D95%) of the planning target volume (PTV) to be higher than 100%. The following parameters were analyzed: PTV D95%, the minimal dose (Dmin) of gross tumor volume (GTV), plan maximum dose (Dmax), conformity index (CI), gradient index (GI), and maximum point dose (D0.03cc) to the nearest OARs. The X1 BgRT planning system also generated dose volume histogram (DVH) bounds, which model variations in BgRT delivery. The low boundary of GTV Dmin, representing the minimum GTV dose in the worst-case scenario, was recorded. BgRT plans were created for all patients, except for one where the target signal was indistinguishable from the bladder. The prescription dose was 2700 cGy or 3000 cGy in 3 fractions for lymph node lesions, 2400 cGy to 3000 cGy in 3 fractions for bone metastasis, and 4500 cGy in 5 fractions for lesions in prostate. All plans met the dose constraints for OARs as per the Timmerman guidelines. The Dmax of all plans was 129.9% ± 6.9% (mean ± standard deviation). The PTV D95% and GTV Dmin were 101.7% ± 1.0% and 111.0% ± 7.6%, respectively. The low boundary of GTV Dmin was 95.9% ± 5.8%. The CI and GI were 1.22 ± 0.11 and 9.40 ± 2.12, respectively. The D0.03cc to nearest OARs was 84.6% ± 25.4%. The estimated treatment time was 699 ± 228 seconds. This study is a pioneering effort to evaluate the quality of BgRT plans for prostate cancer patients using the [18F]-DCFPyL PSMA radiotracer. Our results showed that all BgRT plans met the planning objectives defined in the Timmerman protocol. BgRT with [18F]-DCFPyL represents a promising treatment modality for patients with prostate cancer. Further research is needed to validate this approach, including a comprehensive assessment of the dosimetric and tracking accuracy through physical measurements.

Clinical Implementation of Weak Magnetic Field Generator in Radiation Therapy

The application of weak magnetic fields may improve radiation therapy efficacy by manipulating the free radical activity induced by radiation to optimize tumor death. Once the device is commercially available, we will conduct clinical trials to determine the clinical impact of the weak magnetic field. However, the magnetic field generator (MFG) restricts Linac gantry rotation to approximately 180° and this limitation may limit treatment plan quality. This work is a continuation of an ongoing study to determine if the gantry angle restrictions can be compensated for during treatment planning. Previous work has demonstrated the feasibility for GBM cases. For this work, 10 prostate cancer treatment plans were retrospectively replanned using only coplanar arcs that spanned from 90° to 270° (half-arcs). The prescriptions were 60 Gy for 6 patients, 55.8 Gy for 2 patients, 54 Gy for 1 patient, and 40.05 Gy for 1 patient. The prescription doses were delivered to 95% of the planning target volume (PTV = GTV + 2 cm). The critical structure doses were compared to determine if clinically equivalent plans could be delivered using half-arcs. The dose criteria that were met by the clinical plans were also met by the half-arc plans except for the cases shown in Table 1. Table 1: Doses that did not meet criteria CONCLUSION: The half-arc plans were able to deliver clinically equivalent dose distributions as the clinical treatment plans. This provides continuing evidence that clinical trials will be able to be developed to evaluate the use of weak magnetic fields for radiation therapy.

Opportunities for prostate-specific membrane antigen hybrid imaging in prostate cancer

Prostate-specific membrane antigen (PSMA) hybrid imaging is apromising new technique gaining importance in the field of prostate cancer (PCa) diagnosis and treatment planning. By combining PSMA radioligands and computed tomography (CT) or magnetic resonance imaging (MRI), PSMA hybrid imaging opens up new diagnostic opportunities. PSMA-PET/CT (PET: positron-emission tomography) is already well established in high-risk PCa for primary staging and tumor localization when biochemical recurrence occurs. Further potential indications for PSMA-PET/CT include tumor detection in the initial work-up before arebiopsy with improved accuracy, the identification of target structures for precise local treatment in recurrent PCa (salvage radiotherapy or radio-guided surgery) as well as aprediction of response to PSMA radioligand therapy. This narrative review is based on arecent literature search and aims to highlight the opportunities of PSMA imaging in different disease stages of PCa.

Dual attention guided multiscale neural network trained with curriculum learning for noninvasive prediction of Gleason Grade Group from MRI.

The Gleason Grade Group (GG) is essential in assessing the malignancy of prostate cancer (PCa) and is typically obtained by invasive biopsy procedures in which sampling errors could lead to inaccurately scored GGs. With the gradually recognized value of bi-parametric magnetic resonance imaging (bpMRI) in PCa, it is beneficial to noninvasively predict GGs from bpMRI for early diagnosis and treatment planning of PCa. However, it is challenging to establish the connection between bpMRI features and GGs. In this study, we propose a dual attention-guided multiscale neural network (DAMS-Net) to predict the 5-scored GG from bpMRI and design a training curriculum to further improve the prediction performance. The proposed DAMS-Net incorporates a feature pyramid network (FPN) to fully extract the multiscale features for lesions of varying sizes and a dual attention module to focus on lesion and surrounding regions while avoiding the influence of irrelevant ones. Furthermore, to enhance the differential ability for lesions with the inter-grade similarity and intra-grade variation in bpMRI, the training process employs a specially designed curriculum based on the differences between the radiological evaluations and the ground truth GGs. Extensive experiments were conducted on a private dataset of 382 patients and the public PROSTATEx-2 dataset. For the private dataset, the experimental results showed that the proposed network performed better than the plain baseline model for GG prediction, achieving a mean quadratic weighted Kappa (Kw ) of 0.4902 and a mean positive predictive value of 0.9098 for predicting clinically significant cancer (PPVGG>1 ). With the application of curriculum learning, the mean Kw and PPVGG>1 further increased to 0.5144 and 0.9118, respectively. For the public dataset, the proposed method achieved state-of-the-art results of 0.5413 Kw and 0.9747 PPVGG>1 . The proposed DAMS-Net trained with curriculum learning can effectively predict GGs from bpMRI, which may assist clinicians in early diagnosis and treatment planning for PCa patients.

A Prospective Evaluation of Individualized CONstraints for Radiation Therapy Planning in Prostate Cancer (ICON-P)

<h3>Purpose/Objective(s)</h3> Present planning practices for radiation therapy are based on generic dose-constraints for organs-at-risk (OAR) extrapolated from those defined in the QUANTEC guidance. We have developed a web-based dashboard to determine individualized dose constraints based on summary estimates of achieved doses in prior approved plans in prostate cancer. In this study, we prospectively evaluated the feasibility and improvements achieved in doses to OARs with this approach. <h3>Materials/Methods</h3> A set of 24 cases previously planned using generic constraints to a dose of 60 Gy in 20 fractions was de-identified and replanned using individualized constraints derived from summary statistics of a subset of cases with similar target, OAR and overlap volumes from a reference library of 94 approved plans on a web-based dashboard. From the similar case subset for each study patient, the 25th and 50th percentile of achieved V59 Gy, V56 Gy, V53 Gy, V47 Gy, V40 Gy for the rectum and bladder and V57 Gy for the planning target volume (PTV) were defined as the ideal and acceptable set of individualized dose-constraints. The goal was to assess the improvement in mean doses and the specified dose volumes. Planners were blinded to the prior achieved doses and penalties. Sample size estimation was based on an estimated 3 percentage point improvement in V53 Gy for rectum and bladder with a paired evaluation using Wilcoxon sign-rank test. Python v3.7 was used for creating the dashboard and statistical comparisons. <h3>Results</h3> The differences in reference and replanned cases using individualized dose constraints are charted in table 1. There was a numerically robust and statistically significant reduction of mean doses and percentage volumes of all the discrete dose points for both bladder and rectum, including a 4% and 6.8% reduction in the primary endpoint of V53 Gy. All the plans generated had a D95 of at least 95% for the PTV. <h3>Conclusion</h3> Treatment planning based on individualized dose constraints is feasible and leads to improvement at clinically important dose volumes in prostate cancer treatment planning.

Cost-effectiveness of the implementation of [68Ga]Ga-PSMA-11 PET/CT at initial prostate cancer staging

BackgroundDespite its high specificity, PSMA PET/CT has a moderate to low sensitivity of 40–50% for pelvic lymph node detection, implicating that a negative PSMA PET/CT cannot rule out lymph node metastases. This study investigates a strategy of implementing PSMA PET/CT for initial prostate cancer staging and treatment planning compared to conventional diagnostics. In this PSMA PET/CT strategy, a bilateral extended pelvic lymph node dissection (ePLND) is only performed in case of a negative PSMA PET/CT; in case of a positive scan treatment planning is solely based on PSMA PET/CT results.MethodA decision table and lifetime state transition model were created. Quality-adjusted life years and health care costs were modelled over lifetime.ResultsThe PSMA PET/CT strategy of treatment planning based on initial staging with [68Ga]Ga-PSMA-11 PET/CT results in cost-savings of €674 and a small loss in quality of life (QoL), 0.011 QALY per patient. The positive effect of [68Ga]Ga-PSMA-11 PET/CT was caused by abandoning both an ePLND and unnecessary treatment in iM1 patients, saving costs and resulting in higher QoL. The negative effect was caused by lower QoL and high costs in the false palliative state, due to pN1lim patients (≤ 4 pelvic lymph node metastases) being falsely diagnosed as iN1ext (> 4 pelvic lymph node metastases). These patients received subsequently palliative treatment instead of potentially curative therapy.ConclusionInitial staging and treatment planning based on [68Ga]Ga-PSMA-11 PET/CT saves cost but results in small QALY loss due to the rate of false positive findings.

The Role of a DirectDensity® CT Reconstruction in a Radiotherapy Workflow: A Phantom Study

The DirectDensity® CT reconstruction algorithm provides a reconstruction approach independent of the tube voltage, directly reconstructing the CT projection data into CT numbers related to the electron densities of the materials. This work examines the efficacy of DirectDensity® in the treatment planning process with both tissues and metallic materials. CT scans of a Cheese phantom were acquired at 80, 100, 120 and 140 kVp and reconstructed with different algorithms. Calibration curves were built for each kVp and reconstruction technique. To evaluate the flexibility of the DirectDensity® in dose calculations, a prostate cancer treatment plan was simulated on phantom images with and without metal inserts. Moreover, the robustness of the algorithm was tested by simulating a possible error in the selection of the calibration curve. As expected, the calibration curves related to DirectDensity® showed a tube voltage dependence only for densities above 1.82 g/cm3. The maximum percentage differences in dose distributions comparations never exceeded the 3% of tolerance and the 3D gamma analysis always returned indices greater than 90%. The results suggest that the DD reconstruction algorithm can be employed in most clinical cases and allows for a personalized radiotherapy cancer treatment workflow, maintaining its robustness and simplicity.

DOSIMETRIC VERIFICATION OF INTENSITY MODULATED RADIOTHERAPY (IMRT) TREATMENT PLANS FOR PROSTATE CANCER PATIENTS.

Intensity modulated radiotherapy (IMRT) has become widely used as a standard radiation therapy technique for the treatment of localized prostate cancer. The transition from conformal radiotherapy (3D CRT) to a more complex IMRT technique triggered the need for more thorough verification of the accuracy in the dose delivery. In this work we present the clinical workflow and the results of patient specific quality assurance (PSQA) procedures for 40 prostate cancer patients who have been treated with step and shot IMRT ever since its implementation in our routine clinical practice. PSQA procedures include dosimetric verification of each treatment plan with dedicated rotational phantom and high-resolution matrix detector system Octavius 4D (PTW Freiburg) that allows three-dimensional comparison of the calculated and delivered radiation dose distribution. Our results proved the compliance with the universal tolerance limits recommended for those procedures (1), assuring the safety of the treatment and providing the possibility for the adoption of more stringent constraints in the future.

Evaluation of two independent dose prediction methods to personalize the automated radiotherapy planning process for prostate cancer.

Background and purposeCurrently, automatic approaches for radiotherapy planning are widely used, however creation of high quality treatment plans is still challenging. In this study, two independent dose prediction methods were used to personalize the initial settings for the automated planning template for optimizing prostate cancer treatment plans. This study evaluated the dose metrics of these plans comparing both methods with the current clinical automated prostate cancer treatment plans.Material and methodsDatasets of 20 high-risk prostate cancer treatment plans were taken from our clinical database. The prescription dose for these plans was 70 Gy given in fractions of 2.5 Gy. Plans were replanned using the current clinical automated treatment and compared with two personalized automated planning methods. The feasibility dose volume histogram (FDVH) and modified filter back projection (mFBP) methods were used to calculate independent dose predictions. Parameters for the initial objective values of the planning template were extracted from these predictions and used to personalize the optimization of the automated planning process.ResultsThe current automated replanned clinical plans and the automated plans optimized with the personalized template methods fulfilled the clinical dose criteria. For both methods a reduction in the average mean dose of the rectal wall was found, from 22.5 to 20.1 Gy for the FDVH and from 22.5 to 19.6 Gy for the mFBP method.ConclusionsWith both dose-prediction methods the initial settings of the template could be personalized. Hereby, the average dose to the rectal wall was reduced compared to the standard template method.

Prostate Cancer Risk Stratification via Nondestructive 3D Pathology with Deep Learning-Assisted Gland Analysis.

Prostate cancer treatment planning is largely dependent upon examination of core-needle biopsies. The microscopic architecture of the prostate glands forms the basis for prognostic grading by pathologists. Interpretation of these convoluted three-dimensional (3D) glandular structures via visual inspection of a limited number of two-dimensional (2D) histology sections is often unreliable, which contributes to the under- and overtreatment of patients. To improve risk assessment and treatment decisions, we have developed a workflow for nondestructive 3D pathology and computational analysis of whole prostate biopsies labeled with a rapid and inexpensive fluorescent analogue of standard hematoxylin and eosin (H&E) staining. This analysis is based on interpretable glandular features and is facilitated by the development of image translation-assisted segmentation in 3D (ITAS3D). ITAS3D is a generalizable deep learning-based strategy that enables tissue microstructures to be volumetrically segmented in an annotation-free and objective (biomarker-based) manner without requiring immunolabeling. As a preliminary demonstration of the translational value of a computational 3D versus a computational 2D pathology approach, we imaged 300 ex vivo biopsies extracted from 50 archived radical prostatectomy specimens, of which, 118 biopsies contained cancer. The 3D glandular features in cancer biopsies were superior to corresponding 2D features for risk stratification of patients with low- to intermediate-risk prostate cancer based on their clinical biochemical recurrence outcomes. The results of this study support the use of computational 3D pathology for guiding the clinical management of prostate cancer. SIGNIFICANCE: An end-to-end pipeline for deep learning-assisted computational 3D histology analysis of whole prostate biopsies shows that nondestructive 3D pathology has the potential to enable superior prognostic stratification of patients with prostate cancer.

Somatic Alterations Impact AR Transcriptional Activity and Efficacy of AR-Targeting Therapies in Prostate Cancer.

Simple SummaryFor patients whose prostate cancer spreads beyond the confines of the prostate, treatment options continue to increase. However, we are missing the information that is needed to choose for each patient the best treatment at each step of his cancer progression so we can ensure that maximal remissions and prolonged survival are achieved. In this review, we examine whether a better understanding of how the activity of the target for the default first treatment, the androgen receptor, is regulated in prostate cancer tissues can improve prostate cancer treatment plans. We consider the evidence for variability of androgen receptor activity among patients and examine the molecular basis for this variable action. We summarize clinical evidence supporting that information on a prostate cancer’s genomic composition may inform on its level of androgen receptor action, which may facilitate choice for the most effective first-line therapy and ultimately improve prostate cancer treatment plans overall.Inhibiting the activity of the ligand-activated transcription factor androgen receptor (AR) is the default first-line treatment for metastatic prostate cancer (CaP). Androgen deprivation therapy (ADT) induces remissions, however, their duration varies widely among patients. The reason for this heterogeneity is not known. A better understanding of its molecular basis may improve treatment plans and patient survival. AR’s transcriptional activity is regulated in a context-dependent manner and relies on an interplay between its associated transcriptional regulators, DNA recognition motifs, and ligands. Alterations in one or more of these factors induce shifts in the AR cistrome and transcriptional output. Significant variability in AR activity is seen in both castration-sensitive (CS) and castration-resistant CaP (CRPC). Several AR transcriptional regulators undergo somatic alterations that impact their function in clinical CaPs. Some alterations occur in a significant fraction of cases, resulting in CaP subtypes, while others affect only a few percent of CaPs. Evidence is emerging that these alterations may impact the response to CaP treatments such as ADT, radiation therapy, and chemotherapy. Here, we review the contribution of recurring somatic alterations on AR cistrome and transcriptional output and the efficacy of CaP treatments and explore strategies to use these insights to improve treatment plans and outcomes for CaP patients.

Comparison of treatment plans for hypofractionated high-dose prostate cancer radiotherapy using the Varian Halcyon and the Elekta Synergy platforms.

PurposeTo compare radiotherapy plans between an O‐ring and a conventional C‐arm linac for hypofractionated high‐dose prostate radiotherapy in terms of plan quality, dose distribution, and quality assurance in a multi‐vendor environment.MethodsTwenty prostate cancer treatment plans were irradiated on the O‐ring Varian Halcyon linac and were re‐optimized for the C‐arm Elekta Synergy Agility linac. Dose‐volume histogram metrics for target coverage and organ at risk dose, quality assurance, and monitor units were retrospectively compared. Patient‐specific quality assurance with ion chamber measurements, gamma index analysis, and portal dosimetry was performed using the Varian Portal Dosimetry system and the ArcCHECK® phantom (Sun Nuclear Corporation). Prostate‐only radiotherapy was delivered with simultaneous integrated boost (SIB) volumetric modulated arc therapy (VMAT) in 20 fractions of 2.5/3.0 Gy each.ResultsFor both linacs, target coverage was excellent and plan quality comparable. Homogeneity in PTVBoost was high for Synergy as well as Halcyon with a mean homogeneity index of 0.07 ± 0.01 and 0.05 ± 0.01, respectively. Mean dose for the organs at risk rectum and bladder differed not significantly between the linacs but were higher for the femoral heads and penile bulb for Halcyon. Quality assurance showed no significant differences in terms of ArcCHECK gamma pass rates. Median pass rate for 3%/2 mm was 99.3% (96.7 to 99.8%) for Synergy and 99.8% (95.6 to 100%) for Halcyon. Agreement between calculated and measured dose was high with a median deviation of −0.6% (−1.7 to 0.8%) for Synergy and 0.2% (−0.6 to 2.3%) for Halcyon. Monitor units were higher for the Halcyon by approximately 20% (p < 0.001).ConclusionHypofractionated high‐dose prostate cancer SIB VMAT on the Halcyon system is feasible with comparable plan quality in reference to a standard C‐arm Elekta Synergy linac.

Dosimetric comparison of MR-linac-based IMRT and conventional VMAT treatment plans for prostate cancer

BackgroundThe aim of this study was to evaluate and compare the performance of intensity modulated radiation therapy (IMRT) plans, planned for low-field strength magnetic resonance (MR) guided linear accelerator (linac) delivery (labelled IMRT MRL plans), and clinical conventional volumetric modulated arc therapy (VMAT) plans, for the treatment of prostate cancer (PCa). Both plans used the original planning target volume (PTV) margins. Additionally, the potential dosimetric benefits of MR-guidance were estimated, by creating IMRT MRL plans using smaller PTV margins.Materials and methods20 PCa patients previously treated with conventional VMAT were considered. For each patient, two different IMRT MRL plans using the low-field MR-linac treatment planning system were created: one with original (orig.) PTV margins and the other with reduced (red.) PTV margins. Dose indices related to target coverage, as well as dose-volume histogram (DVH) parameters for the target and organs at risk (OAR) were compared. Additionally, the estimated treatment delivery times and the number of monitor units (MU) of each plan were evaluated.ResultsThe dose distribution in the high dose region and the target volume DVH parameters (D98%, D50%, D2% and V95%) were similar for all three types of treatment plans, with deviations below 1% in most cases. Both IMRT MRL plans (orig. and red. PTV margins) showed similar homogeneity indices (HI), however worse values for the conformity index (CI) were also found when compared to VMAT. The IMRT MRL plans showed similar OAR sparing when the orig. PTV margins were used but a significantly better sparing was feasible when red. PTV margins were applied. Higher number of MU and longer predicted treatment delivery times were seen for both IMRT MRL plans.ConclusionsA comparable plan quality between VMAT and IMRT MRL plans was achieved, when applying the same PTV margin. However, online MR-guided adaptive radiotherapy allows for a reduction of PTV margins. With a red. PTV margin, better sparing of the surrounding tissues can be achieved, while maintaining adequate target coverage. Nonetheless, longer treatment delivery times, characteristic for the IMRT technique, have to be expected.