Auto-delineation of treatment target volume for radiation therapy using large language model-aided multimodal learning.

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.

Automated radiotherapy treatment planning guided by GPT-4Vision.

Radiotherapy treatment planning is a time-consuming and potentially subjective process that requires the iterative adjustment of model parameters to balance multiple conflicting objectives. Recent advancements in large foundation models offer promising avenues for addressing the challenges in planning and clinical decision-making. This study introduces GPT-RadPlan, a fully automated treatment planning framework that harnesses prior radiation oncology knowledge encoded in multi-modal large language models, such as GPT-4Vision (GPT-4V) from OpenAI. GPT-RadPlan is made aware of planning protocols as context and acts as an expert human planner, capable of guiding a treatment planning process. Via in-context learning, we incorporate clinical protocols for various disease sites as prompts to enable GPT-4V to acquire treatment planning domain knowledge. The resulting GPT-RadPlan agent is integrated into our in-house inverse treatment planning system through an API. The efficacy of the automated planning system is showcased using multiple prostate and head & neck cancer cases, where we compared GPT-RadPlan results to clinical plans. In all cases, GPT-RadPlan either outperformed or matched the clinical plans, demonstrating superior target coverage and organ-at-risk sparing. Consistently satisfying the dosimetric objectives in the clinical protocol, GPT-RadPlan represents the first multimodal large language model agent that mimics the behaviors of human planners in radiation oncology clinics, achieving remarkable results in automating the treatment planning process without the need for additional training.

NCCN Guidelines® Insights: Bladder Cancer, Version 3.2024.

Bladder cancer, the sixth most common cancer in the United States, is most commonly of the urothelial carcinoma histologic subtype. The clinical spectrum of bladder cancer is divided into 3 categories that differ in prognosis, management, and therapeutic aims: (1) non-muscle-invasive bladder cancer (NMIBC); (2) muscle invasive, nonmetastatic disease; and (3) metastatic bladder cancer. These NCCN Guidelines Insights detail recent updates to the NCCN Guidelines for Bladder Cancer, including changes in the fifth edition of the WHO Classification of Tumours: Urinary and Male Genital Tumours and how the NCCN Guidelines aligned with these updates; new and emerging treatment options for bacillus Calmette-Guérin (BCG)-unresponsive NMIBC; and updates to systemic therapy recommendations for advanced or metastatic disease.

Noninferiority of Hypofractionated vs Conventional Postprostatectomy Radiotherapy for Genitourinary and Gastrointestinal Symptoms: The NRG-GU003 Phase 3 Randomized Clinical Trial.

Importance: No prior trial has compared hypofractionated postprostatectomy radiotherapy (HYPORT) to conventionally fractionated postprostatectomy (COPORT) in patients primarily treated with prostatectomy. Objective: To determine if HYPORT is noninferior to COPORT for patient-reported genitourinary (GU) and gastrointestinal (GI) symptoms at 2 years. Design, Setting, and Participants: In this phase 3 randomized clinical trial, patients with a detectable prostate-specific antigen (PSA; ≥0.1 ng/mL) postprostatectomy with pT2/3pNX/0 disease or an undetectable PSA (<0.1 ng/mL) with either pT3 disease or pT2 disease with a positive surgical margin were recruited from 93 academic, community-based, and tertiary medical sites in the US and Canada. Between June 2017 and July 2018, a total of 296 patients were randomized. Data were analyzed in December 2020, with additional analyses occurring after as needed. Intervention: Patients were randomized to receive 62.5 Gy in 25 fractions (HYPORT) or 66.6 Gy in 37 fractions (COPORT). Main Outcomes and Measures: The coprimary end points were the 2-year change in score from baseline for the bowel and urinary domains of the Expanded Prostate Cancer Composite Index questionnaire. Secondary objectives were to compare between arms freedom from biochemical failure, time to progression, local failure, regional failure, salvage therapy, distant metastasis, prostate cancer-specific survival, overall survival, and adverse events. Results: Of the 296 patients randomized (median [range] age, 65 [44-81] years; 100% male), 144 received HYPORT and 152 received COPORT. At the end of RT, the mean GU change scores among those in the HYPORT and COPORT arms were neither clinically significant nor different in statistical significance and remained so at 6 and 12 months. The mean (SD) GI change scores for HYPORT and COPORT were both clinically significant and different in statistical significance at the end of RT (-15.52 [18.43] and -7.06 [12.78], respectively; P < .001). However, the clinically and statistically significant differences in HYPORT and COPORT mean GI change scores were resolved at 6 and 12 months. The 24-month differences in mean GU and GI change scores for HYPORT were noninferior to COPORT using noninferiority margins of -5 and -6, respectively, rejecting the null hypothesis of inferiority (mean [SD] GU score: HYPORT, -5.01 [15.10] and COPORT, -4.07 [14.67]; P = .005; mean [SD] GI score: HYPORT, -4.17 [10.97] and COPORT, -1.41 [8.32]; P = .02). With a median follow-up for censored patients of 2.1 years, there was no difference between HYPORT vs COPORT for biochemical failure, defined as a PSA of 0.4 ng/mL or higher and rising (2-year rate, 12% vs 8%; P = .28). Conclusions and Relevance: In this randomized clinical trial, HYPORT was associated with greater patient-reported GI toxic effects compared with COPORT at the completion of RT, but both groups recovered to baseline levels within 6 months. At 2 years, HYPORT was noninferior to COPORT in terms of patient-reported GU or GI toxic effects. HYPORT is a new acceptable practice standard for patients receiving postprostatectomy radiotherapy. Trial Registration: ClinicalTrials.gov Identifier: NCT03274687.

Salvage Therapy for Prostate Cancer: AUA/ASTRO/SUO Guideline Part III: Salvage Therapy After Radiotherapy or Focal Therapy, Pelvic Nodal Recurrence and Oligometastasis, and Future Directions.

PURPOSE: The summary presented herein covers recommendations on salvage therapy for recurrent prostate cancer intended to facilitate care decisions and aid clinicians in caring for patients who have experienced a recurrence following prior treatment with curative intent. This is Part III of a three-part series focusing on evaluation and management of suspected non-metastatic recurrence after radiotherapy (RT) and focal therapy, evaluation and management of regional recurrence, management for molecular imaging metastatic recurrence, and future directions. Please refer to Part I for discussion of treatment decision-making and Part II for discussion of treatment delivery for non-metastatic biochemical recurrence (BCR) after radical prostatectomy (RP). MATERIALS AND METHODS: The systematic review that informs this Guideline was based on searches in Ovid MEDLINE (1946 to July 21, 2022), Cochrane Central Register of Controlled Trials (through August 2022), and Cochrane Database of Systematic Reviews (through August 2022). Update searches were conducted on July 26, 2023. Searches were supplemented by reviewing electronic database reference lists of relevant articles. RESULTS: In a collaborative effort between AUA, ASTRO, and SUO, the Salvage Therapy for Prostate Cancer Guideline Panel developed evidence- and consensus-based guideline statements to provide guidance for the care of patients who experience BCR after initial definitive local therapy for clinically localized disease. CONCLUSIONS: Continuous and deliberate efforts for multidisciplinary care in prostate cancer will be required to optimize and improve the oncologic and functional outcomes of patients treated with salvage therapies in the future.

Salvage Therapy for Prostate Cancer: AUA/ASTRO/SUO Guideline Part I: Introduction and Treatment Decision-Making at the Time of Suspected Biochemical Recurrence after Radical Prostatectomy.

PURPOSE: The summary presented herein covers recommendations on salvage therapy for recurrent prostate cancer intended to facilitate care decisions and aid clinicians in caring for patients who have experienced a recurrence following prior treatment with curative intent. This is Part I of a three-part series focusing on treatment decision-making at the time of suspected biochemical recurrence (BCR) after radical prostatectomy (RP). Please refer to Part II for discussion of treatment delivery for non-metastatic BCR after RP and Part III for discussion of evaluation and management of recurrence after radiotherapy (RT) and focal therapy, regional recurrence, and oligometastasis. MATERIALS AND METHODS: The systematic review that informs this Guideline was based on searches in Ovid MEDLINE (1946 to July 21, 2022), Cochrane Central Register of Controlled Trials (through August 2022), and Cochrane Database of Systematic Reviews (through August 2022). Update searches were conducted on July 26, 2023. Searches were supplemented by reviewing electronic database reference lists of relevant articles. RESULTS: In a collaborative effort between AUA, ASTRO, and SUO, the Salvage Therapy for Prostate Cancer Panel developed evidence- and consensus-based statements to provide guidance for the care of patients who experience BCR after initial definitive local therapy for clinically localized disease. CONCLUSIONS: Advancing work in the area of diagnostic tools (particularly imaging), biomarkers, radiation delivery, and biological manipulation with the evolving armamentarium of therapeutic agents will undoubtedly present new opportunities for patients to experience long-term control of their cancer while minimizing toxicity.

Salvage Therapy for Prostate Cancer: AUA/ASTRO/SUO Guideline Part II: Treatment Delivery for Non-metastatic Biochemical Recurrence After Primary Radical Prostatectomy.

PURPOSE: The summary presented herein covers recommendations on salvage therapy for recurrent prostate cancer intended to facilitate care decisions and aid clinicians in caring for patients who have experienced a recurrence following prior treatment with curative intent. This is Part II of a three-part series focusing on treatment delivery for non-metastatic biochemical recurrence (BCR) after primary radical prostatectomy (RP). Please refer to Part I for discussion of treatment decision-making and Part III for discussion of evaluation and management of recurrence after radiotherapy (RT) and focal therapy, regional recurrence, and oligometastasis. MATERIALS AND METHODS: The systematic review that informs this Guideline was based on searches in Ovid MEDLINE (1946 to July 21, 2022), Cochrane Central Register of Controlled Trials (through August 2022), and Cochrane Database of Systematic Reviews (through August 2022). Update searches were conducted on July 26, 2023. Searches were supplemented by reviewing electronic database reference lists of relevant articles. RESULTS: In a collaborative effort between AUA, ASTRO, and SUO, the Salvage Therapy for Prostate Cancer Panel developed evidence- and consensus-based guideline statements to provide guidance for the care of patients who experience BCR after initial definitive local therapy for clinically localized disease. CONCLUSIONS: Optimizing and personalizing the approach to salvage therapy remains an ongoing area of work in the field of genitourinary oncology and represents an area of research and clinical care that requires well-coordinated, multi-disciplinary efforts.

Salvage prostate brachytherapy in radiorecurrent prostate cancer: An international Delphi consensus study.

BACKGROUND AND PURPOSE: Local recurrences after previous radiotherapy (RT) are increasingly being identified in biochemically recurrent prostate cancer. Salvage prostate brachytherapy (BT) is an effective and well tolerated treatment option. We sought to generate international consensus statements on the use and preferred technical considerations for salvage prostate BT. MATERIALS AND METHODS: International experts in salvage prostate BT were invited (n = 34) to participate. A three-round modified Delphi technique was utilized, with questions focused on patient- and cancer-specific criteria, type and technique of BT, and follow-up. An a priori threshold for consensus of ≥ 75% was set, with a majority opinion being ≥ 50%. RESULTS: Thirty international experts agreed to participate. Consensus was achieved for 56% (18/32) of statements. Consensus was achieved in several areas of patient selection: 1) A minimum of 2-3 years from initial RT to salvage BT; 2) MRI and PSMA PET should be obtained; and 3) Both targeted and systematic biopsies should be performed. Several areas did not reach consensus: 1) Maximum T stage/PSA at time of salvage; 2) Utilization/duration of ADT; 3) Appropriateness of combining local salvage with SABR for oligometastatic disease and 4) Repeating a second course of salvage BT. A majority opinion preferred High Dose-Rate salvage BT, and indicated that both focal and whole gland techniques could be appropriate. There was no single preferred dose/fractionation. CONCLUSION: Areas of consensus within our Delphi study may serve as practical advice for salvage prostate BT. Future research in salvage BT should address areas of controversy identified in our study.

Long-Term Results of a Phase 3 Randomized Prospective Trial of Erectile Tissue-Sparing Intensity-Modulated Radiation Therapy for Men With Clinically Localized Prostate Cancer.

PURPOSE: The objective of this study was to determine whether limiting the doses delivered to the penile bulb (PB) and corporal bodies with intensity modulated radiation therapy (IMRT) preserves erectile function compared with standard IMRT in men with prostate cancer. METHODS AND MATERIALS: A total of 117 patients with low- to intermediate-risk, clinical T1a-T2c prostate adenocarcinoma were enrolled in a single-institution, prospective, single-blind, phase 3 randomized trial. All received definitive IMRT to 74 to 80 Gy in 37 to 40 fractions and standard IMRT (s-IMRT) or erectile tissue-sparing IMRT (ETS-IMRT), which placed additional planning constraints that limited the D90 to the penile bulb and corporal bodies to ≤15 Gy and ≤7 Gy, respectively. Erectile potency was assessed with components of the International Index of Erectile Function and phosphodiesterase type 5 inhibitor (PDE5) medication records. RESULTS: Sixty-two patients received ETS-IMRT, and 54 received s-IMRT; 1 patient did not receive radiation therapy. Before treatment, all patients reported erectile potency. No patients received androgen deprivation therapy. In the intention-to-treat analysis, treatment arms did not differ in potency preservation at 24 months (37.1% ETS-IMRT vs 31.5% s-IMRT, P = .53). Of 85 evaluable patients with International Index of Erectile Function and PDE5 medication follow-up, erectile potency was seen in 47.9% of patients in the ETS-IMRT arm and 46.0% of patients in the s-IMRT arm (P = .86). PDE5 inhibitors were initiated in 41.7% of ETS-IMRT patients and 35.1% of s-IMRT patients (P = .54). Among all patients enrolled, there was no difference in freedom from biochemical failure between those treated with ETS-IMRT and s-IMRT (5-year 91.8% vs 90.7%, respectively, P = .77), with a median follow-up of 7.4 years. There were no differences in acute or late gastrointestinal or genitourinary toxicity. An unplanned per-protocol analysis demonstrated no differences in potency preservation or secondary endpoints between patients who exceeded erectile tissue-sparing constraints and those who met constraints, although power was limited by attrition and unplanned dosimetric crossover. CONCLUSIONS: ETS-IMRT that strictly limits dose to the penile bulb and corporal bodies is safe and feasible. Use of this planning technique did not show an effect on potency preservation outcomes at 2 years, though power to detect a difference was limited.

NCCN Guidelines® Insights: Bladder Cancer, Version 2.2022.

The NCCN Guidelines for Bladder Cancer provide recommendations for the diagnosis, evaluation, treatment, and follow-up of patients with bladder cancer and other urinary tract cancers (upper tract tumors, urothelial carcinoma of the prostate, primary carcinoma of the urethra). These NCCN Guidelines Insights summarize the panel discussion behind recent important updates to the guidelines regarding the treatment of non-muscle-invasive bladder cancer, including how to treat in the event of a bacillus Calmette-Guérin (BCG) shortage; new roles for immune checkpoint inhibitors in non-muscle invasive, muscle-invasive, and metastatic bladder cancer; and the addition of antibody-drug conjugates for metastatic bladder cancer.

Syndrome of inappropriate secretion of antidiuretic hormone following high dose rate brachytherapy for prostate cancer: a case report.

BACKGROUND: The syndrome of inappropriate secretion of antidiuretic hormone is a disorder characterized by the excess release of antidiuretic hormone and can result in hyponatremia. If managed inappropriately, severe hyponatremia can cause seizures, cerebral edema, and even death. There are various known causes of this inappropriate release of antidiuretic hormone, including malignancy, CNS disorders, and disturbances in the hypothalamic-pituitary-renal axis. However, reports of syndrome of inappropriate secretion of antidiuretic hormone after brachytherapy for prostate cancer are exceedingly rare. CASE PRESENTATION: We report a case of symptomatic hyponatremia secondary to the inappropriate secretion of antidiuretic hormone after prostate high-dose rate brachytherapy under general anesthesia in a patient with adenocarcinoma of the prostate. CONCLUSIONS: In rare instances, inappropriate secretion of antidiuretic hormone can occur after high-dose rate brachytherapy for prostate cancer. The cause is likely multifactorial, involving pain or discomfort ensuing from the surgical procedure, the general anesthesia or intraoperative drugs administered. However, due to the potential severity of the side effects, timely diagnosis is crucial to ensure prompt, and effective management.

Refining the definition of biochemical failure in the era of stereotactic body radiation therapy for prostate cancer: The Phoenix definition and beyond.

BACKGROUND AND PURPOSE: The Phoenix definition for biochemical failure (BCF) after radiotherapy uses nadir PSA (nPSA) + 2 ng/mL to classify a BCF and was derived from conventionally fractionated radiotherapy, which produces significantly higher nPSAs than stereotactic body radiotherapy (SBRT). We investigated whether an alternative nPSA-based threshold could be used to define post-SBRT BCFs. MATERIALS AND METHODS: PSA kinetics data on 2038 patients from 9 institutions were retrospectively analyzed for low- and intermediate-risk PCa patients treated with SBRT without ADT. We evaluated the performance of various nPSA-based definitions. We also investigated the relationship of relative PSA decline (rPSA, PSA18month/PSA6month) and timing of reaching nPSA + 2 with BCF. RESULTS: Median follow-up was 71.9 months. BCF occurred in 6.9% of patients. Median nPSA was 0.16 ng/mL. False positivity of nPSA + 2 was 30.2%, compared to 40.9%, 57.8%, and 71.0% for nPSA + 1.5, nPSA + 1.0, and nPSA + 0.5, respectively. Among patients with BCF, the median lead time gained from an earlier nPSA + threshold definition over the Phoenix definition was minimal. Patients with BCF had significantly lower rates of early PSA decline (mean rPSA 1.19 vs. 0.39, p < 0.0001) and were significantly more likely to reach nPSA + 2 ≥ 18 months (83.3% vs. 21.1%, p < 0.0001). The proposed criterion (rPSA ≥ 2.6 or nPSA + 2 ≥ 18 months) had a sensitivity and specificity of 92.4% and 81.5%, respectively, for predicting BCF in patients meeting the Phoenix definition and decreased its false positivity to 6.4%. CONCLUSION: The Phoenix definition remains an excellent definition for BCF post-SBRT. Its high false positivity can be mitigated by applying additional criteria (rPSA ≥ 2.6 or time to nPSA + 2 ≥ 18 months).

Toxicity After Stereotactic Body Radiation Therapy for Prostate Cancer in Patients With Inflammatory Bowel Disease: A Multi-institutional Matched Case-Control Series.

PURPOSE: To evaluate the safety of stereotactic body radiation therapy (SBRT) for prostate cancer in men with inflammatory bowel disease (IBD). METHODS AND MATERIALS: We queried a consortium database for patients with IBD receiving SBRT for prostate cancer between 2006 and 2012. Identified patients were matched with patients without a history of IBD in a 3:1 fashion based on dose, fractionation, use of androgen deprivation therapy, and age distribution. Logistic regression was used to evaluate the association between having IBD and experiencing acute and late gastrointestinal (GI) and genitourinary (GU) toxicities as scored on the Common Terminology Criteria for Adverse Events scale. Time to late toxicity was evaluated using proportional hazard Cox models. Our study was limited by absence of data on prostate size, baseline International Prostate Symptom Score, and rectal dose-volume histogram parameters. RESULTS: Thirty-nine patients with flare-free IBD at time of treatment (median follow-up 83.9 months) and 117 matched controls (median follow-up 88.7 months) were identified. A diagnosis of IBD was associated with increased odds of developing any late grade GI toxicity (odds ratio [OR] 6.11, P <.001) and GU toxicity (odds ratio 6.14, P < .001), but not odds of developing late grade ≥2 GI (P = .08) or GU toxicity (P = .069). Acute GI and GU toxicity, both overall and for grade ≥2 toxicities, were more frequent in men with IBD (P < .05). Time to late GI and GU toxicity of any grade was significantly shorter in patients with IBD (P < .001). Time to late grade ≥2 GU, but not grade ≥2 GI toxicity, was also shorter in patients with IBD (P = .044 for GU and P = .144 for GI). CONCLUSIONS: Patients with IBD who received SBRT for PCa had a higher likelihood of developing acute GI and GU toxicity, in addition to experiencing lower grade late toxicities that occurred earlier. However, patients with IBD did not have a higher likelihood for late grade ≥2 GI or GU toxicity after SBRT compared with the control cohort. Interpretation of this data are limited by the small sample size. Thus, men with IBD in remission should be properly counseled about these risks when considering SBRT.

Development and Validation of an Interpretable Artificial Intelligence Model to Predict 10-Year Prostate Cancer Mortality.

Prostate cancer treatment strategies are guided by risk-stratification. This stratification can be difficult in some patients with known comorbidities. New models are needed to guide strategies and determine which patients are at risk of prostate cancer mortality. This article presents a gradient-boosting model to predict the risk of prostate cancer mortality within 10 years after a cancer diagnosis, and to provide an interpretable prediction. This work uses prospective data from the PLCO Cancer Screening and selected patients who were diagnosed with prostate cancer. During follow-up, 8776 patients were diagnosed with prostate cancer. The dataset was randomly split into a training (n = 7021) and testing (n = 1755) dataset. Accuracy was 0.98 (±0.01), and the area under the receiver operating characteristic was 0.80 (±0.04). This model can be used to support informed decision-making in prostate cancer treatment. AI interpretability provides a novel understanding of the predictions to the users.

MR to ultrasound image registration with segmentation-based learning for HDR prostate brachytherapy.

PURPOSE: Propagation of contours from high-quality magnetic resonance (MR) images to treatment planning ultrasound (US) images with severe needle artifacts is a challenging task, which can greatly aid the organ contouring in high dose rate (HDR) prostate brachytherapy. In this study, a deep learning approach was developed to automatize this registration procedure for HDR brachytherapy practice. METHODS: Because of the lack of training labels and difficulty of accurate registration from inferior image quality, a new segmentation-based registration framework was proposed for this multi-modality image registration problem. The framework consisted of two segmentation networks and a deformable registration network, based on the weakly -supervised registration strategy. Specifically, two 3D V-Nets were trained for the prostate segmentation on the MR and US images separately, to generate the weak supervision labels for the registration network training. Besides the image pair, the corresponding prostate probability maps from the segmentation were further fed to the registration network to predict the deformation matrix, and an augmentation method was designed to randomly scale the input and label probability maps during the registration network training. The overlap between the deformed and fixed prostate contours was analyzed to evaluate the registration accuracy. Three datasets were collected from our institution for the MR and US image segmentation networks, and the registration network learning, which contained 121, 104, and 63 patient cases, respectively. RESULTS: The mean Dice similarity coefficient (DSC) results of the two prostate segmentation networks are 0.86 ± 0.05 and 0.90 ± 0.03, for MR images and the US images after the needle insertion, respectively. The mean DSC, center-of-mass (COM) distance, Hausdorff distance (HD), and averaged symmetric surface distance (ASSD) results for the registration of manual prostate contours were 0.87 ± 0.05, 1.70 ± 0.89 mm, 7.21 ± 2.07 mm, 1.61 ± 0.64 mm, respectively. By providing the prostate probability map from the segmentation to the registration network, as well as applying the random map augmentation method, the evaluation results of the four metrics were all improved, such as an increase in DSC from 0.83 ± 0.08 to 0.86 ± 0.06 and from 0.86 ± 0.06 to 0.87 ± 0.05, respectively. CONCLUSIONS: A novel segmentation-based registration framework was proposed to automatically register prostate MR images to the treatment planning US images with metal artifacts, which not only largely saved the labor work on the data preparation, but also improved the registration accuracy. The evaluation results showed the potential of this approach in HDR prostate brachytherapy practice.

PSMA- and GRPR-Targeted PET: Results from 50 Patients with Biochemically Recurrent Prostate Cancer.

Novel radiopharmaceuticals for PET are being evaluated for the diagnosis of biochemical recurrence (BCR) of prostate cancer (PC). We compared the gastrin-releasing peptide receptor-targeting 68Ga-RM2 with the prostate-specific membrane antigen (PSMA)-targeting 68Ga-PSMA11 and 18F-DCFPyL. Methods: Fifty patients underwent both 68Ga-RM2 PET/MRI and 68Ga-PSMA11 (n = 23) or 18F-DCFPyL (n = 27) PET/CT at an interval ranging from 1 to 60 d (mean ± SD, 15.8 ± 17.7 d). SUVmax was collected for all lesions. Results:68Ga-RM2 PET was positive in 35 and negative in 15 of the 50 patients. 68Ga-PSMA11/18F-DCFPyL PET was positive in 37 and negative in 13 of the 50 patients. Both scans detected 70 lesions in 32 patients. Forty-three lesions in 18 patients were identified on only 1 scan: 68Ga-RM2 detected 7 more lesions in 4 patients, whereas 68Ga-PSMA11/18F-DCFPyL detected 36 more lesions in 13 patients. Conclusion:68Ga-RM2 remains a valuable radiopharmaceutical even when compared with the more widely used 68Ga-PSMA11/18F-DCFPyL in the evaluation of BCR of PC. Larger studies are needed to verify that identifying patients for whom these 2 classes of radiopharmaceuticals are complementary may ultimately allow for personalized medicine.

Automated contour propagation of the prostate from pCT to CBCT images via deep unsupervised learning.

PURPOSE: To develop and evaluate a deep unsupervised learning (DUL) framework based on a regional deformable model for automated prostate contour propagation from planning computed tomography (pCT) to cone-beam CT (CBCT). METHODS: We introduce a DUL model to map the prostate contour from pCT to on-treatment CBCT. The DUL framework used a regional deformable model via narrow-band mapping to augment the conventional strategy. Two hundred and fifty-one anonymized CBCT images from prostate cancer patients were retrospectively selected and divided into three sets: 180 were used for training, 12 for validation, and 59 for testing. The testing dataset was divided into two groups. Group 1 contained 50 CBCT volumes, with one physician-generated prostate contour on CBCT image. Group 2 contained nine CBCT images, each including prostate contours delineated by four independent physicians and a consensus contour generated using the STAPLE method. Results were compared between the proposed DUL and physician-generated contours through the Dice similarity coefficients (DSCs), the Hausdorff distances, and the distances of the center-of-mass. RESULTS: The average DSCs between DUL-based prostate contours and reference contours for test data in group 1 and group 2 consensus were 0.83 ± 0.04, and 0.85 ± 0.04, respectively. Correspondingly, the mean center-of-mass distances were 3.52 mm ± 1.15 mm, and 2.98 mm ± 1.42 mm, respectively. CONCLUSIONS: This novel DUL technique can automatically propagate the contour of the prostate from pCT to CBCT. The proposed method shows that highly accurate contour propagation for CBCT-guided adaptive radiotherapy is achievable via the deep learning technique.

A personalized decision aid for prostate cancer shared decision making.

BACKGROUND: A shared decision-making model is preferred for engaging prostate cancer patients in treatment decisions. However, the process of assessing an individual's preferences and values is challenging and not formalized. The purpose of this study is to develop an automated decision aid for patient-centric treatment decision-making using decision analysis, preference thresholds and value elicitations to maximize the compatibility between a patient's treatment expectations and outcome. METHODS: A template for patient-centric medical decision-making was constructed. The inputs included prostate cancer risk group, pre-treatment health state, treatment alternatives (primarily focused on radiation in this model), side effects (erectile dysfunction, urinary incontinence, nocturia and bowel incontinence), and treatment success (5-year freedom from biochemical failure). A linear additive value function was used to combine the values for each attribute (side effects, success and the alternatives) into a value for all prospects. The patient-reported toxicity probabilities were derived from phase II and III trials. The probabilities are conditioned on the starting state for each of the side effects. Toxicity matrices for erectile dysfunction, urinary incontinence, nocturia and bowel incontinence were created for the treatment alternatives. Toxicity probability thresholds were obtained by identifying the patient's maximum acceptable threshold for each of the side effects. Results are represented as a visual. R and Rstudio were used to perform analyses, and R Shiny for application creation. RESULTS: We developed a web-based decision aid. Based on preliminary use of the application, every treatment alternative could be the best choice for a decision maker with a particular set of preferences. This result implies that no treatment has determinist dominance over the remaining treatments and that a preference-based approach can help patients through their decision-making process, potentially affecting compliance with treatment, tolerance of side effects and satisfaction with the decision. CONCLUSIONS: We present a unique patient-centric prostate cancer treatment decision aid that systematically assesses and incorporates a patient's preferences and values to rank treatment options by likelihood of achieving the preferred outcome. This application enables the practice and study of personalized medicine. This model can be expanded to include additional inputs, such as genomics, as well as competing, concurrent or sequential therapies.

NRG Oncology Updated International Consensus Atlas on Pelvic Lymph Node Volumes for Intact and Postoperative Prostate Cancer.

PURPOSE: In 2009, the Radiation Therapy Oncology Group (RTOG) genitourinary members published a consensus atlas for contouring prostate pelvic nodal clinical target volumes (CTVs). Data have emerged further informing nodal recurrence patterns. The objective of this study is to provide an updated prostate pelvic nodal consensus atlas. METHODS AND MATERIALS: A literature review was performed abstracting data on nodal recurrence patterns. Data were presented to a panel of international experts, including radiation oncologists, radiologists, and urologists. After data review, participants contoured nodal CTVs on 3 cases: postoperative, intact node positive, and intact node negative. Radiation oncologist contours were analyzed qualitatively using count maps, which provided a visual assessment of controversial regions, and quantitatively analyzed using Sorensen-Dice similarity coefficients and Hausdorff distances compared with the 2009 RTOG atlas. Diagnostic radiologists generated a reference table outlining considerations for determining clinical node positivity. RESULTS: Eighteen radiation oncologists' contours (54 CTVs) were included. Two urologists' volumes were examined in a separate analysis. The mean CTV for the postoperative case was 302 cm3, intact node positive case was 409 cm3, and intact node negative case was 342 cm3. Compared with the original RTOG consensus, the mean Sorensen-Dice similarity coefficient for the postoperative case was 0.63 (standard deviation [SD] 0.13), the intact node positive case was 0.68 (SD 0.13), and the intact node negative case was 0.66 (SD 0.18). The mean Hausdorff distance (in cm) for the postoperative case was 0.24 (SD 0.13), the intact node positive case was 0.23 (SD 0.09), and intact node negative case was 0.33 (SD 0.24). Four regions of CTV controversy were identified, and consensus for each of these areas was reached. CONCLUSIONS: Discordance with the 2009 RTOG consensus atlas was seen in a group of experienced NRG Oncology and international genitourinary radiation oncologists. To address areas of variability and account for new data, an updated NRG Oncology consensus contour atlas was developed.

Dose-response with stereotactic body radiotherapy for prostate cancer: A multi-institutional analysis of prostate-specific antigen kinetics and biochemical control.

BACKGROUND AND PURPOSE: The optimal dose for prostate stereotactic body radiotherapy (SBRT) is still unknown. This study evaluated the dose-response relationships for prostate-specific antigen (PSA) decay and biochemical recurrence (BCR) among 4 SBRT dose regimens. MATERIALS AND METHODS: In 1908 men with low-risk (50.0%), favorable intermediate-risk (30.9%), and unfavorable intermediate-risk (19.1%) prostate cancer treated with prostate SBRT across 8 institutions from 2003 to 2018, we examined 4 regimens (35 Gy/5 fractions [35/5, n = 265, 13.4%], 36.25 Gy/5 fractions [36.25/5, n = 711, 37.3%], 40 Gy/5 fractions [40/5, n = 684, 35.8%], and 38 Gy/4 fractions [38/4, n = 257, 13.5%]). Between dose groups, we compared PSA decay slope, nadir PSA (nPSA), achievement of nPSA ≤0.2 and ≤0.5 ng/mL, and BCR-free survival (BCRFS). RESULTS: Median follow-up was 72.3 months. Median nPSA was 0.01 ng/mL for 38/4, and 0.17-0.20 ng/mL for 5-fraction regimens (p < 0.0001). The 38/4 cohort demonstrated the steepest PSA decay slope and greater odds of nPSA ≤0.2 ng/mL (both p < 0.0001 vs. all other regimens). BCR occurred in 6.25%, 6.75%, 3.95%, and 8.95% of men treated with 35/5, 36.25/5, 40/5, and 38/4, respectively (p = 0.12), with the highest BCRFS after 40/5 (vs. 35/5 hazard ratio [HR] 0.49, p = 0.026; vs. 36.25/5 HR 0.42, p = 0.0005; vs. 38/4 HR 0.55, p = 0.037) including the entirety of follow-up, but not for 5-year BCRFS (≥93% for all regimens, p ≥ 0.21). CONCLUSION: Dose-escalation was associated with greater prostate ablation and PSA decay. Dose-escalation to 40/5, but not beyond, was associated with improved BCRFS. Biochemical control remains excellent, and prospective studies will provide clarity on the benefit of dose-escalation.