Dosimetric evaluation and treatment planning considerations for GammaTile permanent brain implants - a pilot, institutional experience.

PURPOSE: GammaTile® (GT) is a brachytherapy platform that received Federal Drug Administration (FDA) approval as brain tumor therapy in late 2018. Here, we reviewed our institutional experience with GT as treatment for recurrent glioblastomas and characterized dosimetric parameter and associated clinical outcome. METHODS AND MATERIALS: A total of 20 consecutive patients with 21 (n = 21) diagnosis of recurrent glioblastoma underwent resection followed by intraoperative GT implant between 01/2019 and 12/2020. Data on gross tumor volume (GTV), number of GT units implanted, dose coverage for the high-risk clinical target volume (HR-CTV), measured by D90 or dose received by 90% of the HR-CTV, dose to organs at risk, and six months local control were collected. RESULTS: The median D90 to HR-CTV was 56.0 Gy (31.7-98.7 Gy). The brainstem, optic chiasm, ipsilateral optic nerve, and ipsilateral hippocampus median Dmax were 11.2, 5.4, 6.4, and 10.0 Gy, respectively. None of the patients in this study cohort suffered from radiation necrosis or adverse events attributable to the GT. Correlation was found between pre-op GTV, the volume of the resection cavity, and the number of GT units implanted. Of the resection cavities, 7/21 (33%) of the cavity experienced shrinkage, 3/21 (14%) remained stable, and 11/21 (52%) of the cavities expanded on the 3-months post-resection/GT implant MRIs. D90 to HR-CTV was found to be associated with local recurrence at 6-month post GT implant, suggesting a dose response relationship (p = 0.026). The median local recurrence-free survival was 366.5 days (64-1,098 days), and a trend towards improved local recurrence-free survival was seen in patients with D90 to HR-CTV ≥ 56 Gy (p = 0.048). CONCLUSIONS: Our pilot, institutional experience provides clinical outcome, dosimetric considerations, and offer technical guidance in the clinical implementation of GT brachytherapy.

Target Volume Optimization for Localized Prostate Cancer.

PURPOSE: To provide a comprehensive review of the means by which to optimize target volume definition for the purposes of treatment planning for patients with intact prostate cancer with a specific emphasis on focal boost volume definition. METHODS: Here we conduct a narrative review of the available literature summarizing the current state of knowledge on optimizing target volume definition for the treatment of localized prostate cancer. RESULTS: Historically, the treatment of prostate cancer included a uniform prescription dose administered to the entire prostate with or without coverage of all or part of the seminal vesicles. The development of prostate magnetic resonance imaging (MRI) and positron emission tomography (PET) using prostate-specific radiotracers has ushered in an era in which radiation oncologists are able to localize and focally dose-escalate high-risk volumes in the prostate gland. Recent phase 3 data has demonstrated that incorporating focal dose escalation to high-risk subvolumes of the prostate improves biochemical control without significantly increasing toxicity. Still, several fundamental questions remain regarding the optimal target volume definition and prescription strategy to implement this technique. Given the remaining uncertainty, a knowledge of the pathological correlates of radiographic findings and the anatomic patterns of tumor spread may help inform clinical judgement for the definition of clinical target volumes. CONCLUSION: Advanced imaging has the ability to improve outcomes for patients with prostate cancer in multiple ways, including by enabling focal dose escalation to high-risk subvolumes. However, many questions remain regarding the optimal target volume definition and prescription strategy to implement this practice, and key knowledge gaps remain. A detailed understanding of the pathological correlates of radiographic findings and the patterns of local tumor spread may help inform clinical judgement for target volume definition given the current state of uncertainty.

Comparative Evaluation of LLMs in Clinical Oncology.

BACKGROUND: As artificial intelligence (AI) tools become widely accessible, more patients and medical professionals will turn to them for medical information. Large language models (LLMs), a subset of AI, excel in natural language processing tasks and hold considerable promise for clinical use. Fields such as oncology, in which clinical decisions are highly dependent on a continuous influx of new clinical trial data and evolving guidelines, stand to gain immensely from such advancements. It is therefore of critical importance to benchmark these models and describe their performance characteristics to guide their safe application to clinical oncology. Accordingly, the primary objectives of this work were to conduct comprehensive evaluations of LLMs in the field of oncology and to identify and characterize strategies that medical professionals can use to bolster their confidence in a model's response. METHODS: This study tested five publicly available LLMs (LLaMA 1, PaLM 2, Claude-v1, generative pretrained transformer 3.5 [GPT-3.5], and GPT-4) on a comprehensive battery of 2044 oncology questions, including topics from medical oncology, surgical oncology, radiation oncology, medical statistics, medical physics, and cancer biology. Model prompts were presented independently of each other, and each prompt was repeated three times to assess output consistency. For each response, models were instructed to provide a self-appraised confidence score (from 1 to 4). Model performance was also evaluated against a novel validation set comprising 50 oncology questions curated to eliminate any risk of overlap with the data used to train the LLMs. RESULTS: There was significant heterogeneity in performance between models (analysis of variance, P<0.001). Relative to a human benchmark (2013 and 2014 examination results), GPT-4 was the only model to perform above the 50th percentile. Overall, model performance varied as a function of subject area across all models, with worse performance observed in clinical oncology subcategories compared with foundational topics (medical statistics, medical physics, and cancer biology). Within the clinical oncology subdomain, worse performance was observed in female-predominant malignancies. A combination of model selection, prompt repetition, and confidence self-appraisal allowed for the identification of high-performing subgroups of questions with observed accuracies of 81.7 and 81.1% in the Claude-v1 and GPT-4 models, respectively. Evaluation of the novel validation question set produced similar trends in model performance while also highlighting improved performance in newer, centrally hosted models (GPT-4 Turbo and Gemini 1.0 Ultra) and local models (Mixtral 8×7B and LLaMA 2). CONCLUSIONS: Of the models tested on a standardized set of oncology questions, GPT-4 was observed to have the highest performance. Although this performance is impressive, all LLMs continue to have clinically significant error rates, including examples of overconfidence and consistent inaccuracies. Given the enthusiasm to integrate these new implementations of AI into clinical practice, continued standardized evaluations of the strengths and limitations of these products will be critical to guide both patients and medical professionals. (Funded by the National Institutes of Health Clinical Center for Research and the Intramural Research Program of the National Institutes of Health; Z99 CA999999.).

A Phase 1 Trial of Salvage Stereotactic Body Radiation Therapy for Radiorecurrent Prostate Cancer After Brachytherapy.

PURPOSE: NCT03253744 is a phase 1 trial with the primary objective to identify the maximum tolerated dose (MTD) of salvage stereotactic body radiation therapy (SBRT) in patients with local prostate cancer recurrence after brachytherapy. Additional objectives included biochemical control and imaging response. METHODS AND MATERIALS: This trial was initially designed to test 3 therapeutic dose levels (DLs): 40 Gy (DL1), 42.5 Gy (DL2), and 45 Gy (DL3) in 5 fractions. Intensity modulation was used to deliver the prescription dose to the magnetic resonance imaging and prostate-specific membrane antigen-based positron emission tomography imaging-defined gross tumor volume while simultaneously delivering 30 Gy to an elective volume defined by the prostate gland. This phase 1 trial followed a 3+3 design with a 3-patient expansion at the MTD. Toxicities were scored until trial completion at 2 years post-SBRT using Common Terminology Criteria for Adverse Events version 5.0. Escalation was halted if 2 dose limiting toxicities occurred, defined as any persistent (>4 days) grade 3 toxicity occurring within the first 3 weeks after SBRT or any grade ≥3 genitourinary (GU) or grade 4 gastrointestinal toxicity thereafter. RESULTS: Between August 2018 and January 2023, 9 patients underwent salvage SBRT and were observed for a median of 22 months (Q1-Q3, 20-43 months). No grade 3 to 5 adverse events related to study treatment were observed; thus, no dose limiting toxicities occurred during the observation period. Escalation was halted by amendment given excellent biochemical control in DL1 and DL2 in the setting of a high incidence of clinically significant late grade 2 GU toxicity. Therefore, the MTD was considered 42.5 Gy in 5 fractions (DL2). One- and 2-year biochemical progression-free survival were 100% and 86%, representing a single patient in the trial cohort with biochemical failure (prostate-specific antigen [PSA] nadir + 2.0) at 20 months posttreatment. CONCLUSIONS: The MTD of salvage SBRT for the treatment of intraprostatic radiorecurrence after brachytherapy was 42.5 Gy in 5 fractions producing an 86% 2-year biochemical progression-free survival rate, with 1 poststudy failure at 20 months. The most frequent clinically significant toxicity was late grade 2 GU toxicity.

A platform-independent AI tumor lineage and site (ATLAS) classifier.

Histopathologic diagnosis and classification of cancer plays a critical role in guiding treatment. Advances in next-generation sequencing have ushered in new complementary molecular frameworks. However, existing approaches do not independently assess both site-of-origin (e.g. prostate) and lineage (e.g. adenocarcinoma) and have minimal validation in metastatic disease, where classification is more difficult. Utilizing gradient-boosted machine learning, we developed ATLAS, a pair of separate AI Tumor Lineage and Site-of-origin models from RNA expression data on 8249 tumor samples. We assessed performance independently in 10,376 total tumor samples, including 1490 metastatic samples, achieving an accuracy of 91.4% for cancer site-of-origin and 97.1% for cancer lineage. High confidence predictions (encompassing the majority of cases) were accurate 98-99% of the time in both localized and remarkably even in metastatic samples. We also identified emergent properties of our lineage scores for tumor types on which the model was never trained (zero-shot learning). Adenocarcinoma/sarcoma lineage scores differentiated epithelioid from biphasic/sarcomatoid mesothelioma. Also, predicted lineage de-differentiation identified neuroendocrine/small cell tumors and was associated with poor outcomes across tumor types. Our platform-independent single-sample approach can be easily translated to existing RNA-seq platforms. ATLAS can complement and guide traditional histopathologic assessment in challenging situations and tumors of unknown primary.

Automated prostate gland segmentation in challenging clinical cases: comparison of three artificial intelligence methods.

OBJECTIVE: Automated methods for prostate segmentation on MRI are typically developed under ideal scanning and anatomical conditions. This study evaluates three different prostate segmentation AI algorithms in a challenging population of patients with prior treatments, variable anatomic characteristics, complex clinical history, or atypical MRI acquisition parameters. MATERIALS AND METHODS: A single institution retrospective database was queried for the following conditions at prostate MRI: prior prostate-specific oncologic treatment, transurethral resection of the prostate (TURP), abdominal perineal resection (APR), hip prosthesis (HP), diversity of prostate volumes (large ≥ 150 cc, small ≤ 25 cc), whole gland tumor burden, magnet strength, noted poor quality, and various scanners (outside/vendors). Final inclusion criteria required availability of axial T2-weighted (T2W) sequence and corresponding prostate organ segmentation from an expert radiologist. Three previously developed algorithms were evaluated: (1) deep learning (DL)-based model, (2) commercially available shape-based model, and (3) federated DL-based model. Dice Similarity Coefficient (DSC) was calculated compared to expert. DSC by model and scan factors were evaluated with Wilcox signed-rank test and linear mixed effects (LMER) model. RESULTS: 683 scans (651 patients) met inclusion criteria (mean prostate volume 60.1 cc [9.05-329 cc]). Overall DSC scores for models 1, 2, and 3 were 0.916 (0.707-0.971), 0.873 (0-0.997), and 0.894 (0.025-0.961), respectively, with DL-based models demonstrating significantly higher performance (p < 0.01). In sub-group analysis by factors, Model 1 outperformed Model 2 (all p < 0.05) and Model 3 (all p < 0.001). Performance of all models was negatively impacted by prostate volume and poor signal quality (p < 0.01). Shape-based factors influenced DL models (p < 0.001) while signal factors influenced all (p < 0.001). CONCLUSION: Factors affecting anatomical and signal conditions of the prostate gland can adversely impact both DL and non-deep learning-based segmentation models.