Quantitative [68Ga]Ga-PSMA-11 PET biomarkers for the analysis of lesion-level progression in biochemically recurrent prostate cancer: a multicentre study.

[68Ga]Ga-PSMA-11 PET has become the standard imaging modality for biochemically recurrent (BCR) prostate cancer (PCa). However, its prognostic value in assessing response at this stage remains uncertain. The study aimed to assess the prognostic significance of radiographic patient-level patterns of progression derived from lesion-level biomarker quantitation in metastatic disease sites. A total of 138 BCR PCa patients with both baseline and follow-up [68Ga]Ga-PSMA-11 PET scans were included in this analysis. Tumour response was quantified at the lesion level using commonly used quantitative parameters (SUVmean, SUVmax, SUVpeak, volume), and patients were classified as systemic, mixed, or no-progression based on these response classifications. A total of 328 matched lesions between baseline and follow-up scans were analysed. The results showed that systemic progressors had a significantly higher risk of death than patients with no progression with SUVmean demonstrating the highest prognostic value (HR = 5.70, 95% CI = 2.63-12.37, p < 0.001, C-Index = 0.69). Moreover, progressive disease as measured by SUVmean using the radiographic PSMA PET Progression Criteria (rPPP) was found to be significantly prognostic for patient overall survival (HR = 3.67, 95% CI = 1.82-7.39, p < 0.001, C-Index = 0.65). This work provides important evidence supporting the prognostic utility of PSMA response quantitation in the BCR setting.

Prospective inter- and intra-tracer repeatability analysis of radiomics features in [68Ga]Ga-PSMA-11 and [18F]F-PSMA-1007 PET scans in metastatic prostate cancer.

OBJECTIVE: This study aimed to quantify both the intra- and intertracer repeatability of lesion-level radiomics features in [68Ga]Ga-prostate-specific membrane antigen (PSMA)-11 and [18F]F-PSMA-1007 positron emission tomography (PET) scans. METHODS: Eighteen patients with metastatic prostate cancer (mPCa) were prospectively recruited for the study and randomised to one of three test-retest groups: (i) intratracer [68Ga]Ga-PSMA-11 PET, (ii) intratracer [18F]F-PSMA-1007 PET or (iii) intertracer between [68Ga]Ga-PSMA-11 and [18F]F-PSMA-1007 PET. Four conventional PET metrics (standardised uptake value (SUV)max, SUVmean, SUVtotal and volume) and 107 radiomics features were extracted from 75 lesions and assessed using the repeatability coefficient (RC) and the ICC. Radiomic feature repeatability was also quantified after the application of 16 filters to the PET image. RESULTS: Test-retest scans were taken a median of 5 days apart (range: 2-7 days). SUVmean demonstrated the lowest RC limits of the conventional features, with RCs of 7.9%, 14.2% and 24.7% for the [68Ga]Ga-PSMA-11 PET, [18F]F-PSMA-1007 PET, and intertracer groups, respectively. 69%, 66% and 9% of all radiomics features had good or excellent ICC values (ICC ≥ 0.75) for the same groups. Feature repeatability therefore diminished considerably for the intertracer group relative to intratracer groups. CONCLUSION: In this study, robust biomarkers for each tracer group that can be used in subsequent clinical studies were identified. Overall, the repeatability of conventional and radiomic features were found to be substantially lower for the intertracer group relative to both intratracer groups, suggesting that assessing patient response quantitatively should be done using the same radiotracer where possible. ADVANCES IN KNOWLEDGE: Intertracer biomarker repeatability limits are significantly larger than intratracer limits.

Delineation and agreement of FET PET biological volumes in glioblastoma: results of the nuclear medicine credentialing program from the prospective, multi-centre trial evaluating FET PET In Glioblastoma (FIG) study-TROG 18.06.

PURPOSE: The O-(2-[18F]-fluoroethyl)-L-tyrosine (FET) PET in Glioblastoma (FIG) trial is an Australian prospective, multi-centre study evaluating FET PET for glioblastoma patient management. FET PET imaging timepoints are pre-chemoradiotherapy (FET1), 1-month post-chemoradiotherapy (FET2), and at suspected progression (FET3). Before participant recruitment, site nuclear medicine physicians (NMPs) underwent credentialing of FET PET delineation and image interpretation. METHODS: Sites were required to complete contouring and dynamic analysis by ≥ 2 NMPs on benchmarking cases (n = 6) assessing biological tumour volume (BTV) delineation (3 × FET1) and image interpretation (3 × FET3). Data was reviewed by experts and violations noted. BTV definition includes tumour-to-background ratio (TBR) threshold of 1.6 with crescent-shaped background contour in the contralateral normal brain. Recurrence/pseudoprogression interpretation (FET3) required assessment of maximum TBR (TBRmax), dynamic analysis (time activity curve [TAC] type, time to peak), and qualitative assessment. Intraclass correlation coefficient (ICC) assessed volume agreement, coefficient of variation (CoV) compared maximum/mean TBR (TBRmax/TBRmean) across cases, and pairwise analysis assessed spatial (Dice similarity coefficient [DSC]) and boundary agreement (Hausdorff distance [HD], mean absolute surface distance [MASD]). RESULTS: Data was accrued from 21 NMPs (10 centres, n ≥ 2 each) and 20 underwent review. The initial pass rate was 93/119 (78.2%) and 27/30 requested resubmissions were completed. Violations were found in 25/72 (34.7%; 13/12 minor/major) of FET1 and 22/74 (29.7%; 14/8 minor/major) of FET3 reports. The primary reasons for resubmission were as follows: BTV over-contour (15/30, 50.0%), background placement (8/30, 26.7%), TAC classification (9/30, 30.0%), and image interpretation (7/30, 23.3%). CoV median and range for BTV, TBRmax, and TBRmean were 21.53% (12.00-30.10%), 5.89% (5.01-6.68%), and 5.01% (3.37-6.34%), respectively. BTV agreement was moderate to excellent (ICC = 0.82; 95% CI, 0.63-0.97) with good spatial (DSC = 0.84 ± 0.09) and boundary (HD = 15.78 ± 8.30 mm; MASD = 1.47 ± 1.36 mm) agreement. CONCLUSION: The FIG study credentialing program has increased expertise across study sites. TBRmax and TBRmean were robust, with considerable variability in BTV delineation and image interpretation observed.

Prognostic utility of RECIP 1.0 with manual and AI-based segmentations in biochemically recurrent prostate cancer from [68Ga]Ga-PSMA-11 PET images.

PURPOSE: This study aimed to (i) validate the Response Evaluation Criteria in PSMA (RECIP 1.0) criteria in a cohort of biochemically recurrent (BCR) prostate cancer (PCa) patients and (ii) determine if this classification could be performed fully automatically using a trained artificial intelligence (AI) model. METHODS: One hundred ninety-nine patients were imaged with [68Ga]Ga-PSMA-11 PET/CT once at the time of biochemical recurrence and then a second time a median of 6.0 months later to assess disease progression. Standard-of-care treatments were administered to patients in the interim. Whole-body tumour volume was quantified semi-automatically (TTVman) in all patients and using a novel AI method (TTVAI) in a subset (n = 74, the remainder were used in the training process of the model). Patients were classified as having progressive disease (RECIP-PD), or non-progressive disease (non RECIP-PD). Association of RECIP classifications with patient overall survival (OS) was assessed using the Kaplan-Meier method with the log rank test and univariate Cox regression analysis with derivation of hazard ratios (HRs). Concordance of manual and AI response classifications was evaluated using the Cohen's kappa statistic. RESULTS: Twenty-six patients (26/199 = 13.1%) presented with RECIP-PD according to semi-automated delineations, which was associated with a significantly lower survival probability (log rank p < 0.005) and higher risk of death (HR = 3.78 (1.96-7.28), p < 0.005). Twelve patients (12/74 = 16.2%) presented with RECIP-PD according to AI-based segmentations, which was also associated with a significantly lower survival (log rank p = 0.013) and higher risk of death (HR = 3.75 (1.23-11.47), p = 0.02). Overall, semi-automated and AI-based RECIP classifications were in fair agreement (Cohen's k = 0.31). CONCLUSION: RECIP 1.0 was demonstrated to be prognostic in a BCR PCa population and is robust to two different segmentation methods, including a novel AI-based method. RECIP 1.0 can be used to assess disease progression in PCa patients with less advanced disease. This study was registered with the Australian New Zealand Clinical Trials Registry (ACTRN12615000608561) on 11 June 2015.

Fully automatic prognostic biomarker extraction from metastatic prostate lesion segmentations in whole-body [68Ga]Ga-PSMA-11 PET/CT images.

PURPOSE: This study aimed to develop and assess an automated segmentation framework based on deep learning for metastatic prostate cancer (mPCa) lesions in whole-body [68Ga]Ga-PSMA-11 PET/CT images for the purpose of extracting patient-level prognostic biomarkers. METHODS: Three hundred thirty-seven [68Ga]Ga-PSMA-11 PET/CT images were retrieved from a cohort of biochemically recurrent PCa patients. A fully 3D convolutional neural network (CNN) is proposed which is based on the self-configuring nnU-Net framework, and was trained on a subset of these scans, with an independent test set reserved for model evaluation. Voxel-level segmentation results were assessed using the dice similarity coefficient (DSC), positive predictive value (PPV), and sensitivity. Sensitivity and PPV were calculated to assess lesion level detection; patient-level classification results were assessed by the accuracy, PPV, and sensitivity. Whole-body biomarkers total lesional volume (TLVauto) and total lesional uptake (TLUauto) were calculated from the automated segmentations, and Kaplan-Meier analysis was used to assess biomarker relationship with patient overall survival. RESULTS: At the patient level, the accuracy, sensitivity, and PPV were all > 90%, with the best metric being the PPV (97.2%). PPV and sensitivity at the lesion level were 88.2% and 73.0%, respectively. DSC and PPV measured at the voxel level performed within measured inter-observer variability (DSC, median = 50.7% vs. second observer = 32%, p = 0.012; PPV, median = 64.9% vs. second observer = 25.7%, p < 0.005). Kaplan-Meier analysis of TLVauto and TLUauto showed they were significantly associated with patient overall survival (both p < 0.005). CONCLUSION: The fully automated assessment of whole-body [68Ga]Ga-PSMA-11 PET/CT images using deep learning shows significant promise, yielding accurate scan classification, voxel-level segmentations within inter-observer variability, and potentially clinically useful prognostic biomarkers associated with patient overall survival. TRIAL REGISTRATION: This study was registered with the Australian New Zealand Clinical Trials Registry (ACTRN12615000608561) on 11 June 2015.

Deep learning methods for enhancing cone-beam CT image quality toward adaptive radiation therapy: A systematic review.

The use of deep learning (DL) to improve cone-beam CT (CBCT) image quality has gained popularity as computational resources and algorithmic sophistication have advanced in tandem. CBCT imaging has the potential to facilitate online adaptive radiation therapy (ART) by utilizing up-to-date patient anatomy to modify treatment parameters before irradiation. Poor CBCT image quality has been an impediment to realizing ART due to the increased scatter conditions inherent to cone-beam acquisitions. Given the recent interest in DL applications in radiation oncology, and specifically DL for CBCT correction, we provide a systematic theoretical and literature review for future stakeholders. The review encompasses DL approaches for synthetic CT generation, as well as projection domain methods employed in the CBCT correction literature. We review trends pertaining to publications from January 2018 to April 2022 and condense their major findings-with emphasis on study design and DL techniques. Clinically relevant endpoints relating to image quality and dosimetric accuracy are summarized, highlighting gaps in the literature. Finally, we make recommendations for both clinicians and DL practitioners based on literature trends and the current DL state-of-the-art methods utilized in radiation oncology.

Radiomics for Identification and Prediction in Metastatic Prostate Cancer: A Review of Studies.

Metastatic Prostate Cancer (mPCa) is associated with a poor patient prognosis. mPCa spreads throughout the body, often to bones, with spatial and temporal variations that make the clinical management of the disease difficult. The evolution of the disease leads to spatial heterogeneity that is extremely difficult to characterise with solid biopsies. Imaging provides the opportunity to quantify disease spread. Advanced image analytics methods, including radiomics, offer the opportunity to characterise heterogeneity beyond what can be achieved with simple assessment. Radiomics analysis has the potential to yield useful quantitative imaging biomarkers that can improve the early detection of mPCa, predict disease progression, assess response, and potentially inform the choice of treatment procedures. Traditional radiomics analysis involves modelling with hand-crafted features designed using significant domain knowledge. On the other hand, artificial intelligence techniques such as deep learning can facilitate end-to-end automated feature extraction and model generation with minimal human intervention. Radiomics models have the potential to become vital pieces in the oncology workflow, however, the current limitations of the field, such as limited reproducibility, are impeding their translation into clinical practice. This review provides an overview of the radiomics methodology, detailing critical aspects affecting the reproducibility of features, and providing examples of how artificial intelligence techniques can be incorporated into the workflow. The current landscape of publications utilising radiomics methods in the assessment and treatment of mPCa are surveyed and reviewed. Associated studies have incorporated information from multiple imaging modalities, including bone scintigraphy, CT, PET with varying tracers, multiparametric MRI together with clinical covariates, spanning the prediction of progression through to overall survival in varying cohorts. The methodological quality of each study is quantified using the radiomics quality score. Multiple deficits were identified, with the lack of prospective design and external validation highlighted as major impediments to clinical translation. These results inform some recommendations for future directions of the field.