[89Zr]Zr-DFO-girentuximab and [18F]FDG PET/CT to Predict Watchful Waiting Duration in Patients with Metastatic Clear-cell Renal Cell Carcinoma

PURPOSE

Watchful waiting (WW) can be considered for patients with metastatic clear-cell renal cell carcinoma (mccRCC) with good or intermediate prognosis, especially those with <2 International Metastatic RCC Database Consortium criteria and ≤2 metastatic sites [referred to as watch and wait ("W&W") criteria]. The IMaging PAtients for Cancer drug SelecTion-Renal Cell Carcinoma study objective was to assess the predictive value of [18F]FDG PET/CT and [89Zr]Zr-DFO-girentuximab PET/CT for WW duration in patients with mccRCC.

EXPERIMENTAL DESIGN

Between February 2015 and March 2018, 48 patients were enrolled, including 40 evaluable patients with good (n = 14) and intermediate (n = 26) prognosis. Baseline contrast-enhanced CT, [18F]FDG and [89Zr]Zr-DFO-girentuximab PET/CT were performed. Primary endpoint was the time to disease progression warranting systemic treatment. Maximum standardized uptake values (SUVmax) were measured using lesions on CT images coregistered to PET/CT. High and low uptake groups were defined on the basis of median geometric mean SUVmax of RECIST-measurable lesions across patients.

RESULTS

The median WW time was 16.1 months [95% confidence interval (CI): 9.0-31.7]. The median WW period was shorter in patients with high [18F]FDG tumor uptake than those with low uptake (9.0 vs. 36.2 months; HR, 5.6; 95% CI: 2.4-14.7; P < 0.001). Patients with high [89Zr]Zr-DFO-girentuximab tumor uptake had a median WW period of 9.3 versus 21.3 months with low uptake (HR, 1.7; 95% CI: 0.9-3.3; P = 0.13). Patients with "W&W criteria" had a longer median WW period of 21.3 compared with patients without: 9.3 months (HR, 1.9; 95% CI: 0.9-3.9; Pone-sided = 0.034). Adding [18F]FDG uptake to the "W&W criteria" improved the prediction of WW duration (P < 0.001); whereas [89Zr]Zr-DFO-girentuximab did not (P = 0.53).

CONCLUSIONS

In patients with good- or intermediate-risk mccRCC, low [18F]FDG uptake is associated with prolonged WW. This study shows the predictive value of the "W&W criteria" for WW duration and shows the potential of [18F]FDG-PET/CT to further improve this.

Meta-Analysis of the Test-Retest Repeatability of [18F]-Fluorodeoxyglucose Standardized Uptake Values: Implications for Assessment of Tumor Response

PURPOSE

Currently, guidelines for PET with 18F-fluorodeoxyglucose (FDG-PET) interpretation for assessment of therapy response in oncology primarily involve visual evaluation of FDG-PET/CT scans. However, quantitative measurements of the metabolic activity in tumors may be even more useful in evaluating response to treatment. Guidelines based on such measurements, including the European Organization for Research and Treatment of Cancer Criteria and PET Response Criteria in Solid Tumors, have been proposed. However, more rigorous analysis of response criteria based on FDG-PET measurements is needed to adopt regular use in practice.

EXPERIMENTAL DESIGN

Well-defined boundaries of repeatability and reproducibility of quantitative measurements to discriminate noise from true signal changes are a needed initial step. An extension of the meta-analysis from de Langen and colleagues (2012) of the test-retest repeatability of quantitative FDG-PET measurements, including mean, maximum, and peak standardized uptake values (SUVmax, SUVmean, and SUVpeak, respectively), was performed. Data from 11 studies in the literature were used to estimate the relationship between the variance in test-retest measurements with uptake level and various study-level, patient-level, and lesion-level characteristics.

RESULTS

Test-retest repeatability of percentage fluctuations for all three types of SUV measurement (max, mean, and peak) improved with higher FDG uptake levels. Repeatability in all three SUV measurements varied for different lesion locations. Worse repeatability in SUVmean was also associated with higher tumor volumes.

CONCLUSIONS

On the basis of these results, recommendations regarding SUV measurements for assessing minimal detectable changes based on repeatability and reproducibility are proposed. These should be applied to differentiate between response categories for a future set of FDG-PET-based criteria that assess clinically significant changes in tumor response.

The Impact of Semiautomatic Segmentation Methods on Metabolic Tumor Volume, Intensity, and Dissemination Radiomics in 18F-FDG PET Scans of Patients with Classical Hodgkin Lymphoma

Consensus about a standard segmentation method to derive metabolic tumor volume (MTV) in classical Hodgkin lymphoma (cHL) is lacking, and it is unknown how different segmentation methods influence quantitative PET features. Therefore, we aimed to evaluate the delineation and completeness of lesion selection and the need for manual adaptation with different segmentation methods, and to assess the influence of segmentation methods on the prognostic value of MTV, intensity, and dissemination radiomics features in cHL patients. Methods: We analyzed a total of 105 ¹⁸F-FDG PET/CT scans from patients with newly diagnosed (n = 35) and relapsed/refractory (n = 70) cHL with 6 segmentation methods: 2 fixed thresholds on SUV4.0 and SUV2.5, 2 relative methods of 41% of SUV_max (41max) and a contrast-corrected 50% of SUV_peak (A50P), and 2 combination majority vote (MV) methods (MV2, MV3). Segmentation quality was assessed by 2 reviewers on the basis of predefined quality criteria: completeness of selection, the need for manual adaptation, and delineation of lesion borders. Correlations and prognostic performance of resulting radiomics features were compared among the methods. Results: SUV4.0 required the least manual adaptation but tended to underestimate MTV and often missed small lesions with low ¹⁸F-FDG uptake. SUV2.5 most frequently included all lesions but required minor manual adaptations and generally overestimated MTV. In contrast, few lesions were missed when using 41max, A50P, MV2, and MV3, but these segmentation methods required extensive manual adaptation and overestimated MTV in most cases. MTV and dissemination features significantly differed among the methods. However, correlations among methods were high for MTV and most intensity and dissemination features. There were no significant differences in prognostic performance for all features among the methods. Conclusion: A high correlation existed between MTV, intensity, and most dissemination features derived with the different segmentation methods, and the prognostic performance is similar. Despite frequently missing small lesions with low ¹⁸F-FDG avidity, segmentation with a fixed threshold of SUV4.0 required the least manual adaptation, which is critical for future research and implementation in clinical practice. However, the importance of small, low ¹⁸F-FDG-avidity lesions should be addressed in a larger cohort of cHL patients.

Convolutional neural networks for automatic image quality control and EARL compliance of PET images

Background

Machine learning studies require a large number of images often obtained on different PET scanners. When merging these images, the use of harmonized images following EARL-standards is essential. However, when including retrospective images, EARL accreditation might not have been in place. The aim of this study was to develop a convolutional neural network (CNN) that can identify retrospectively if an image is EARL compliant and if it is meeting older or newer EARL-standards.

Materials and methods

96 PET images acquired on three PET/CT systems were included in the study. All images were reconstructed with the locally clinically preferred, EARL1, and EARL2 compliant reconstruction protocols. After image pre-processing, one CNN was trained to separate clinical and EARL compliant reconstructions. A second CNN was optimized to identify EARL1 and EARL2 compliant images. The accuracy of both CNNs was assessed using fivefold cross-validation. The CNNs were validated on 24 images acquired on a PET scanner not included in the training data. To assess the impact of image noise on the CNN decision, the 24 images were reconstructed with different scan durations.

Results

In the cross-validation, the first CNN classified all images correctly. When identifying EARL1 and EARL2 compliant images, the second CNN identified 100% EARL1 compliant and 85% EARL2 compliant images correctly. The accuracy in the independent dataset was comparable to the cross-validation accuracy. The scan duration had almost no impact on the results.

Conclusion

The two CNNs trained in this study can be used to retrospectively include images in a multi-center setting by, e.g., adding additional smoothing. This method is especially important for machine learning studies where the harmonization of images from different PET systems is essential.

Supplementary Information

The online version contains supplementary material available at 10.1186/s40658-022-00468-w.

Comparing lesion and feature selections to predict progression in newly diagnosed DLBCL patients with FDG PET/CT radiomics features

PURPOSE

Biomarkers that can accurately predict outcome in DLBCL patients are urgently needed. Radiomics features extracted from baseline [¹⁸F]-FDG PET/CT scans have shown promising results. This study aims to investigate which lesion- and feature-selection approaches/methods resulted in the best prediction of progression after 2 years.

METHODS

A total of 296 patients were included. 485 radiomics features (n = 5 conventional PET, n = 22 morphology, n = 50 intensity, n = 408 texture) were extracted for all individual lesions and at patient level, where all lesions were aggregated into one VOI. 18 features quantifying dissemination were extracted at patient level. Several lesion selection approaches were tested (largest or hottest lesion, patient level [all with/without dissemination], maximum or median of all lesions) and compared to the predictive value of our previously published model. Several data reduction methods were applied (principal component analysis, recursive feature elimination (RFE), factor analysis, and univariate selection). The predictive value of all models was tested using a fivefold cross-validation approach with 50 repeats with and without oversampling, yielding the mean cross-validated AUC (CV-AUC). Additionally, the relative importance of individual radiomics features was determined.

RESULTS

Models with conventional PET and dissemination features showed the highest predictive value (CV-AUC: 0.72-0.75). Dissemination features had the highest relative importance in these models. No lesion selection approach showed significantly higher predictive value compared to our previous model. Oversampling combined with RFE resulted in highest CV-AUCs.

CONCLUSION

Regardless of the applied lesion selection or feature selection approach and feature reduction methods, patient level conventional PET features and dissemination features have the highest predictive value. Trial registration number and date: EudraCT: 2006-005174-42, 01-08-2008.

Proposed New Dynamic Prognostic Index for Diffuse Large B-Cell Lymphoma: International Metabolic Prognostic Index

PURPOSE

Baseline metabolic tumor volume (MTV) is a promising biomarker in diffuse large B-cell lymphoma (DLBCL). Our aims were to determine the best statistical relationship between MTV and survival and to compare MTV with the International Prognostic Index (IPI) and its individual components to derive the best prognostic model.

METHODS

PET scans and clinical data were included from five published studies in newly diagnosed diffuse large B-cell lymphoma. Transformations of MTV were compared with the primary end points of 3-year progression-free survival (PFS) and overall survival (OS) to derive the best relationship for further analyses. MTV was compared with IPI categories and individual components to derive the best model. Patients were grouped into three groups for survival analysis using Kaplan-Meier analysis; 10% at highest risk, 30% intermediate risk, and 60% lowest risk, corresponding with expected clinical outcome. Validation of the best model was performed using four studies as a test set and the fifth study for validation and repeated five times.

RESULTS

The best relationship for MTV and survival was a linear spline model with one knot located at the median MTV value of 307.9 cm3. MTV was a better predictor than IPI for PFS and OS. The best model combined MTV with age as continuous variables and individual stage as I-IV. The MTV-age-stage model performed better than IPI and was also better at defining a high-risk group (3-year PFS 46.3% v 58.0% and 3-year OS 51.5% v 66.4% for the new model and IPI, respectively). A regression formula was derived to estimate individual patient survival probabilities.

CONCLUSION

A new prognostic index is proposed using MTV, age, and stage, which outperforms IPI and enables individualized estimates of patient outcome.

Proposed New Dynamic Prognostic Index for Diffuse Large B-Cell Lymphoma: International Metabolic Prognostic Index

PURPOSE

Baseline metabolic tumor volume (MTV) is a promising biomarker in diffuse large B-cell lymphoma (DLBCL). Our aims were to determine the best statistical relationship between MTV and survival and to compare MTV with the International Prognostic Index (IPI) and its individual components to derive the best prognostic model.

METHODS

PET scans and clinical data were included from five published studies in newly diagnosed diffuse large B-cell lymphoma. Transformations of MTV were compared with the primary end points of 3-year progression-free survival (PFS) and overall survival (OS) to derive the best relationship for further analyses. MTV was compared with IPI categories and individual components to derive the best model. Patients were grouped into three groups for survival analysis using Kaplan-Meier analysis; 10% at highest risk, 30% intermediate risk, and 60% lowest risk, corresponding with expected clinical outcome. Validation of the best model was performed using four studies as a test set and the fifth study for validation and repeated five times.

RESULTS

The best relationship for MTV and survival was a linear spline model with one knot located at the median MTV value of 307.9 cm³. MTV was a better predictor than IPI for PFS and OS. The best model combined MTV with age as continuous variables and individual stage as I-IV. The MTV-age-stage model performed better than IPI and was also better at defining a high-risk group (3-year PFS 46.3% v 58.0% and 3-year OS 51.5% v 66.4% for the new model and IPI, respectively). A regression formula was derived to estimate individual patient survival probabilities.

CONCLUSION

A new prognostic index is proposed using MTV, age, and stage, which outperforms IPI and enables individualized estimates of patient outcome.

18F-FDG PET Improves Baseline Clinical Predictors of Response in Diffuse Large B-Cell Lymphoma: The HOVON-84 Study

We aimed to determine the added value of baseline metabolic tumor volume (MTV) and interim PET (I-PET) to the age-adjusted international prognostic index (aaIPI) to predict 2-y progression-free survival (PFS) in diffuse large B-cell lymphoma. Secondary objectives were to investigate optimal I-PET response criteria (using Deauville score [DS] or quantitative change in SUV_max [ΔSUV_max] between baseline and I-PET4 [observational I-PET scans after 4 cycles of rituximab, cyclophosphamide, doxorubicin, vincristine, and prednisone administered in 2-wk intervals with intensified rituximab in the first 4 cycles [R(R)-CHOP14]). Methods: I-PET4 scans in the HOVON-84 (Hemato-Oncologie voor Volwassenen Nederland [Haemato Oncology Foundation for Adults in the Netherlands]) randomized clinical trial (EudraCT 2006-005174-42) were centrally reviewed using DS (cutoff, 4-5). Additionally, ΔSUV_max (prespecified cutoff, 70%) and baseline MTV were measured. Multivariable hazard ratio (HR), positive predictive value (PPV), and negative predictive value (NPV) were obtained for 2-y PFS. Results: In total, 513 I-PET4 scans were reviewed according to DS, and ΔSUV_max and baseline MTV were available for 367 and 296 patients. The NPV of I-PET ranged between 82% and 86% for all PET response criteria. Univariate HR and PPV were better for ΔSUV_max (4.8% and 53%, respectively) than for DS (3.1% and 38%, respectively). aaIPI and ΔSUV_max independently predicted 2-y PFS (HR, 3.2 and 5.0, respectively); adding MTV brought about a slight improvement. Low or low-intermediate aaIPI combined with a ΔSUV_max of more than 70% (37% of patients) yielded an NPV of 93%, and the combination of high-intermediate or high aaIPI and a ΔSUV_max of 70% or less yielded a PPV of 65%. Conclusion: In this study on diffuse large B-cell lymphoma, I-PET after 4 cycles of R(R)-CHOP14 added predictive value to aaIPI for 2-y PFS, and both were independent response biomarkers in a multivariable Cox model. We externally validated that ΔSUV_max outperformed DS in 2-y PFS prediction.

Dual time point imaging in locally advanced head and neck cancer to assess residual nodal disease after chemoradiotherapy

Background

FDG-PET/CT has a high negative predictive value to detect residual nodal disease in patients with locally advanced squamous cell head and neck cancer after completing concurrent chemoradiotherapy (CCRT). However, the positive predictive value remains suboptimal due to inflammation after radiotherapy, generating unnecessary further investigations and possibly even surgery. We report the results of a preplanned secondary end point of the ECLYPS study regarding the potential advantages of dual time point FDG-PET/CT imaging (DTPI) in this setting. Standardized dedicated head and neck FDG-PET/CT images were obtained 12 weeks after CCRT at 60 and 120 min after tracer administration. We performed a semiquantitative assessment of lymph nodes, and the retention index (RI) was explored to optimize diagnostic performance. The reference standard was histology, negative FDG-PET/CT at 1 year, or > 2 years of clinical follow-up. The time-dependent area under the receiver operator characteristics (AUROC) curves was calculated.

Results

In total, 102 subjects were eligible for analysis. SUV values increased in malignant nodes (median SUV₁ = 2.6 vs. SUV₂ = 2.7; P = 0.04) but not in benign nodes (median SUV₁ = 1.8 vs. SUV₂ = 1.7; P = 0.28). In benign nodes, RI was negative although highly variable (median RI = − 2.6; IQR 21.2), while in malignant nodes RI was positive (median RI = 12.3; IQR 37.2) and significantly higher (P = 0.018) compared to benign nodes. A combined threshold (SUV₁ ≥ 2.2 + RI ≥ 3%) significantly reduced the amount of false-positive cases by 53% (P = 0.02) resulting in an increased specificity (90.8% vs. 80.5%) and PPV (52.9% vs. 37.0%), while sensitivity (60.0% vs. 66.7%) and NPV remained comparably high (92.9% vs. 93.3%). However, AUROC, as overall measure of benefit in diagnostic accuracy, did not significantly improve (P = 0.62). In HPV-related disease (n = 32), there was no significant difference between SUV₁, SUV₂, and RI in malignant and benign nodes, yet this subgroup was small.

Conclusions

DTPI did not improve the overall diagnostic accuracy of FDG-PET/CT to detect residual disease 12 weeks after chemoradiation. Due to differences in tracer kinetics between malignant and benign nodes, DTPI improved the specificity, but at the expense of a loss in sensitivity, albeit minimal. Since false negatives at the 12 weeks PET/CT are mainly due to minimal residual disease, DTPI is not able to significantly improve sensitivity, but repeat scanning at a later time (e.g. after 12 months) could possibly solve this problem. Further study is required in HPV-associated disease.

Cost-Effectiveness of Shortening Treatment Duration Based on Interim PET Outcome in Patients With Diffuse Large B-cell Lymphoma

BACKGROUND

Guideline recommendations for diffuse large-B-cell lymphoma (DLBCL) treatment are shifting from long to short treatment duration, although it is still unclear whether shortening treatment duration does not cause any harm. As interim PET (I-PET) has high negative predictive value for progression, we evaluated the cost-effectiveness of shortening treatment duration dependent on I-PET result.

MATERIALS AND METHODS

We developed a Markov cohort model using the PET Re-Analysis (PETRA) database to evaluate a long treatment duration (LTD) strategy, ie 8x R-CHOP or 6x R-CHOP plus 2 R, and a short treatment duration (STD) strategy, ie 6x R-CHOP. Strategies were evaluated separately in I-PET2 positive and I-PET2 negative patients. Outcomes included total costs and quality-adjusted life-years (QALYs) per patient (pp) from a societal perspective. Net monetary benefit (NMB) per strategy was calculated using a willingness-to-pay threshold of €50,000/QALY. Robustness of model predictions was assessed in sensitivity analyses.

RESULTS

In I-PET2 positive patients, shortening treatment duration led to 50.4 additional deaths per 1000 patients. The STD strategy was less effective (-0.161 [95%CI: -0.343;0.028] QALYs pp) and less costly (-€2768 [95%CI: -€8420;€1105] pp). Shortening treatment duration was not cost-effective (incremental NMB -€5281). In I-PET2 negative patients, shortening treatment duration led to 5.0 additional deaths per 1000 patients and a minor difference in effectiveness (-0.007 [95%CI: -0.136;0.140] QALY pp). The STD strategy was less costly (-€5807 [95%CI: -€10,724;-€2685] pp) and led to an incremental NMB of €5449, indicating that it is cost-effective to shorten treatment duration. Robustness of these findings was underpinned by deterministic and probabilistic sensitivity analyses.

CONCLUSION

Treatment duration should not be shortened in I-PET2 positive patients whereas it is cost-effective to shorten treatment duration in I-PET2 negative patients.

3D Convolutional Neural Network-Based Denoising of Low-Count Whole-Body 18F-Fluorodeoxyglucose and 89Zr-Rituximab PET Scans

Acquisition time and injected activity of ¹⁸F-fluorodeoxyglucose (¹⁸F-FDG) PET should ideally be reduced. However, this decreases the signal-to-noise ratio (SNR), which impairs the diagnostic value of these PET scans. In addition, ⁸⁹Zr-antibody PET is known to have a low SNR. To improve the diagnostic value of these scans, a Convolutional Neural Network (CNN) denoising method is proposed. The aim of this study was therefore to develop CNNs to increase SNR for low-count ¹⁸F-FDG and ⁸⁹Zr-antibody PET. Super-low-count, low-count and full-count ¹⁸F-FDG PET scans from 60 primary lung cancer patients and full-count ⁸⁹Zr-rituximab PET scans from five patients with non-Hodgkin lymphoma were acquired. CNNs were built to capture the features and to denoise the PET scans. Additionally, Gaussian smoothing (GS) and Bilateral filtering (BF) were evaluated. The performance of the denoising approaches was assessed based on the tumour recovery coefficient (TRC), coefficient of variance (COV; level of noise), and a qualitative assessment by two nuclear medicine physicians. The CNNs had a higher TRC and comparable or lower COV to GS and BF and was also the preferred method of the two observers for both ¹⁸F-FDG and ⁸⁹Zr-rituximab PET. The CNNs improved the SNR of low-count ¹⁸F-FDG and ⁸⁹Zr-rituximab PET, with almost similar or better clinical performance than the full-count PET, respectively. Additionally, the CNNs showed better performance than GS and BF.

Aberrant patterns of PET response during treatment for DLBCL patients with MYC gene rearrangements

Purpose

MYC gene rearrangements in diffuse large B-cell lymphoma (DLBCL) patients are associated with poor prognosis. Our aim was to compare patterns of 2[¹⁸F]fluoro-2-deoxy-D-glucose positron emission tomography computed tomography (PET/CT) response in MYC + and MYC- DLBCL patients.

Methods

Interim PET/CT (I-PET) and end of treatment PET/CT (EoT-PET) scans of 81 MYC + and 129 MYC- DLBCL patients from 2 HOVON trials were reviewed using the Deauville 5-point scale (DS). DS1-3 was regarded as negative and DS4-5 as positive. Standardized uptake values (SUV) and metabolic tumor volume (MTV) were quantified at baseline, I-PET, and EoT-PET. Negative (NPV) and positive predictive values (PPV) were calculated using 2-year overall survival.

Results

MYC + DLBCL patients had significantly more positive EoT-PET scans than MYC- patients (32.5 vs 15.7%, p = 0.004). I-PET positivity rates were comparable (28.8 vs 23.8%). In MYC + patients 23.2% of the I-PET negative patients converted to positive at EoT-PET, vs only 2% for the MYC- patients (p = 0.002). Nine (34.6%) MYC + DLBCL showed initially uninvolved localizations at EoT-PET, compared to one (5.3%) MYC- patient. A total of 80.8% of EoT-PET positive MYC + patients showed both increased lesional SUV and MTV compared to I-PET. In MYC- patients, 31.6% showed increased SUV and 42.1% showed increased MTV. NPV of I-PET and EoT-PET was high for both MYC subgroups (81.8–94.1%). PPV was highest at EoT-PET for MYC + patients (61.5%).

Conclusion

MYC + DLBCL patients demonstrate aberrant PET response patterns compared to MYC- patients with more frequent progression during treatment after I-PET negative assessment and new lesions at sites that were not initially involved.

Trial registration number and date of registration

HOVON-84: EudraCT: 2006–005,174-42, retrospectively registered 01–08-2008. HOVON-130: EudraCT: 2014–002,654-39, registered 26–01-2015

Supplementary Information

The online version contains supplementary material available at 10.1007/s00259-021-05498-7.

Potential and pitfalls of 89Zr-immuno-PET to assess target status: 89Zr-trastuzumab as an example

Background

⁸⁹Zirconium-immuno-positron emission tomography (⁸⁹Zr-immuno-PET) is used for assessment of target status to guide antibody-based therapy. We aim to determine the relation between antibody tumor uptake and target concentration to improve future study design and interpretation.

Methods

The relation between tumor uptake and target concentration was predicted by mathematical modeling of ⁸⁹Zr-labeled antibody disposition in the tumor. Literature values for trastuzumab kinetics were used to provide an example.

Results

⁸⁹Zr-trastuzumab uptake initially increases with increasing target concentration, until it levels off to a constant value. This is determined by the total administered mass dose of trastuzumab. For a commonly used imaging dose of 50 mg ⁸⁹Zr-trastuzumab, uptake can discriminate between immunohistochemistry score (IHC) 0 versus 1–2–3.

Conclusion

The example for ⁸⁹Zr-trastuzumab illustrates the potential to assess target expression. The pitfall of false-positive findings depends on the cut-off to define clinical target positivity (i.e., IHC 3) and the administered mass dose.

PD-L1 PET/CT imaging with radiolabeled durvalumab in patients with advanced stage non-small cell lung cancer

Background: Better biomarkers are needed to predict treatment outcome in NSCLC patients treated with anti PD-(L)1 checkpoint inhibitors. PD-L1 immunohistochemistry has limited predictive value, possibly due to tumor heterogeneity of PD-L1 expression. Noninvasive PD-L1 imaging using ⁸⁹Zr-durvalumab might provide a better reflection of tumor PD-L1 expression and can therefore support treatment decision making. Patients and Methods: NSCLC patients eligible for second line immunotherapy treatment were enrolled. Patients received two injections of ⁸⁹Zr-durvalumab; one without a preceding dose of unlabeled durvalumab ('tracer dose only') and one with a preceding dose of 750 mg durvalumab, directly prior to tracer injection. Up to four PET/CT scans were obtained after tracer injection. Post-imaging acquisition, patients were treated with 750mg durvalumab every two weeks. Tracer biodistribution and tumor uptake were visually assessed and quantified as standardized uptake value (SUV) and both imaging acquisitions were compared. Tumor tracer uptake was correlated with PD-L1 expression and clinical outcome, defined as treatment response to durvalumab treatment. Results: Thirteen patients were included and ten completed all scheduled PET scans. No tracer related adverse events were observed and all patients started durvalumab treatment. Biodistribution analysis showed ⁸⁹Zr-durvalumab accumulation in the blood pool, liver and spleen. Serial imaging showed that image acquisition 120 hours post injection delivered the best tumor to blood pool ratio. Most tumor lesions were visualized with the tracer-dose only versus the co-injection imaging acquisition (25% vs 13.5% of all lesions). Uptake heterogeneity was observed within (range SUVpeak 0.2 to 15.1) and between patients. Tumor uptake was higher in patients with treatment response or stable disease, compared to patients with disease progression according to RECIST 1.1. However, this difference was not statistically significant (median SUVpeak 4.9 vs 2.4, P = 0.06). SUVpeak correlated better with the combined tumor and immune cell PD-L1 score than with PD-L1 expression on tumor cells, although both were not statistically significant (P = 0.06 and P = 0.93, respectively). Conclusion: ⁸⁹Zr-durvalumab was safe without any tracer related adverse events and more tumor lesions were visualized using the tracer dose only imaging acquisition. ⁸⁹Zr-durvalumab tumor uptake was higher in patients with response to durvalumab treatment, but did not correlate with tumor PD-L1 IHC.

Quantitative radiomics features in diffuse large B-cell lymphoma: does segmentation method matter?

INTRODUCTION

Radiomics features may predict outcome in diffuse large B-cell lymphoma (DLBCL). Currently, multiple segmentation methods are used to calculate metabolic tumor volume (MTV). We assessed the influence of segmentation method on the discriminative power of radiomics features in DLBCL for patient level and for the largest lesion. Methods: 50 baseline ¹⁸F-fluorodeoxyglucose positron emission tomography computed tomography (PET/CT) scans of DLBCL patients who progressed or relapsed within 2 years after diagnosis were matched on uptake time and reconstruction method with 50 baseline PET/CT scans of DLBCL patients without progression. Scans were analysed using 6 semi-automatic segmentation methods (standardized uptake value (SUV)4.0, SUV2.5, 41% of the maximum SUV, 50% of the SUVpeak, majority vote (MV)2 and MV3, respectively). Based on these segmentations, 490 radiomics features were extracted at patient level and 486 features for the largest lesion. To quantify the agreement between features extracted from different segmentation methods, the intra-class correlation (ICC) agreement was calculated for each method compared to SUV4.0. The feature space was reduced by deleting features that had high Pearson correlations (≥0.7) with the previously established predictors MTV and/or SUVpeak. Model performance was assessed using stratified repeated cross-validation with 5 folds and 2000 repeats yielding the mean receiver-operating characteristics curve integral (CV-AUC) for all segmentation methods using logistic regression with backward feature selection. Results: The percentage of features yielding an ICC ≥0.75 compared to the SUV4.0 segmentation was lowest for A50P both at patient level and for the largest lesion, with 77.3% and 66.7% of the features yielding an ICC ≥0.75, respectively. Features were not highly correlated with MTV, with at least 435 features at patient level and 409 features for the largest lesion for all segmentation methods with a correlation coefficient <0.7. Features were highly correlated with SUVpeak (at least 190 and 134 were uncorrelated, respectively). CV-AUCs ranged between 0.69±0.11 and 0.84±0.09 for patient level, and between 0.69±0.11 and 0.73±0.10 for lesion level. Conclusion: Even though there are differences in the actual radiomics feature values derived and selected features between segmentation methods, there is no substantial difference in the discriminative power of radiomics features between segmentation methods.

First-in-human study of 89Zr-pembrolizumab PET/CT in patients with advanced stage non-small-cell lung cancer

Background: Tumor programmed-death ligand-1 (PD-L1) proportion score is the current method to select non-small-cell lung cancer (NSCLC) patients for single agent treatment with pembrolizumab, a programmed cell death-1 (PD-1) monoclonal antibody. However, not all patients respond to therapy. Better understanding of in vivo drug behavior may help to select patients that benefit most. Methods: NSCLC patients eligible for pembrolizumab monotherapy as first or later line therapy were enrolled. Patients received two injections of ⁸⁹Zr-pembrolizumab; one without a preceding dose of pembrolizumab and one with 200 mg pembrolizumab, directly prior to tracer injection. Up to four PET/CT scans were obtained after tracer injection. Post-imaging acquisition, patients were treated with 200 mg pembrolizumab, every three weeks. Tumor uptake and tracer biodistribution were visually assessed and quantified as standardized uptake value (SUV). Tumor tracer uptake was correlated with PD-1 and PD-L1 expression and response to pembrolizumab treatment. Results: Twelve NSCLC patients were included. One patient experienced grade 3 myalgia after tracer injection. ⁸⁹Zr-pembrolizumab was observed in the blood pool, liver and spleen. Tracer uptake was visualized in 47,2% of 72 tumor lesions measuring ≥20 mm long axis diameter, and substantial uptake heterogeneity was observed within and between patients. Uptake was higher in patients with response to pembrolizumab treatment (n = 3) compared to patients without a response (n = 9), although this was not statistically significant (median SUVpeak 11.4 vs 5.7, P = 0.066). No significant correlations were found with PD-L1 or PD-1 immunohistochemistry. Conclusion: ⁸⁹Zr-pembrolizumab injection was safe with only one grade 3 adverse event, possibly immune related, out of 12 patients. ⁸⁹Zr-pembrolizumab tumor uptake was higher in patients with response to pembrolizumab treatment, but did not correlate with PD-L1 or PD-1 immunohistochemistry.

11C-Sorafenib and 15O-H2O PET for Early Evaluation of Sorafenib Therapy

Sorafenib leads to clinical benefit in a subgroup of patients, whereas all are exposed to potential toxicity. Currently, no predictive biomarkers are available. The purpose of this study was to evaluate whether ¹¹C-sorafenib and ¹⁵O-H₂O PET have potential to predict treatment efficacy. Methods: In this prospective exploratory study, 8 patients with advanced solid malignancies and an indication for sorafenib treatment were included. Microdose ¹¹C-sorafenib and perfusion ¹⁵O-H₂O dynamic PET scans were performed before and after 2 wk of sorafenib therapy. The main objective was to assess whether tumor ¹¹C-sorafenib uptake predicts sorafenib concentrations during therapy in corresponding tumor biopsy samples measured with liquid chromatography tandem mass spectrometry. Secondary objectives included determining the association of ¹¹C-sorafenib PET findings, perfusion ¹⁵O-H₂O PET findings, and sorafenib concentrations after therapeutic dosing with response. Results: ¹¹C-sorafenib PET findings did not predict sorafenib concentrations in tumor biopsy samples during therapy. In addition, sorafenib plasma and tumor concentrations were not associated with clinical outcome in this exploratory study. Higher ¹¹C-sorafenib accumulation in tumors at baseline and day 14 of treatment showed an association with poorer prognosis and correlated with tumor perfusion (Spearman correlation coefficient = 0.671, P = 0.020). Interestingly, a decrease in tumor perfusion measured with ¹⁵O-H₂O PET after only 14 d of therapy showed an association with response, with a decrease in tumor perfusion of 56% ± 23% (mean ± SD) versus 18% ± 32% in patients with stable and progressive disease, respectively. Conclusion: Microdose ¹¹C-sorafenib PET did not predict intratumoral sorafenib concentrations after therapeutic dosing, but the association between a decrease in tumor perfusion and clinical benefit warrants further investigation.

Spatial concordance of DNA methylation classification in diffuse glioma

Background

Intratumoral heterogeneity is a hallmark of diffuse gliomas. DNA methylation profiling is an emerging approach in the clinical classification of brain tumors. The goal of this study is to investigate the effects of intratumoral heterogeneity on classification confidence.

Methods

We used neuronavigation to acquire 133 image-guided and spatially separated stereotactic biopsy samples from 16 adult patients with a diffuse glioma (7 IDH-wildtype and 2 IDH-mutant glioblastoma, 6 diffuse astrocytoma, IDH-mutant and 1 oligodendroglioma, IDH-mutant and 1p19q codeleted), which we characterized using DNA methylation arrays. Samples were obtained from regions with and without abnormalities on contrast-enhanced T1-weighted and fluid-attenuated inversion recovery MRI. Methylation profiles were analyzed to devise a 3-dimensional reconstruction of (epi)genetic heterogeneity. Tumor purity was assessed from clonal methylation sites.

Results

Molecular aberrations indicated that tumor was found outside imaging abnormalities, underlining the infiltrative nature of this tumor and the limitations of current routine imaging modalities. We demonstrate that tumor purity is highly variable between samples and explains a substantial part of apparent epigenetic spatial heterogeneity. We observed that DNA methylation subtypes are often, but not always, conserved in space taking tumor purity and prediction accuracy into account.

Conclusion

Our results underscore the infiltrative nature of diffuse gliomas and suggest that DNA methylation subtypes are relatively concordant in this tumor type, although some heterogeneity exists.

Interobserver agreement in automated metabolic tumor volume measurements of Deauville score 4 and 5 lesions at interim 18F-FDG PET in DLBCL

Introduction: Metabolic tumor volume (MTV) on interim-PET (I-PET) is a potential prognostic biomarker for diffuse large B-cell lymphoma (DLBCL). Implementation of MTV on I-PET requires consensus which semi-automated segmentation method delineates lesions most successfully with least user interaction. Methods used for baseline PET are not necessarily optimal for I-PET due to lower lesional standardized uptake values (SUV) at I-PET. Therefore, we aimed to evaluate which method provides the best delineation quality of Deauville-score (DS) 4-5 DLBCL lesions on I-PET at best interobserver agreement on delineation quality and, secondly, to assess the effect of lesional SUV_max on delineation quality and performance agreements. Methods: DS4-5 lesions from 45 I-PET scans were delineated using six semi-automated methods i) SUV 2.5, ii) SUV 4.0, iii) adaptive threshold [A50%peak], iv) 41% of maximum SUV [41%max], v) majority vote including voxels detected by ≥2 methods [MV2] and vi) detected by ≥3 methods [MV3]. Delineation quality per MTV was rated by three independent observers as acceptable or non-acceptable. For each method, observer scores on delineation quality, specific agreements and MTV were assessed for all lesions, and per category of lesional SUV_max (<5, 5-10, >10). Results: In 60 DS4-5 lesions on I-PET, MV3 performed best, with acceptable delineation in 90% of lesions, with a positive agreement (PA) of 93%. Delineation quality scores and agreements per method strongly depended on lesional SUV: the best delineation quality scores were obtained using MV3 in lesions with SUV_max<10 and SUV4.0 in more FDG-avid lesions. Consequently, overall delineation quality and PA improved by applying the most preferred method per SUV category instead of using MV3 as single best method. MV3- and SUV4.0-derived MTVs of lesions with SUV_max>10, were comparable after excluding visually failed MV3 contouring. For lesions with SUV_max<10, MTVs using different methods correlated poorly. Conclusion: On I-PET, MV3 performed best and provided the highest interobserver agreement regarding acceptable delineations of DS4-5 DLBCL lesions. However, delineation method preference strongly depended on lesional SUV. Therefore, we suggest to explore an approach that identifies the optimal delineation method per lesion as function of tumor FDG uptake characteristics, i.e. SUV_max.

Pelvic lymph-node staging with 18F-DCFPyL PET/CT prior to extended pelvic lymph-node dissection in primary prostate cancer - the SALT trial

PURPOSE

The detection of lymph-node metastases (N1) with conventional imaging such as magnetic resonance imaging (MRI) and computed tomography (CT) is inadequate for primarily diagnosed prostate cancer (PCa). Prostate-specific membrane antigen (PSMA) PET/CT is successfully introduced for the staging of (biochemically) recurrent PCa. Besides the frequently used 68gallium-labelled PSMA tracers, 18fluorine-labelled PSMA tracers are available. This study examined the diagnostic accuracy of 18F-DCFPyL (PSMA) PET/CT for lymph-node staging in primary PCa.

METHODS

This was a prospective, multicentre cohort study. Patients with primary PCa underwent 18F-DCFPyL PET/CT prior to robot-assisted radical prostatectomy (RARP) with extended pelvic lymph-node dissection (ePLND). Patients were included between October 2017 and January 2020. A Memorial Sloan Kettering Cancer Centre (MSKCC) nomogram risk probability of ≥ 8% of lymph-node metastases was set to perform ePLND. All images were reviewed by two experienced nuclear physicians, and were compared with post-operative histopathologic results.

RESULTS

A total of 117 patients was analysed. Lymph-node metastases (N1) were histologically diagnosed in 17/117 patients (14.5%). The sensitivity, specificity, positive predictive value and negative predictive value for the 18F-DCFPyL PET/CT detection of pelvic lymph-node metastases on a patient level were 41.2% (confidence interval (CI): 19.4-66.5%), 94.0% (CI 86.9-97.5%), 53.8% (CI 26.1-79.6%) and 90.4% (CI 82.6-95.0%), respectively.

CONCLUSION

18F-DCFPyL PET/CT showed a high specificity (94.4%), yet a limited sensitivity (41.2%) for the detection of pelvic lymph-node metastases in primary PCa. This implies that current PSMA PET/CT imaging cannot replace diagnostic ePLND. Further research is necessary to define the exact place of PSMA PET/CT imaging in the primary staging of PCa.

Improved detection of diffuse glioma infiltration with imaging combinations: a diagnostic accuracy study

Background

Surgical resection and irradiation of diffuse glioma are guided by standard MRI: T2/fluid attenuated inversion recovery (FLAIR)–weighted MRI for non-enhancing and T1-weighted gadolinium-enhanced (T1G) MRI for enhancing gliomas. Amino acid PET has been suggested as the new standard. Imaging combinations may improve standard MRI and amino acid PET. The aim of the study was to determine the accuracy of imaging combinations to detect glioma infiltration.

Methods

We included 20 consecutive adults with newly diagnosed non-enhancing glioma (7 diffuse astrocytomas, isocitrate dehydrogenase [IDH] mutant; 1 oligodendroglioma, IDH mutant and 1p/19q codeleted; 1 glioblastoma IDH wildtype) or enhancing glioma (glioblastoma, 9 IDH wildtype and 2 IDH mutant). Standardized preoperative imaging (T1-, T2-, FLAIR-weighted, and T1G MRI, perfusion and diffusion MRI, MR spectroscopy and O-(2-[18F]-fluoroethyl)-L-tyrosine ([¹⁸F]FET) PET) was co-localized with multiregion stereotactic biopsies preceding resection. Tumor presence in the biopsies was assessed by 2 neuropathologists. Diagnostic accuracy was determined using receiver operating characteristic analysis.

Results

A total of 174 biopsies were obtained (63 from 9 non-enhancing and 111 from 11 enhancing gliomas), of which 129 contained tumor (50 from non-enhancing and 79 from enhancing gliomas). In enhancing gliomas, the combination of apparent diffusion coefficient (ADC) with [¹⁸F]FET PET (area under the curve [AUC], 95% CI: 0.89, 0.79‒0.99) detected tumor better than T1G MRI (0.56, 0.39‒0.72; P < 0.001) and [¹⁸F]FET PET (0.76, 0.66‒0.86; P = 0.001). In non-enhancing gliomas, no imaging combination detected tumor significantly better than standard MRI. FLAIR-weighted MRI had an AUC of 0.81 (0.65–0.98) compared with 0.69 (0.56–0.81; P = 0.019) for [¹⁸F]FET PET.

Conclusion

Combining ADC and [¹⁸F]FET PET detects glioma infiltration better than standard MRI and [¹⁸F]FET PET in enhancing gliomas, potentially enabling better guidance of local therapy.

Repeatability of two semi-automatic artificial intelligence approaches for tumor segmentation in PET

Background

Positron emission tomography (PET) is routinely used for cancer staging and treatment follow-up. Metabolic active tumor volume (MATV) as well as total MATV (TMATV—including primary tumor, lymph nodes and metastasis) and/or total lesion glycolysis derived from PET images have been identified as prognostic factor or for the evaluation of treatment efficacy in cancer patients. To this end, a segmentation approach with high precision and repeatability is important. However, the implementation of a repeatable and accurate segmentation algorithm remains an ongoing challenge.

Methods

In this study, we compare two semi-automatic artificial intelligence (AI)-based segmentation methods with conventional semi-automatic segmentation approaches in terms of repeatability. One segmentation approach is based on a textural feature (TF) segmentation approach designed for accurate and repeatable segmentation of primary tumors and metastasis. Moreover, a convolutional neural network (CNN) is trained. The algorithms are trained, validated and tested using a lung cancer PET dataset. The segmentation accuracy of both segmentation approaches is compared using the Jaccard coefficient (JC). Additionally, the approaches are externally tested on a fully independent test–retest dataset. The repeatability of the methods is compared with those of two majority vote (MV2, MV3) approaches, 41%SUV_MAX, and a SUV > 4 segmentation (SUV4). Repeatability is assessed with test–retest coefficients (TRT%) and intraclass correlation coefficient (ICC). An ICC > 0.9 was regarded as representing excellent repeatability.

Results

The accuracy of the segmentations with the reference segmentation was good (JC median TF: 0.7, CNN: 0.73). Both segmentation approaches outperformed most other conventional segmentation methods in terms of test–retest coefficient (TRT% mean: TF: 13.0%, CNN: 13.9%, MV2: 14.1%, MV3: 28.1%, 41%SUV_MAX: 28.1%, SUV4: 18.1%) and ICC (TF: 0.98, MV2: 0.97, CNN: 0.99, MV3: 0.73, SUV4: 0.81, and 41%SUV_MAX: 0.68).

Conclusion

The semi-automatic AI-based segmentation approaches used in this study provided better repeatability than conventional segmentation approaches. Moreover, both algorithms lead to accurate segmentations for both primary tumors as well as metastasis and are therefore good candidates for PET tumor segmentation.