Faculty Bibliography

PURPOSE/OBJECTIVE:Neuroendocrine tumors (NETs) are a rare form of cancer that can occur anywhere in the body and commonly metastasizes. The large variance in location and aggressiveness of the tumors makes it a difficult cancer to treat. Assessments of the whole-body tumor burden in a patient image allow for better tracking of disease progression and inform better treatment decisions. Currently, radiologists rely on qualitative assessments of this metric since manual segmentation is unfeasible within a typical busy clinical workflow. METHODS:We address these challenges by extending the application of the nnU-net pipeline to produce automatic NET segmentation models. We utilize the ideal imaging type of 68Ga-DOTATATE PET/CT to produce segmentation masks from which to calculate total tumor burden metrics. We provide a human-level baseline for the task and perform ablation experiments of model inputs, architectures, and loss functions. RESULTS:Our dataset is comprised of 915 PET/CT scans and is divided into a held-out test set (87 cases) and 5 training subsets to perform cross-validation. The proposed models achieve test Dice scores of 0.644, on par with our inter-annotator Dice score on a subset 6 patients of 0.682. If we apply our modified Dice score to the predictions, the test performance reaches a score of 0.80. CONCLUSION/CONCLUSIONS:In this paper, we demonstrate the ability to automatically generate accurate NET segmentation masks given PET images through supervised learning. We publish the model for extended use and to support the treatment planning of this rare cancer.

OBJECTIVES/OBJECTIVE:The aims of this study were to determine whether ComBat harmonization improves multiclass radiomics-based tissue classification in technically heterogeneous MRI data sets and to compare the performances of 2 ComBat variants. MATERIALS AND METHODS/METHODS:One hundred patients who had undergone T1-weighted 3D gradient echo Dixon MRI (2 scanners/vendors; 50 patients each) were retrospectively included. Volumes of interest (2.5 cm3) were placed in 3 disease-free tissues with visually similar appearance on T1 Dixon water images: liver, spleen, and paraspinal muscle. Gray-level histogram (GLH), gray-level co-occurrence matrix (GLCM), gray-level run-length matrix (GLRLM), and gray-level size-zone matrix (GLSZM) radiomic features were extracted. Tissue classification was performed on pooled data from the 2 centers (1) without harmonization, (2) after ComBat harmonization with empirical Bayes estimation (ComBat-B), and (3) after ComBat harmonization without empirical Bayes estimation (ComBat-NB). Linear discriminant analysis with leave-one-out cross-validation was used to distinguish among the 3 tissue types, using all available radiomic features as input. In addition, a multilayer perceptron neural network with a random 70%:30% split into training and test data sets was used for the same task, but separately for each radiomic feature category. RESULTS:Linear discriminant analysis-based mean tissue classification accuracies were 52.3% for unharmonized, 66.3% for ComBat-B harmonized, and 92.7% for ComBat-NB harmonized data. For multilayer perceptron neural network, mean classification accuracies for unharmonized, ComBat-B-harmonized, and ComBat-NB-harmonized test data were as follows: 46.8%, 55.1%, and 57.5% for GLH; 42.0%, 65.3%, and 71.0% for GLCM; 45.3%, 78.3%, and 78.0% for GLRLM; and 48.1%, 81.1%, and 89.4% for GLSZM. Accuracies were significantly higher for both ComBat-B- and ComBat-NB-harmonized data than for unharmonized data for all feature categories (at P = 0.005, respectively). For GLCM (P = 0.001) and GLSZM (P = 0.005), ComBat-NB harmonization provided slightly higher accuracies than ComBat-B harmonization. CONCLUSIONS:ComBat harmonization may be useful for multicenter MRI radiomics studies with nonbinary classification tasks. The degree of improvement by ComBat may vary among radiomic feature categories, among classifiers, and among ComBat variants.

PURPOSE/OBJECTIVE:The aim of this study was to compare CXCR4 imaging with 68Ga-pentixafor PET to MRI for treatment response assessment in patients with mantle cell lymphoma (MCL). PATIENTS AND METHODS/METHODS:Twenty-two posttreatment 68Ga-pentixafor PET/MRI scans of 16 patients (7 women and 9 men; mean age, 69.9 ± 7.9) with a total of 67 target lesions on baseline PET/MRI were analyzed. Rates of complete remission per lesion and per scan, according to MRI (based on lesion size) and 68Ga-pentixafor PET (based on SUV decrease to lower than liver and blood pool uptake), were compared using McNemar tests. The t tests and Pearson correlation coefficients (r) were used to compare rates of change in lesion diameter products (DPs) on MRI, and standardized uptake values (SUVmax, SUVmean) on PET, relative to baseline. RESULTS:At interim PET/MRI, 18/32 (56.3%) target lesions met CR criteria on 68Ga-pentixafor PET, and 16/32 (50.0%) lesions met size-based MRI criteria for CR (P = 0.63). At end-of-treatment PET/MRI, 40/57 (70.2%) target lesions met 68Ga-pentixafor PET criteria for CR, and 27/57 (47.4%) lesions met size-based MRI criteria for CR (P = 0.021). Complete remission after treatment was observed more frequently on 68Ga-pentixafor PET (11/22 scans, 54.5%) than on MRI (6/22 scans, 27.3%) (P = 0.031). Rates of change did not differ significantly between lesion DP (-69.20% ± 34.62%) and SUVmax (-64.59% ± 50.78%, P = 0.22), or DP and SUVmean (-60.15 ± 64.58, P = 0.064). Correlations were strong between DP and SUVmax (r = 0.71, P < 0.001) and DP and SUVmean (r = 0.73, P < 0.001). CONCLUSIONS:In MCL patients, 68Ga-pentixafor PET may be superior for assessment of complete remission status than anatomic MRI using lesion size criteria, especially at the end of treatment.

Multiple myeloma (MM) is the second most prevalent hematological malignancy. It remains incurable despite the availability of novel therapeutic approaches, marking an urgent need for new agents for noninvasive targeted imaging of MM lesions. CD38 has proven to be an excellent biomarker due to its high expression in aberrant lymphoid and myeloid cells relative to normal cell populations. Using isatuximab (Sanofi), the latest FDA-approved CD38-targeting antibody, we have developed Zirconium-89(⁸⁹Zr)-labeled isatuximab as a novel immunoPET tracer for the in vivo delineation of MM and evaluated the extension of its applicability to lymphomas. In vitro studies validated the high binding affinity and specificity of ⁸⁹Zr-DFO-isatuximab for CD38. PET imaging demonstrated the high performance of ⁸⁹Zr-DFO-isatuximab as a targeted imaging agent to delineate tumor burden in disseminated models of MM and Burkitt's lymphoma. Ex vivo biodistribution studies confirmed that high accumulations of the tracer in bone marrow and bone skeleton correspond to specific disease lesions as they are reduced to background in blocking and healthy controls. This work demonstrates the promise of ⁸⁹Zr-DFO-isatuximab as an immunoPET tracer for CD38-targeted imaging of MM and certain lymphomas. More importantly, its potential as an alternative to ⁸⁹Zr-DFO-daratumumab holds great clinical relevance.

RECIST 1.1 criteria are commonly used with computed tomography (CT) to evaluate the efficacy of systemic treatments in patients with neuroendocrine tumors (NETs) and liver metastases (LMs), but their relevance is questioned in this setting. We aimed to explore alternative criteria using different numbers of measured LMs and thresholds of size and density variation. We retrospectively studied patients with advanced pancreatic or small intestine NETs with LMs, treated with systemic treatment in the first-and/or second-line, without early progression, in 14 European expert centers. We compared time to treatment failure (TTF) between responders and non-responders according to various criteria defined by 0%, 10%, 20% or 30% decrease in the sum of LM size, and/or by 10%, 15% or 20% decrease in LM density, measured on two, three or five LMs, on baseline (≤1 month before treatment initiation) and first revaluation (≤6 months) contrast-enhanced CT scans. Multivariable Cox proportional hazard models were performed to adjust the association between response criteria and TTF on prognostic factors. We included 129 systemic treatments (long-acting somatostatin analogs 41.9%, chemotherapy 26.4%, targeted therapies 31.8%), administered as first-line (53.5%) or second-line therapies (46.5%) in 91 patients. A decrease ≥10% in the size of three LMs was the response criterion that best predicted prolonged TTF, with significance at multivariable analysis (HR 1.90; 95% CI: 1.06-3.40; p = .03). Conversely, response defined by RECIST 1.1 did not predict prolonged TTF (p = .91), and neither did criteria based on changes in LM density. A ≥10% decrease in size of three LMs could be a more clinically relevant criterion than the current 30% threshold utilized by RECIST 1.1 for the evaluation of treatment efficacy in patients with advanced NETs. Its implementation in clinical trials is mandatory for prospective validation. Criteria based on changes in LM density were not predictive of treatment efficacy. CLINICAL TRIAL REGISTRATION: Registered at CNIL-CERB, Assistance publique hopitaux de Paris as "E-NETNET-L-E-CT" July 2018. No number was assigned. Approved by the Medical Ethics Review Board of University Medical Center Groningen.

This study investigated the predictive role of baseline ¹⁸F-FDG PET/CT (bPET/CT) radiomics from two distinct target lesions in patients with classical Hodgkin's lymphoma (cHL). cHL patients examined with bPET/CT and interim PET/CT between 2010 and 2019 were retrospectively included. Two bPET/CT target lesions were selected for radiomic feature extraction: Lesion_A, with the largest axial diameter, and Lesion_B, with the highest SUV_max. Deauville score at interim PET/CT (DS) and 24-month progression-free-survival (PFS) were recorded. Mann-Whitney test identified the most promising image features (p < 0.05) from both lesions with regards to DS and PFS; all possible radiomic bivariate models were then built through a logistic regression analysis and trained/tested with a cross-fold validation test. The best bivariate models were selected based on their mean area under curve (mAUC). A total of 227 cHL patients were included. The best models for DS prediction had 0.78 ± 0.05 maximum mAUC, with a predominant contribution of Lesion_A features to the combinations. The best models for 24-month PFS prediction reached 0.74 ± 0.12 mAUC and mainly depended on Lesion_B features. bFDG-PET/CT radiomic features from the largest and hottest lesions in patients with cHL may provide relevant information in terms of early response-to-treatment and prognosis, thus representing an earlier and stronger decision-making support for therapeutic strategies. External validations of the proposed model are planned.

OBJECTIVES/OBJECTIVE:To explore radiologists' opinions regarding the shift from in-person oncologic multidisciplinary team meetings (MDTMs) to online MDTMs. To assess the perceived impact of online MDTMs, and to evaluate clinical and technical aspects of online meetings. METHODS:An online questionnaire including 24 questions was e-mailed to all European Society of Oncologic Imaging (ESOI) members. Questions targeted the structure and efficacy of online MDTMs, including benefits and limitations. RESULTS:A total of 204 radiologists responded to the survey. Responses were evaluated using descriptive statistical analysis. The majority (157/204; 77%) reported a shift to online MDTMs at the start of the pandemic. For the most part, this transition had a positive effect on maintaining and improving attendance. The majority of participants reported that online MDTMs provide the same clinical standard as in-person meetings, and that interdisciplinary discussion and review of imaging data were not hindered. Seventy three of 204 (35.8%) participants favour reverting to in-person MDTs, once safe to do so, while 7/204 (3.4%) prefer a continuation of online MDTMs. The majority (124/204, 60.8%) prefer a combination of physical and online MDTMs. CONCLUSIONS:Online MDTMs are a viable alternative to in-person meetings enabling continued timely high-quality provision of care with maintained coordination between specialties. They were accepted by the majority of surveyed radiologists who also favoured their continuation after the pandemic, preferably in combination with in-person meetings. An awareness of communication issues particular to online meetings is important. Training, improved software, and availability of support are essential to overcome technical and IT difficulties reported by participants. KEY POINTS/CONCLUSIONS:• Majority of surveyed radiologists reported shift from in-person to online oncologic MDT meetings during the COVID-19 pandemic. • The shift to online MDTMs was feasible and generally accepted by the radiologists surveyed with the majority reporting that online MDTMs provide the same clinical standard as in-person meetings. • Most would favour the return to in-person MDTMs but would also accept the continued use of online MDTMs following the end of the current pandemic.

PURPOSE:The purpose of this study was to determine whether multiparametric positron emission tomography/magnetic resonance imaging (mpPET/MRI) can improve locoregional staging of rectal cancer (RC) and to assess its prognostic value after resection. METHODS:In this retrospective study, 46 patients with primary RC, who underwent multiparametric 18F-fluorodeoxyglucose (FDG) PET/MRI, followed by surgical resection without chemoradiotherapy, were included. Two readers reviewed T- and N- stage, mesorectal involvement, sphincter infiltration, tumor length, and distance from anal verge. In addition, diffusion-weighted imaging (DWI) and PET parameters were extracted from the multiparametric protocol and were compared to radiological staging as well as to the histopathological reference standard. Clinical and imaging follow-up was systematically assessed for tumor recurrence and death. RESULTS:Locally advanced rectal cancers (LARC) exhibited significantly higher metabolic tumor volume (MTV, AUC 0.74 [95% CI 0.59-0.89], p = 0.004) and total lesion glycolysis (TLG, AUC 0.70 [95% CI 0.53-0.87], p = 0.022) compared to early tumors. T-stage was associated with MTV (AUC 0.70 [95% CI 0.54-0.85], p = 0.021), while N-stage was better assessed using anatomical MRI sequences (AUC 0.72 [95% CI 0.539-0.894], p = 0.032). In the multivariate regression analysis, depending on the model, both anatomical MRI sequences and MTV/TLG were capable of detecting LARC. Combining anatomical MRI stage and MTV/TLG led to a superior diagnostic performance for detecting LARC (AUC 0.81, [95% CI 0.68-0.94], p &lt; 0.001). In the survival analysis, MTV was independently associated with overall survival (HR 1.05 [95% CI 1.01-1.10], p = 0.044). CONCLUSION:Multiparametric PET-MRI can improve identification of locally advanced tumors and, hence, help in treatment stratification. It provides additional information on RC tumor biology and may have prognostic value.

BACKGROUND:Lesion/tissue segmentation on digital medical images enables biomarker extraction, image-guided therapy delivery, treatment response measurement, and training/validation for developing artificial intelligence algorithms and workflows. To ensure data reproducibility, criteria for standardised segmentation are critical but currently unavailable. METHODS:A modified Delphi process initiated by the European Imaging Biomarker Alliance (EIBALL) of the European Society of Radiology (ESR) and the European Organisation for Research and Treatment of Cancer (EORTC) Imaging Group was undertaken. Three multidisciplinary task forces addressed modality and image acquisition, segmentation methodology itself, and standards and logistics. Devised survey questions were fed via a facilitator to expert participants. The 58 respondents to Round 1 were invited to participate in Rounds 2-4. Subsequent rounds were informed by responses of previous rounds. RESULTS/CONCLUSIONS/CONCLUSIONS:Items with ≥ 75% consensus are considered a recommendation. These include system performance certification, thresholds for image signal-to-noise, contrast-to-noise and tumour-to-background ratios, spatial resolution, and artefact levels. Direct, iterative, and machine or deep learning reconstruction methods, use of a mixture of CE marked and verified research tools were agreed and use of specified reference standards and validation processes considered essential. Operator training and refreshment were considered mandatory for clinical trials and clinical research. Items with a 60-74% agreement require reporting (site-specific accreditation for clinical research, minimal pixel number within lesion segmented, use of post-reconstruction algorithms, operator training refreshment for clinical practice). Items with ≤ 60% agreement are outside current recommendations for segmentation (frequency of system performance tests, use of only CE-marked tools, board certification of operators, frequency of operator refresher training). Recommendations by anatomical area are also specified.