Search

The aim of this study was to validate a previously developed deep learning model in 5 independent clinical trials. The predictive performance of this model was compared with the international prognostic index (IPI) and 2 models incorporating radiomic PET/CT features (clinical PET and PET models). Methods: In total, 1,132 diffuse large B-cell lymphoma patients were included: 296 for training and 836 for external validation. The primary outcome was 2-y time to progression. The deep learning model was trained on maximum-intensity projections from PET/CT scans. The clinical PET model included metabolic tumor volume, maximum distance from the bulkiest lesion to another lesion, SUV peak , age, and performance status. The PET model included metabolic tumor volume, maximum distance from the bulkiest lesion to another lesion, and SUV peak Model performance was assessed using the area under the curve (AUC) and Kaplan-Meier curves. Results: The IPI yielded an AUC of 0.60 on all external data. The deep learning model yielded a significantly higher AUC of 0.66 ( P < 0.01). For each individual clinical trial, the model was consistently better than IPI. Radiomic model AUCs remained higher for all clinical trials. The deep learning and clinical PET models showed equivalent performance (AUC, 0.69; P > 0.05). The PET model yielded the highest AUC of all models (AUC, 0.71; P < 0.05). Conclusion: The deep learning model predicted outcome in all trials with a higher performance than IPI and better survival curve separation. This model can predict treatment outcome in diffuse large B-cell lymphoma without tumor delineation but at the cost of a lower prognostic performance than with radiomics., (© 2024 by the Society of Nuclear Medicine and Molecular Imaging.)

Objectives: To investigate the prognostic value of clinical, volumetric, and radiomics-based textural parameters in baseline [18F]FDG-PET/CT scans of diffuse large B-cell lymphoma (DLBCL) patients., Methods: We retrospectively investigated baseline PET/CT scans and collected clinical data of fifty DLBCL patients. PET images were segmented semiautomatically to determine metabolic tumor volume (MTV), then the largest segmented lymphoma volume of interest (VOI) was used to extract first-, second-, and high-order textural features. A novel value, MTVrate was introduced as the quotient of the largest lesion's volume and total body MTV. Receiver operating characteristics (ROC) analyses were performed and 24-months progression-free survival (PFS) of low- and high-risk cohorts were compared by log-rank analyses. A machine learning algorithm was used to build a prognostic model from the available clinical, volumetric, and textural data based on logistic regression., Results: The area-under-the-curve (AUC) on ROC analysis was the highest of MTVrate at 0.74, followed by lactate-dehydrogenase, MTV, and skewness, with AUCs of 0.68, 0.63, and 0.55, respectively which parameters were also able to differentiate the PFS. A combined survival analysis including MTV and MTVrate identified a subgroup with particularly low PFS at 38%. In the machine learning-based model had an AUC of 0.83 and the highest relative importance was attributed to three textural features and both MTV and MTVrate as important predictors of PFS., Conclusion: Individual evaluation of different biomarkers yielded only limited prognostic data, whereas a machine learning-based combined analysis had higher effectivity. MTVrate had the highest prognostic ability on individual analysis and, combined with MTV, it identified a patient group with particularly poor prognosis., (Copyright © 2024 The Author(s). Published by Wolters Kluwer Health, Inc.)

Abstract: A 76-year-old man with hepatocellular carcinoma was referred for liver radioembolization. Given a prior left hemihepatectomy, it was clinically important to consider potentially irradiated healthy liver at planning. Thus, at the SPECT/CT imaging of the scout dose 166 Ho-microparticles before injected superselectively in the right hepatic artery, 99m Tc-mebrofenin was injected intravenously, and functional volumetry SPECT was performed simultaneously. Based on the 2 image sets, the nonirradiated healthy liver was calculated as 1589 mL (functional liver reserve of 85.5% on 99m Tc-mebrofenin SPECT). Posttreatment dosimetry calculations showed optimal normal tissue and tumor absorbed doses, and the patient is clinically well after 3 months., Competing Interests: Conflicts of interest and sources of funding: none declared., (Copyright © 2023 The Author(s). Published by Wolters Kluwer Health, Inc.)

The staff of the Radiation Protection Service of a European clinical center measured the radiation dose by type-tested thermoluminescent dosemeter systems to which the medical staff was exposed, to assess the effectiveness of current procedures and equipment for optimalisation prompted by the requirements EU Basic Safety Standard 2013. There were three participating sites, the Site 1 was an external hospital, whereas Sites 2 and 3 are part of the same clinical center, who provided data regarding their personnel, from technologists, nurses and medical doctors. In this preliminary study, only a low number of cases were available and used to establish a new, more realistic yearly dose constraint, namely 6 (from two) mSv for whole-body effective dose, 15 (from two) mSv for eye lens dose and 300 (from 50) mSv for extremity dose. Furthermore, the state of safety culture and protection equipment was assessed. Collection of the sufficient amount of data for statistical evaluation is ongoing., (© The Author(s) 2023. Published by Oxford University Press. All rights reserved. For Permissions, please email: journals.permissions@oup.com.)

Objective: 2-[ 18 F]fluoro-2-deoxy- d -glucose PET/computed tomography ([ 18 F]FDG-PET/CT) is a widely used imaging method in the management of diffuse large B-cell lymphomas (DLBCL). Our aim was to investigate the prognostic performance of different PET biomarkers in a multicenter setting., Methods: We investigated baseline volumetric values [metabolic tumor volume (MTV) and total lesion glycolysis (TLG), also normalized for body weight] segmented with three different methods [>SUV4 (glob4); 41% isocontour (41pc), and a gradient-based lesion growing algorithm (grad)] and interim parameters [Deauville score, maximal standardized uptake value (ΔSUVmax), modified qPET, and ratio PET (rPET)] alongside clinical parameters (stage, revised International Prognostic Index), using 24-month progression-free survival as the clinical endpoint. Receiver operating characteristics analyses were performed to define optimal cutoff points for the continuous PET parameters., Results: A total of 107 diffuse large B-cell lymphoma patients were included (54 women; mean age: 53.7 years). MTV and TLG calculations showed good correlation among glob4, 41pc, and grad methods; however, optimal cutoff points were markedly different.Significantly different PFS was observed between low- and high-risk groups according to baseline MTV, body weight-adjusted (bwa) MTV, TLG, bwaTLG, as well as interim parameters Deauville score, ΔSUVmax, mqPET, and rPET. Univariate Cox regression analyses showed hazard ratios (HRs) lowest for bwaMTVglob4 (HR = 2.3) and highest for rPET (HR = 9.09). In a multivariate Cox-regression model, rPET was shown to be an independent predictor of PFS ( P  = 0.041; HR = 9.15). Combined analysis showed that ΔSUVmax positive patients with high MTV formed a group with distinctly poor PFS (35.3%)., Conclusion: Baseline MTV and TLG values and optimal cutoff points achieved with different segmentation methods varied markedly and showed a limited prognostic impact. Interim PET/CT parameters provided more accurate prognostic information with semiquantitative 'Deauville-like' parameters performing best in the present study., (Copyright © 2023 The Author(s). Published by Wolters Kluwer Health, Inc.)

The scientific literature of coronavirus-disease 2019 (COVID-19) is rapidly expanding. There is a growing evidence on the discrepancy between clinical symptoms and radiologic findings in many patients. This case report gives details about a patient with only mild symptoms but relatively severe radiological findings. The 75-year-old patient suffering from oncologic disease had a planned a F18-fluoro-deoxy-glucose positron-emission tomography/computer tomography scan with a routine oncological indication where incidental radiomorphologic findings of pneumonia suspect for COVID-19 were detected. After immediate isolation, the patient was transferred to the corresponding medical department, where further investigations verified the diagnosis of COVID-19. With this case, our aim is to raise the awareness for the importance of the instant evaluation of chest computer tomography series when performing planned imaging examination, especially in frail patients. With this practice, potential radiomorphologic findings of pneumonia suspect for COVID-19 could be identified in time, which fundamentally determines further patient management steps. Orv Hetil. 2020; 161(23): 971-976.

Background: Left ventricular hypertrophy and diastolic dysfunction are common echocardiographic features of both aortic valve stenosis (AS) and cardiac amyloidosis (CA). These two different entities therefore may mask each other. From recent years, there is a growing body of evidence about the relatively high incidence of wild-type transthyretin (wtTTR) amyloidosis in AS, but there are scarce data on the prevalence of AS in CA, particularly in AL-type amyloidosis. The echocardiographic approach to these patients is not obvious, and not evidence based. We aimed to study the prevalence, severity, and type of AS in patients with CA and also to evaluate the potential of echocardiography in the diagnostic process., Methods: Between January 2009 and January 2019, we retrospectively analyzed the clinical and echocardiographic data, and the echocardiographic work up of 55 consecutive CA patients., Results: 80% of our CA patients had AL amyloidosis. We identified 5 patients (9%) with moderate to severe AS: two with moderate AS and three with low-flow, low-grade AS (LFLG AS). Further analysis of the latter three patients with dobutamine stress echocardiography revealed pseudo-severe LFLG AS in two, and true-severe AS in one patient., Conclusion: The prevalence of moderate to severe AS is 9% in our population of CA patients, the majority of whom have AL amyloidosis. Dobutamine echocardiography seems to be appropriate for the further characterization of patients with LFLG AS, even with normal ejection fraction.