Radiomics analysis of 18F-Choline PET/CT in the prediction of disease outcome in high-risk prostate cancer: an explorative study on machine learning feature classification in 94 patients.

OBJECTIVE: The aim of this study was (1) to investigate the application of texture analysis of choline PET/CT images in prostate cancer (PCa) patients and (2) to propose a machine-learning radiomics model able to select PET features predictive of disease progression in PCa patients with a same high-risk class at restaging. MATERIAL AND METHODS: Ninety-four high-risk PCa patients who underwent restaging Cho-PET/CT were analyzed. Follow-up data were recorded for a minimum of 13 months after the PET/CT scan. PET images were imported in LIFEx toolbox to extract 51 features from each lesion. A statistical system based on correlation matrix and point-biserial-correlation coefficient has been implemented for features reduction and selection, while Discriminant analysis (DA) was used as a method for features classification in a whole sample and sub-groups for primary tumor or local relapse (T), nodal disease (N), and metastatic disease (M). RESULTS: In the whole group, 2 feature (HISTO_Entropy_log10; HISTO_Energy_Uniformity) results were able to discriminate the occurrence of disease progression at follow-up, obtaining the best performance in DA classification (sensitivity 47.1%, specificity 76.5%, positive predictive value (PPV) 46.7%, and accuracy 67.6%). In the sub-group analysis, the best performance in DA classification for T was obtained by selecting 3 features (SUVmin; SHAPE_Sphericity; GLCM_Correlation) with a sensitivity of 91.6%, specificity 84.1%, PPV 79.1%, and accuracy 87%; for N by selecting 2 features (HISTO = _Energy Uniformity; GLZLM_SZLGE) with a sensitivity of 68.1%, specificity 91.4%, PPV 83%, and accuracy 82.6%; and for M by selecting 2 features (HISTO_Entropy_log10 - HISTO_Entropy_log2) with a sensitivity 64.4%, specificity 74.6%, PPV 40.6%, and accuracy 72.5%. CONCLUSION: This machine learning model demonstrated to be feasible and useful to select Cho-PET features for T, N, and M with valuable association with high-risk PCa patients' outcomes. KEY POINTS: • Artificial intelligence applications are feasible and useful to select Cho-PET features. • Our model demonstrated the presence of specific features for T, N, and M with valuable association with high-risk PCa patients' outcomes. • Further prospective studies are necessary to confirm our results and to develop the application of artificial intelligence in PET imaging of PCa.

Subcutaneous Uptake on [18F]Florbetaben PET/CT: a Case Report of Possible Amyloid-Beta Immune-Reactivity After COVID-19 Vaccination.

Introduction: Large-scale worldwide COVID-19 vaccination programs are being rapidly deployed, and high-risk patients with comorbidity are now receiving the first doses of the vaccine. Physicians should be, therefore, aware of new pitfalls associated with the current pandemic vaccination program, also in the case of [18F]Florbetaben PET/CT.Case PresentationWe described the first image of [18F]Florbetaben PET/CT in the evaluation of a 70-year-old male with suspicious Alzheimer disease and unclear history of heart disease. We detailed the diagnostic imaging PET/CT workup with different findings. Conclusion: In this case, [18F]Florbetaben PET/CT can demonstrate potential beta-amyloid immune-reactivity and deposition associated with the current COVID-19 pandemic vaccination programs.

Clinical and Prognostic Value of 18F-FDG-PET/CT in the Restaging Process of Recurrent Cutaneous Melanoma.

BACKGROUND: Several studies on 18F-FDG-PET/CT have investigated the prognostic role of this imaging modality in different tumors after treatment. Nevertheless, its role in restaging patients with recurrent CM still needs to be defined. OBJECTIVE: The aim of this retrospective multicenter study was to evaluate the clinical and prognostic impact of 18F-FDG-PET/CT on the restaging process of cutaneous melanoma (CM) after surgery in patients with suspected distant recurrent disease or suspected metastatic progression disease. MATERIALS AND METHODS: 74 patients surgically treated for CM underwent 18F-FDG-PET/CT for suspected distant recurrent disease or suspected metastatic progression disease. The diagnostic accuracy of visually interpreted 18F-FDG-PET/CT was obtained by considering histology (n=21 patients), other diagnostic imaging modalities performed within 2 months of PET/CT (CT in 52/74 patients and Whole-Body MRI in 18/74 patients) and clinical follow-up (n=74 patients) for at least 24 months containing all the clinical and diagnostic information useful for the PET performance assessment and outcome. Progression-free survival (PFS) and overall survival (OS) were assessed by using the Kaplan- Meier method. The risk of progression (Hazard Ratio-HR) was computed by the Cox regression analysis. RESULTS: Suspicion of recurrent CM was confirmed in 24/27 patients with a positive 18F-FDG-PET/CT scan. Overall, the sensitivity, specificity, positive predictive value, negative predictive value and accuracy of 18F-FDG-PET/CT were 82%, 93%, 88%, 89%, and 89%, respectively, with area under the curve being 0.87 (95%IC 0.78-0.97; p<0.05). 18F-FDG-PET/CT findings significantly influenced the therapeutic management in 18 patients (modifying therapy in 10 patients; guiding surgery in 8 patients). After 2 years of follow-up, PFS was significantly longer in patients with a negative vs. a positive 18F-FDG-PET/CT scan (90% vs 46%, p<0.05; Fig. 1). Moreover, a negative scan was associated with a significantly longer OS than a positive one (76% vs 39% after 2 years, p<0.05; Fig. 2). In addition, a positive 18F-FDG-PET/CT scan was associated with an increased risk of disease progression (HR=8.2; p<0,05). CONCLUSION: 18F-FDG-PET/CT showed a valuable diagnostic performance in patients with suspicion of recurrent CM. This imaging modality might have an important prognostic value in predicting the survival outcomes, assessing the risk of disease progression, and guiding treatment decision making.

Potential clinical value of quantitative fluorine-18-fluorodeoxyglucose-PET/computed tomography using a graph-based method analysis in evaluation of incidental lesions of gastrointestinal tract: correlation with endoscopic and histopathological findings.

OBJECTIVES: To identify the clinical relevance of incidentally detected lesions (IDLs) in the gastrointestinal tract (GIT) with 18F-FDG PET/CT and to assess the potential benefit of using semiquantitative PET measures to discern malignant from benign lesions. METHODS: Forty-one patients who underwent F-FDG PET/CT scans during the oncologic follow-up, revealing abnormal incidental 18F-FDG accumulations in the GIT were included in this retrospective analysis. Incidental PET/CT findings were correlated with endoscopic and histological findings. Semiquantitative PET values (SUVmax, SUVmean, SULpeak, and TLG) were evaluated by using a new graph-based method. Two sample t-test analysis has been performed to evaluate the differences of PET parameters between precancerous or cancerous lesions and inflammatory disease. RESULTS: Nine of the 41 patients had an IDL of the GIT on F-FDG PET/CT (detection rate 22%). Endoscopic examination and biopsy have confirmed the presence of precancerous or cancerous lesions as follow: colonic adenoma with high-grade dysplasia (N = 2), colonic adenoma with low-grade dysplasia (N =3), colonic metastatic lesion from primary breast cancer (N =1), gastric carcinoma (N=3). Precancerous or cancerous lesions showed a higher SUVmax, SUVmean, SULpeak, and TLG with a mean value of 10.6 (range, 5.3- 16.7), 6.2 (range, 2.1-10.6), 5.2 (2.7-11), and 66.6 (range, 7.4-164), than patients with inflammatory and endoscopically negative lesions. Two sample t-test analysis showed that SUVmean (P = 0.03), SULpeak (P = 0.05) were statistically different between the two subgroups. CONCLUSION: The use of new semiquantitative PET parameters may increase the diagnostic yield of FDG PET in the case of abnormal incidental F-FDG accumulations.

18F-Florbetaben PET/CT to Assess Alzheimer's Disease: A new Analysis Method for Regional Amyloid Quantification.

BACKGROUND AND PURPOSE: While AD can be definitively confirmed by postmortem histopathologic examination, in vivo imaging may improve the clinician's ability to identify AD at the earliest stage. The aim of the study was to test the performance of amyloid PET using new processing imaging algorithm for more precise diagnosis of AD. METHODS: Amyloid PET results using a new processing imaging algorithm (MRI-Less and AAL Atlas) were correlated with clinical, cognitive status, CSF analysis, and other imaging. The regional SUVR using the white matter of cerebellum as reference region and scores from clinical and cognitive tests were used to create ROC curves. Leave-one-out cross-validation was carried out to validate the results. RESULTS: Forty-four consecutive patients with clinical evidence of dementia, were retrospectively evaluated. Amyloid PET scan was positive in 26/44 patients with dementia. After integration with 18F-FDG PET, clinical data and CSF protein levels, 22 of them were classified as AD, the remaining 4 as vascular or frontotemporal dementia. Amyloid and FDG PET, CDR 1, CSF Tau, and p-tau levels showed the best true positive and true negative rates (amyloid PET: AUC = .85, sensitivity .91, specificity .79). A SUVR value of 1.006 in the inferior frontal cortex and of 1.03 in the precuneus region was the best cutoff SUVR value and showed a good correlation with the diagnosis of AD. Thirteen of 44 amyloid PET positive patients have been enrolled in clinical trials using antiamyloid approaches. CONCLUSIONS: Amyloid PET using SPM-normalized SUVR analysis showed high predictive power for the differential diagnosis of AD.

Prognostic and diagnostic value of [18F]FDG-PET/CT in restaging patients with small cell lung carcinoma: an Italian multicenter study.

BACKGROUND: The presence of residual disease after initial treatment in small cell lung cancer (SCLC) influences prognosis and impacts patient management. To date, few data exist on the value of fluorine-18-fluorodeoxyglucose ([F]FDG)-PET/computed tomography (CT) in SCLC at restaging. Therefore, in restaging patients with SCLC, we aimed to (a) evaluate the prognostic value yielded by [F]FDG-PET/CT and (b) assess the diagnostic agreement between [F]FDG-PET/CT and contrast-enhanced computed tomography (ceCT). PATIENTS AND METHODS: From a multicenter database, we evaluated 164 patients with SCLC who underwent [F]FDG-PET/CT for restaging purposes. PET scans were evaluated visually to identify the presence of recurrence. For each patient, the maximum and the mean standardized uptake value (SUVmax and SUVmean, respectively), metabolic tumor volume, and total lesion glycolysis were calculated, taking into account the lesion with the highest [F]FDG uptake (namely, the index lesion) in the local recurrences, lymph node involvement, and distant metastasis categories. Kaplan-Meier curves were computed to assess the effects of [F]FDG-PET/CT findings on overall survival (OS) and progression-free survival. Furthermore, the agreement between PET/CT and ceCT in detecting metastases was evaluated in 119 patients on a patient-based analysis (Cohen's κ; P < 0.05). RESULTS: The presence of metastatic lesions at [F]FDG-PET/CT was associated with a significantly shorter OS (P = 0.039) and progression-free survival (P < 0.001). Higher SUVmax showed a trend toward a shorter OS (P = 0.065). The K-agreement between ceCT and PET/CT in recurrent SCLC was 0.37 (P < 0.001). PET/CT and ceCT showed the same number of lesions in 52 (43.7%) patients, whereas PET/CT detected additional lesions in 35 (29.4%) patients. CONCLUSION: Detection of metastatic lesions at restaging by [F]FDG-PET/CT can predict a higher rate of progression and negatively influence OS in patients with SCLC. [F]FDG-PET/CT and ceCT seem to be complementary imaging modalities in patients with metastatic SCLC.

Clinical and prognostic value of 18F-FDG-PET/CT in restaging of pancreatic cancer.

AIM: The aim of this retrospective multicentre study was to evaluate the clinical and prognostic effect of fluorine-18-fluorodeoxyglucose (F-FDG)-PET/computed tomography (CT) in the restaging process of pancreatic cancer (PC). MATERIALS AND METHODS: Data from patients treated for primary PC, who underwent F-FDG-PET/CT for suspicious of disease progression, were collected. Accuracy was assessed employing conventional diagnostic procedures, multidisciplinary team case notes, further F-FDG-PET/CT scans and/or follow-up. Receiver operating characteristic curve and likelihood ratio (LR+/-) analyses were used for completion of accuracy definition. Progression-free survival (PFS) and overall survival were assessed by using Kaplan-Meier method. The Cox proportional hazards model was used to identify predictors of outcome. RESULTS: Fifty-two patients (33 males and 19 females, with mean age of 59 years and range: 42-78 years) with PC were finally included in our study. Sensitivity, specificity, positive predictive value, negative predictive value, and accuracy of F-FDG-PET were 85, 84, 90, 76, and 84%, respectively. Area under the curve was 0.84 (95% confidence intervals: 0.72-0.96; P<0.05). LR+ and LR- were 5.3 and 0.17, respectively. F-FDG-PET/CT revealed new metastatic foci in 5/52 patients (10%) and excluded suspicious lesions in 11/52 (21%). Analysis of PFS revealed F-FDG-PET/CT positivity to be associated with a worse cumulative survival rate over a 6 and 12-month period in comparison with F-FDG-PET/CT negativity (6-month PFS 95 vs. 67%, P<0.05; 12-month PFS 81 vs. 29%, P<0.05). A negative F-FDG-PET/CT result was associated with a significantly longer overall survival than a positive one (70 vs. 26% after 2 years, P<0.05). In addition, a positive F-FDG-PET/CT scan result and an maximum standardized uptake value (SUVmax) value more than 6 were significantly associated with an increased risk of disease progression (PET positivity hazard ratio=3.9, P=0.01; SUVmax>6 h=4.2, P=0.02) and death (PET positivity hazard ratio=3.5, P=0.02; SUVmax>6 h=3.7, P=0.01). CONCLUSION: F-FDG-PET/CT showed high diagnostic accuracy for restaging process of PC, proving also its potential value in predicting clinical outcome after primary treatment.