Machine learning approach using 18F-FDG-PET-radiomic features and the visibility of right ventricle 18F-FDG uptake for predicting clinical events in patients with cardiac sarcoidosis.

OBJECTIVES: To investigate the usefulness of machine learning (ML) models using pretreatment 18F-FDG-PET-based radiomic features for predicting adverse clinical events (ACEs) in patients with cardiac sarcoidosis (CS). MATERIALS AND METHODS: This retrospective study included 47 patients with CS who underwent 18F-FDG-PET/CT scan before treatment. The lesions were assigned to the training (n = 38) and testing (n = 9) cohorts. In total, 49 18F-FDG-PET-based radiomic features and the visibility of right ventricle 18F-FDG uptake were used to predict ACEs using seven different ML algorithms (namely, decision tree, random forest [RF], neural network, k-nearest neighbors, Naïve Bayes, logistic regression, and support vector machine [SVM]) with tenfold cross-validation and the synthetic minority over-sampling technique. The ML models were constructed using the top four features ranked by the decrease in Gini impurity. The AUCs and accuracies were used to compare predictive performances. RESULTS: Patients who developed ACEs presented with a significantly higher surface area and gray level run length matrix run length non-uniformity (GLRLM_RLNU), and lower neighborhood gray-tone difference matrix_coarseness and sphericity than those without ACEs (each, p < 0.05). In the training cohort, all seven ML algorithms had a good classification performance with AUC values of > 0.80 (range: 0.841-0.944). In the testing cohort, the RF algorithm had the highest AUC and accuracy (88.9% [8/9]) with a similar classification performance between training and testing cohorts (AUC: 0.945 vs 0.889). GLRLM_RLNU was the most important feature of the modeling process of this RF algorithm. CONCLUSION: ML analyses using 18F-FDG-PET-based radiomic features may be useful for predicting ACEs in patients with CS.

Clinical application of 18F-fluorodeoxyglucose positron emission tomography/computed tomography radiomics-based machine learning analyses in the field of oncology.

Machine learning (ML) analyses using 18F-fluorodeoxyglucose (18F-FDG) positron emission tomography (PET)/computed tomography (CT) radiomics features have been applied in the field of oncology. The current review aimed to summarize the current clinical articles about 18F-FDG PET/CT radiomics-based ML analyses to solve issues in classifying or constructing prediction models for several types of tumors. In these studies, lung and mediastinal tumors were the most commonly evaluated lesions, followed by lymphatic, abdominal, head and neck, breast, gynecological, and other types of tumors. Previous studies have commonly shown that 18F-FDG PET radiomics-based ML analysis has good performance in differentiating benign from malignant tumors, predicting tumor characteristics and stage, therapeutic response, and prognosis by examining significant differences in the area under the receiver operating characteristic curves, accuracies, or concordance indices (> 0.70). However, these studies have reported several ML algorithms. Moreover, different ML models have been applied for the same purpose. Thus, various procedures were used in 18F-FDG PET/CT radiomics-based ML analysis in oncology, and 18F-FDG PET/CT radiomics-based ML models, which are easy and universally applied in clinical practice, would be expected to be established.

The usefulness of machine-learning-based evaluation of clinical and pretreatment 18F-FDG-PET/CT radiomic features for predicting prognosis in patients with laryngeal cancer.

OBJECTIVE: To examine whether machine learning (ML) analyses involving clinical and 18F-FDG-PET-based radiomic features are helpful in predicting prognosis in patients with laryngeal cancer. METHODS: This retrospective study included 49 patients with laryngeal cancer who underwent18F-FDG-PET/CT before treatment, and these patients were divided into the training (n = 34) and testing (n = 15) cohorts.Seven clinical (age, sex, tumor size, T stage, N stage, Union for International Cancer Control stage, and treatment) and 40 18F-FDG-PET-based radiomic features were used to predict disease progression and survival. Six ML algorithms (random forest, neural network, k-nearest neighbors, naïve Bayes, logistic regression, and support vector machine) were used for predicting disease progression. Two ML algorithms (cox proportional hazard and random survival forest [RSF] model) considering for time-to-event outcomes were used to assess progression-free survival (PFS), and prediction performance was assessed by the concordance index (C-index). RESULTS: Tumor size, T stage, N stage, GLZLM_ZLNU, and GLCM_Entropy were the five most important features for predicting disease progression.In both cohorts, the naïve Bayes model constructed by these five features was the best performing classifier (training: AUC = 0.805; testing: AUC = 0.842). The RSF model using the five features (tumor size, GLZLM_ZLNU, GLCM_Entropy, GLRLM_LRHGE and GLRLM_SRHGE) exhibited the highest performance in predicting PFS (training: C-index = 0.840; testing: C-index = 0.808). CONCLUSION: ML analyses involving clinical and 18F-FDG-PET-based radiomic features may help predict disease progression and survival in patients with laryngeal cancer. ADVANCES IN KNOWLEDGE: ML approach using clinical and 18F-FDG-PET-based radiomic features has the potential to predict prognosis of laryngeal cancer.

Application of Machine Learning Analyses Using Clinical and [18F]-FDG-PET/CT Radiomic Characteristics to Predict Recurrence in Patients with Breast Cancer.

PURPOSE: To develop and identify machine learning (ML) models using pretreatment clinical and 2-deoxy-2-[18F]fluoro-D-glucose positron emission tomography ([18F]-FDG-PET)-based radiomic characteristics to predict disease recurrences in patients with breast cancers who underwent surgery. PROCEDURES: This retrospective study included 112 patients with 118 breast cancer lesions who underwent [18F]-FDG-PET/ X-ray computed tomography (CT) preoperatively, and these lesions were assigned to training (n=95) and testing (n=23) cohorts. A total of 12 clinical and 40 [18F]-FDG-PET-based radiomic characteristics were used to predict recurrences using 7 different ML algorithms, namely, decision tree, random forest (RF), neural network, k-nearest neighbors, naive Bayes, logistic regression, and support vector machine (SVM) with a 10-fold cross-validation and synthetic minority over-sampling technique. Three different ML models were created using clinical characteristics (clinical ML models), radiomic characteristics (radiomic ML models), and both clinical and radiomic characteristics (combined ML models). Each ML model was constructed using the top ten characteristics ranked by the decrease in Gini impurity. The areas under ROC curves (AUCs) and accuracies were used to compare predictive performances. RESULTS: In training cohorts, all 7 ML algorithms except for logistic regression algorithm in the radiomics ML model (AUC = 0.760) achieved AUC values of >0.80 for predicting recurrences with clinical (range, 0.892-0.999), radiomic (range, 0.809-0.984), and combined (range, 0.897-0.999) ML models. In testing cohorts, the RF algorithm of combined ML model achieved the highest AUC and accuracy (95.7% (22/23)) with similar classification performance between training and testing cohorts (AUC: training cohort, 0.999; testing cohort, 0.992). The important characteristics for modeling process of this RF algorithm were radiomic GLZLM_ZLNU and AJCC stage. CONCLUSIONS: ML analyses using both clinical and [18F]-FDG-PET-based radiomic characteristics may be useful for predicting recurrence in patients with breast cancers who underwent surgery.

The Usefulness of Machine Learning-Based Evaluation of Clinical and Pretreatment [18F]-FDG-PET/CT Radiomic Features for Predicting Prognosis in Hypopharyngeal Cancer.

PURPOSE: To examine whether the machine learning (ML) analyses using clinical and pretreatment 2-deoxy-2-[18F]fluoro-D-glucose positron emission tomography ([18F]-FDG-PET)-based radiomic features were useful for predicting prognosis in patients with hypopharyngeal cancer. PROCEDURES: This retrospective study included 100 patients with hypopharyngeal cancer who underwent [18F]-FDG-PET/X-ray computed tomography (CT) before treatment, and these patients were allocated to the training (n=80) and validation (n=20) cohorts. Eight clinical (age, sex, histology, T stage, N stage, M stage, UICC stage, and treatment) and 40 [18F]-FDG-PET-based radiomic features were used to predict disease progression. A feature reduction procedure based on the decrease of the Gini impurity was applied. Six ML algorithms (random forest, neural network, k-nearest neighbors, naïve Bayes, logistic regression, and support vector machine) were compared using the area under the receiver operating characteristic curve (AUC). Progression-free survival (PFS) was assessed using Cox regression analysis. RESULTS: The five most important features for predicting disease progression were UICC stage, N stage, gray level co-occurrence matrix entropy (GLCM_Entropy), gray level run length matrix run length non-uniformity (GLRLM_RLNU), and T stage. Patients who experienced disease progression displayed significantly higher UICC stage, N stage, GLCM_Entropy, GLRLM_RLNU, and T stage than those without progression (each, p<0.001). In both cohorts, the logistic regression model constructed by these 5 features was the best performing classifier (training: AUC=0.860, accuracy=0.800; validation: AUC=0.803, accuracy=0.700). In the logistic regression model, 5-year PFS was significantly higher in patients with predicted non-progression than those with predicted progression (75.8% vs. 8.3%, p<0.001), and this model was only the independent factor for PFS in multivariate analysis (hazard ratio = 3.22; 95% confidence interval = 1.03-10.11; p=0.045). CONCLUSIONS: The logistic regression model constructed by UICC, T and N stages and pretreatment [18F]-FDG-PET-based radiomic features, GLCM_Entropy, and GLRLM_RLNU may be the most important predictor of prognosis in patients with hypopharyngeal cancer.

Application of 123I-MIBG myocardial maximum standardized uptake value to characterize cardiac function in patients with pheochromocytoma: comparison with echocardiography.

PURPOSE: This study examined the usefulness of the maximum standardized uptake value (SUVmax) of myocardial [123I]-metaiodobenzylguanidine ([123I]-MIBG) to characterize myocardial function by comparing it with echocardiographic parameters in patients with pheochromocytoma. MATERIALS AND METHODS: This study included 18 patients with pheochromocytoma who underwent both planar and [123I]-MIBG single-photon emission computed tomography/computed tomography scans and echocardiography before surgery. Myocardial [123I]-MIBG visibility and SUVmax were compared with echocardiographic parameters related to systolic and diastolic functions. The Mann-Whitney U test, Fisher exact test, or Spearman rank correlation assessed differences or relationships between two quantitative variables. RESULTS: On visual analysis, 6 patients showed normal myocardial [123I]-MIBG uptake, whereas 12 patients showed decreased myocardial [123I]-MIBG uptake. No patients showed systolic dysfunction. A significant difference was observed in the incidence of diastolic dysfunction between the groups with normal and decreased uptake (p = 0.009), and left ventricular (LV) diastolic dysfunction was observed in 9 (75%) of 12 patients with decreased myocardial uptake. The myocardial SUVmax was significantly lower in 9 patients with LV diastolic dysfunction than in 9 patients with normal cardiac function (1.67 ± 0.37 vs. 3.03 ± 1.38, p = 0.047). Myocardial SUVmax was positively correlated with septal e' (early diastolic velocity of septal mitral annulus) (ρ = 0.51, p = 0.031) and negatively correlated with the septal E/e' ratio (early mitral E-velocity to early diastolic velocity of septal mitral annulus; ρ = - 0.64, p = 0.004), respectively. CONCLUSIONS: LV diastolic dysfunction was inversely related to myocardial [123I]-MIBG uptake. Myocardial [123I]-MIBG SUVmax may be useful for characterizing cardiac function in patients with pheochromocytoma. Second abstract. The semiquantitative analysis using the myocardial SUVmax in 123I-MIBG SPECT/CT was found to be potentially useful for characterizing cardiac function in patients with pheochromocytoma.

I-131 false-positive uptake in a thymic cyst with expression of the sodium-iodide symporter: A case report.

RATIONALE: I-131 radioiodine false-positive findings in postoperative patients with differentiated thyroid cancer (DTC) should be recognized to avoid unnecessary therapies. PATIENT CONCERNS AND DIAGNOSES: A 50-year-old man underwent I-131 therapy 3 times, including the initial ablative therapy after total thyroidectomy for papillary thyroid cancer. The initial I-131 posttherapeutic whole-body scintigraphy showed 2 cervical and one superior mediastinal focal I-131 positive uptake lesions. The serum thyroglobulin level was negative every time when the radioiodine therapy was performed. Although the 2 cervical positive uptake lesions disappeared after the second therapy, the superior mediastinal I-131 positive uptake persisted even after the third therapy, and this lesion was suspicion of I-131 therapy-resistant node metastasis. INTERVENTIONS AND OUTCOMES: The lesion was resected, and the pathological diagnosis with immune-histochemical analysis was a thymic cyst with thymic epithelial cells having a weak expression of the sodium-iodide symporter (NIS). LESSONS: The false-positive result may be attributed to the NIS expression in the thymic cyst epithelial cells. It is necessary to include a thymic cyst in the differential diagnosis, when I-131 uptake is noted in the superior mediastinal region on I-131 posttherapeutic scans of patients with postoperative DTC. Although the I-131 positive uptake in a thymic cyst may be influenced by the I-131 administered dose and scan timing after I-131 administration, the NIS expression may be essential to the false-positive uptake in a thymic cyst.

The efficacy of 18F-FDG-PET-based radiomic and deep-learning features using a machine-learning approach to predict the pathological risk subtypes of thymic epithelial tumors.

OBJECTIVE: To examine whether the machine-learning approach using 18-fludeoxyglucose positron emission tomography (18F-FDG-PET)-based radiomic and deep-learning features is useful for predicting the pathological risk subtypes of thymic epithelial tumors (TETs). METHODS: This retrospective study included 79 TET [27 low-risk thymomas (types A, AB and B1), 31 high-risk thymomas (types B2 and B3) and 21 thymic carcinomas] patients who underwent pre-therapeutic 18F-FDG-PET/CT. High-risk TETs (high-risk thymomas and thymic carcinomas) were 52 patients. The 107 PET-based radiomic features, including SUV-related parameters [maximum SUV (SUVmax), metabolic tumor volume (MTV), and total lesion glycolysis (TLG)] and 1024 deep-learning features extracted from the convolutional neural network were used to predict the pathological risk subtypes of TETs using six different machine-learning algorithms. The area under the curves (AUCs) were calculated to compare the predictive performances. RESULTS: SUV-related parameters yielded the following AUCs for predicting thymic carcinomas: SUVmax 0.713, MTV 0.442, and TLG 0.479 or high-risk TETs: SUVmax 0.673, MTV 0.533, and TLG 0.539. The best-performing algorithm was the logistic regression model for predicting thymic carcinomas (AUC 0.900, accuracy 81.0%), and the random forest (RF) model for high-risk TETs (AUC 0.744, accuracy 72.2%). The AUC was significantly higher in the logistic regression model than three SUV-related parameters for predicting thymic carcinomas, and in the RF model than MTV and TLG for predicting high-risk TETs (each; p < 0.05). CONCLUSION: 18F-FDG-PET-based radiomic analysis using a machine-learning approach may be useful for predicting the pathological risk subtypes of TETs. ADVANCES IN KNOWLEDGE: Machine-learning approach using 18F-FDG-PET-based radiomic features has the potential to predict the pathological risk subtypes of TETs.

Dual-Energy CT-Derived Electron Density for Diagnosing Metastatic Mediastinal Lymph Nodes in Non-Small Cell Lung Cancer: Comparison With Conventional CT and FDG PET/CT Findings.

BACKGROUND. Accurate nodal staging is essential to guide treatment selection in patients with non-small cell lung cancer (NSCLC). To our knowledge, measurement of electron density (ED) using dual-energy CT (DECT) is unexplored for this purpose. OBJECTIVE. The purpose of our study was to assess the utility of ED from DECT in diagnosing metastatic mediastinal lymph nodes in patients with NSCLC in comparison with conventional CT and FDG PET/CT. METHODS. This retrospective study included 57 patients (36 men, 21 women; mean age, 68.4 ± 8.9 [SD] years) with NSCLC and surgically resected mediastinal lymph nodes who underwent preoperative DECT and FDG PET/CT. The patients had a total of 117 resected mediastinal lymph nodes (33 metastatic, 84 nonmetastatic). Two radiologists independently reviewed the morphologic features of nodes on the 120-kVp images and also measured the iodine concentration (IC) and ED of nodes using maps generated from DECT data; consensus was reached for discrepancies. Two different radiologists assessed FDG PET/CT examinations in consensus for positive node uptake. Diagnostic performance was evaluated for individual and pairwise combinations of features. RESULTS. The sensitivity, specificity, and accuracy for nodal metastasis were 15.2%, 98.8%, and 75.2% for the presence of necrosis, respectively; 54.5%, 85.7%, and 76.9% for short-axis diameter greater than 8.5 mm; 63.6%, 73.8%, and 70.9% for long-axis diameter greater than 13.0 mm; 51.5%, 79.8%, and 71.8% for attenuation on 120-kVp images of 95.8 HU or less; 87.9%, 58.3%, and 66.7% for ED of 3.48 × 1023/cm3 or less; and 66.7%, 75.0%, and 72.6% for positive FDG uptake. Among pairwise combinations of features, accuracy was highest for the combination of ED and short-axis diameter (accuracy, 82.9%; sensitivity, 54.5%; specificity, 94.0%) and the combination of ED and positive FDG uptake (accuracy, 82.1%; sensitivity, 60.6%; specificity, 90.5%); these accuracies were greater than those for the individual features (p < .05). The remaining combinations exhibited accuracies ranging from 74.4% to 77.8%. Interobserver agreement analysis showed an intraclass correlation coefficient of 0.90 for ED. IC was not significantly different between metastatic and nonmetastatic nodes (p = .18) and was excluded from the diagnostic performance analysis. CONCLUSION. ED derived from DECT may help diagnose metastatic lymph nodes in NSCLC given decreased ED in metastatic nodes. CLINICAL IMPACT. ED may complement conventional CT findings and FDG uptake on PET/CT in diagnosing metastatic nodes.

An open-label, single-arm, multi-center, phase II clinical trial of single-dose [131I]meta-iodobenzylguanidine therapy for patients with refractory pheochromocytoma and paraganglioma.

OBJECTIVE: In this phase II study, we aimed to investigate the efficacy and safety of single-dose [131I]meta-iodobenzylguanidine (131I-mIBG) therapy in patients with refractory pheochromocytoma and paraganglioma (PPGL). PATIENTS AND METHODS: This study was designed as an open-label, single-arm, multi-center, phase II clinical trial. The enrolled patients were administered 7.4 GBq of 131I-mIBG. Its efficacy was evaluated 12 and 24 weeks later, and its safety was monitored continuously until the end of the study. We evaluated the biochemical response rate as the primary endpoint using the one-sided exact binomial test based on the null hypothesis (≤ 5%). RESULTS: Seventeen patients were enrolled in this study, of which 16 were treated. The biochemical response rate (≥ 50% decrease in urinary catecholamines) was 23.5% (90% confidence interval: 8.5-46.1%, p = 0.009). The radiographic response rates, determined with CT/MRI according to the response evaluation criteria in solid tumors (RECIST) version 1.1 and 123I-mIBG scintigraphy were 5.9% (0.3%-25.0%) and 29.4% (12.4%-52.2%), respectively. The most frequent non-hematologic treatment-emergent adverse events (TEAEs) were gastrointestinal symptoms including nausea, appetite loss, and constipation, which were, together, observed in 15 of 16 patients. Hematologic TEAEs up to grade 3 were observed in 14 of 16 patients. No grade 4 or higher TEAEs were observed. All patients had experienced at least one TEAE, but no fatal or irreversible TEAEs were observed. CONCLUSION: A single dose 131I-mIBG therapy was well tolerated by patients with PPGL, and statistically significantly reduced catecholamine levels compared to the threshold response rate, which may lead to an improved prognosis for these patients.

Machine learning based evaluation of clinical and pretreatment 18F-FDG-PET/CT radiomic features to predict prognosis of cervical cancer patients.

PURPOSE: To examine the usefulness of machine learning to predict prognosis in cervical cancer using clinical and radiomic features of 2-deoxy-2-[18F]fluoro-D-glucose (18F-FDG) positron emission tomography/computed tomography (CT) (18F-FDG-PET/CT). METHODS: This retrospective study included 50 cervical cancer patients who underwent 18F-FDG-PET/CT before treatment. Four clinical (age, histology, stage, and treatment) and 41 18F-FDG-PET-based radiomic features were ranked and a subset of useful features for association with disease progression was selected based on decrease of the Gini impurity. Six machine learning algorithms (random forest, neural network, k-nearest neighbors, naive Bayes, logistic regression, and support vector machine) were compared using the areas under the receiver operating characteristic curve (AUC). Progression-free survival (PFS) was assessed using Cox regression analysis. RESULTS: The five top predictors of disease progression were: stage, surface area, metabolic tumor volume, gray-level run length non-uniformity (GLRLM_RLNU), and gray-level non-uniformity for run (GLRLM_GLNU). The naive Bayes model was the best-performing classifier for predicting disease progression (AUC = 0.872, accuracy = 0.780, F1 score = 0.781, precision = 0.788, and recall = 0.780). In the naive Bayes model, 5-year PFS was significantly higher in predicted non-progression than predicted progression (80.1% vs. 9.1%, p < 0.001) and was only the independent factor for PFS in multivariate analysis (HR, 6.89; 95% CI, 1.92-24.69; p = 0.003). CONCLUSION: A machine learning approach based on clinical and pretreatment 18F-FDG PET-based radiomic features may be useful for predicting tumor progression in cervical cancer patients.

Clinical Utility and Limitation of Diagnostic Ability for Different Degrees of Dysplasia of Intraductal Papillary Mucinous Neoplasms of the Pancreas Using 18F-Fluorodeoxyglucose-Positron Emission Tomography/Computed Tomography.

The diagnostic value of 18F-fluorodeoxyglucose (FDG) uptake in the management of intraductal papillary mucinous neoplasms (IPMNs) of the pancreas remains unclear. This study aimed to assess the role of FDG uptake in the diagnosis of different degrees of dysplasia of IPMNs. We retrospectively analyzed the following three points in 84 patients with IPMNs: (1) risk factors to predict high-grade dysplasia (HGD) and invasive carcinoma (INV); (2) the relationship between FDG uptake and glucose transporter 1 (GLUT-1) expression; and (3) the relationship between FDG uptake and the presence of mural nodules. The histopathological diagnosis was low-grade dysplasia (LGD) in 43 patients, HGD in 16, and INV in 25. The maximum standardized uptake value (SUV-max) was significantly higher in INV than in LGD/HGD (p < 0.0001, p = 0.0136). The sensitivity and specificity to discriminate INV from LGD/HGD were 80.0% and 86.2%, respectively, using the receiver operator characteristic curve, when the optimal cutoff score of SUV-max was set at 4.03. Those values were not different between HGD and LGD. More than half of HGD patients had low GLUT-1 expression. Taken together, FDG-PET/CT is useful in distinguishing between non-invasive and invasive IPMN. Our results offer critical information that may determine surgical treatment strategies.

Application of a Machine Learning Approach for the Analysis of Clinical and Radiomic Features of Pretreatment [18F]-FDG PET/CT to Predict Prognosis of Patients with Endometrial Cancer.

PURPOSE: To examine the prognostic significance of pretreatment 2-deoxy-2-[18F]fluoro-D-glucose ([18F]-FDG) positron emission tomography (PET)-based radiomic features using a machine learning approach in patients with endometrial cancers. PROCEDURES: Included in this retrospective study were 53 patients with endometrial cancers who underwent [18F]-FDG PET/X-ray computed tomography (CT) before treatment. Since two different PET scanners were used, post-reconstruction harmonization was performed for all PET parameters using the ComBat harmonization method. Four clinical (age, histological type, stage, and treatment method) and 40 [18F]-FDG PET-based radiomic features were ranked, and a subset of useful features was selected based on the decrease in the Gini impurity in terms of associations with disease progression. The machine learning algorithms (random forest, neural network, k-nearest neighbors (kNN), naive Bayes, logistic regression, and support vector machine) were compared using the areas under the receiver operating characteristic curve (AUC) and validated by the random sampling method. Progression-free survival (PFS) and overall survival (OS) were assessed by the Cox regression analysis. RESULTS: The five best predictors of disease progression were coarseness, gray-level run length nonuniformity, stage, treatment method, and gray-level zone length nonuniformity. The kNN model obtained the best performance classifier for predicting the disease progression (AUC =0.890, accuracy =0.849, F1 score =0.848, precision =0.857, and recall =0.849). Coarseness which was the first ranked radiomic feature was selected for survival analyses, and only coarseness remained as a significant and independent factor for both PFS (hazard ratios (HR), 0.65; 95 % confidence interval [CI], 0.49-0.86; p=0.003) and OS (HR, 0.52; 95 % CI, 0.36-0.76; p<0.001) at multivariate Cox regression analysis. CONCLUSIONS: [18F]-FDG PET-based radiomic analysis using a machine learning approach may be useful for predicting tumor progression and prognosis in patients with endometrial cancers.

Application of a machine learning approach to characterization of liver function using 99mTc-GSA SPECT/CT.

PURPOSE: To assess the utility of a machine-learning approach for predicting liver function based on technetium-99 m-galactosyl serum albumin (99mTc-GSA) single photon emission computed tomography (SPECT)/CT. METHODS: One hundred twenty-eight patients underwent a 99mTc-GSA SPECT/CT-based liver function evaluation. All were classified into the low liver-damage or high liver-damage group. Four clinical (age, sex, background liver disease and histological type) and 8 quantitative 99mTc-GSA SPECT/CT features (receptor index [LHL15], clearance index [HH15], liver-SUVmax, liver-SUVmean, heart-SUVmax, metabolic volume of liver [MVL], total lesion GSA [TL-GSA, liver-SUVmean × MVL] and SUVmax ratio [liver-SUVmax/heart-SUVmax]) were obtained. To predict high liver damage, a machine learning classification with features selection based on Gini impurity and principal component analysis (PCA) were performed using a support vector machine and a random forest (RF) with a five-fold cross-validation scheme. To overcome imbalanced data, stratified sampling was used. The ability to predict high liver damage was evaluated using a receiver operating characteristic (ROC) curve analysis. RESULTS: Four indices (LHL15, HH15, heart SUVmax and SUVmax ratio) yielded high areas under the ROC curves (AUCs) for predicting high liver damage (range: 0.89-0.93). In a machine learning classification, the RF with selected features (heart SUVmax, SUVmax ratio, LHL15, HH15, and background liver disease) and PCA model yielded the best performance for predicting high liver damage (AUC = 0.956, sensitivity = 96.3%, specificity = 90.0%, accuracy = 91.4%). CONCLUSION: A machine-learning approach based on clinical and quantitative 99mTc-GSA SPECT/CT parameters might be useful for predicting liver function.

Case Report: 18F-FDG PET-CT for Diagnosing Prosthetic Device-Related Infection in an Infant With CHD.

Patients who have undergone cardiac surgery using prosthetic devices have an increased risk of developing prosthetic device-related infection and mediastinitis. However, accurate diagnosis of prosthetic device-related infection can be difficult to evaluate and treat with antibiotic therapy alone. In recent years, 18F-fluorodeoxyglucose positron emission tomography-computed tomography (18F-FDG PET-CT) has made promising contributions to detect infective endocarditis, pacemaker infections, or other inflammations. Nevertheless, 18F-FDG PET-CT for congenital heart disease (CHD) with device infection has been sparsely reported. We present an infantile girl diagnosed with pulmonary atresia with a ventricular septal defect who underwent replacement of the right ventricle-to-pulmonary artery (RV-PA) conduit for improvement cyanosis. She developed high fever and was diagnosed with mediastinitis and bacteremia by Pseudomonas aeruginosa (P. aeruginosa) on postoperative day 4. Mediastinal drainage and 6 weeks of antibiotic therapy improved her condition, but bacteremia flared up on postoperative day 56. Despite a long course of antibiotic therapy, she had two more recurrences of bacteremia with the detection of P. aeruginosa. Echocardiography and chest contrast CT showed no evidence of vegetation and mediastinitis. On postoperative day 115, 18F-FDG PET-CT revealed an accumulation on the RV-PA conduit (SUV max 3.4). Finally, she developed an infectious ventricular pseudo-aneurysm on postoperative day 129 and underwent aneurysm removal and RV-PA conduit replacement on postoperative day 136. Our case showed the importance of 18F-FDG PET-CT for diagnosing specific localization of prosthetic device-related infection which is hard to detect using other imaging techniques. It can be a useful diagnostic tool for infantile patients with CHD with cardiac prosthetic devices and improve subsequent clinical treatments.

Value of Patlak Ki images from 18F-FDG-PET/CT for evaluation of the relationships between disease activity and clinical events in cardiac sarcoidosis.

The association between 18F-fluorodeoxyglucose (18F-FDG) myocardial uptake and clinical presentations in cardiac sarcoidosis (CS) has not yet been clarified. The Patlak slope, Ki, which represents the rate of 18F-FDG uptake is a quantitative index of 18F-FDG metabolism. This study aims to investigate the usefulness of standardized uptake value (SUV) and Patlak Ki images (Ki images) extracted from dynamic 18F-FDG-PET/CT for evaluating the risk of clinical events (CEs) in CS. The SUV and Ki myocardial images were generated from 30 dynamic 18F-FDG-PET/CT scans of 21 CS patients. The SUV and Ki images both were rated as positive in 19 scans and negative in 11 scans with the same incidence of CEs which were significantly higher in positive than negative scans [cardiac dysfunction: 78.9% (15/19) vs. 27.2% (3/11); arrhythmic events: 65.5% (10/19) vs. 0% (0/11)]. In 19 positive scans, the three Ki parameters (Ki max, Ki mean and Ki volume) were significantly higher in scans for patients with arrhythmic events than in those without. Logistic regression analysis showed that the Ki volume alone was significantly associated with the risk of arrhythmic events. Our study suggests that Ki images may add value to SUV images for evaluating the risk of CEs in CS patients.

Application of adrenal maximum standardized uptake value to 131I-6ß-iodomethyl-19-norcholesterol SPECT/CT for characterizing unilateral hyperfunctioning adrenocortical masses.

PURPOSE: To evaluate the maximum standardized uptake value (SUVmax) by 131I-6ß-iodomethyl-19-norcholesterol (NP-59) single-photon emission computed tomography (SPECT)/computed tomography (CT) for characterizing unilateral hyperfunctioning adrenocortical masses. METHODS: Ten patients underwent NP-59 SPECT/CT to evaluate the following unilateral adrenocortical hyperfuncting masses: three with Cushing's syndrome (CS), three with subclinical CS, and four with primary aldosteronism (PA). Visual and quantitative or semiquantitative analyses (noncontrast CT HU [Hounsfield units], lesion SUVmax, contralateral SUVmax, and SUVmax ratio [lesion SUVmax/contralateral adrenal SUVmax]) were performed. The Mann-Whitney U test or Chi-squared test was used appropriately to assess differences between quantitative variables or compare categorical data. Diagnostic performance was evaluated by receiver operating characteristic (ROC) curve analysis. RESULTS: All adrenal tumors were diagnosed as cortical adenomas. On visual analysis, unilateral uptake was noted in three patients with CS and one patient with subclinical CS, whereas bilateral uptake was noted in four patients with PA and two patients with subclinical CS (p = 0.046). No significant difference was observed in CT HU (p = 0.055). The lesion SUVmax and SUVmax ratio were significantly higher and the contralateral SUVmax was significantly lower in six patients with CS than in four patients with PA (each, p < 0.05). The area under the ROC curve and accuracy for differentiating between CS and PA were, respectively, 0.92 and 90.0 % for the lesion SUVmax, 1.00 and 100 % for the contralateral SUVmax, and 0.92 and 90.0 % for the SUVmax ratio. CONCLUSIONS: Quantitative or semiquantitative analysis using the adrenal SUVmax in adrenocortical NP-59 SPECT/CT has potential for characterizing unilateral hyperfunctioning adrenocortical masses.

Correction to: [18F]-FDG-PET/CT and [18F]-FAZA-PET/CT Hypoxia Imaging of Metastatic Thyroid Cancer: Association with Short-Term Progression after Radioiodine Therapy.

This article was update to correct the spelling of Takashi Yoshiura's name; it is correct as displayed here.

[18F]-FDG-PET/CT and [18F]-FAZA-PET/CT Hypoxia Imaging of Metastatic Thyroid Cancer: Association with Short-Term Progression After Radioiodine Therapy.

PURPOSE: To examine the relationships between 2-deoxy-2-[18F]fluoro-D-glucose ([18F]-FDG) and hypoxia tracer [18F]fluoro-azomycinarabinofuranoside ([18F]-FAZA) and between 131I and [18F]-FAZA uptake in patients with metastatic thyroid cancer and to evaluate imaging features associated with short-term progression after 131I therapy. PROCEDURES: The study population was 20 patients (17 women and 3 men; mean age, 67 years) with metastatic thyroid cancer who underwent both [18F]-FDG- and [18F]-FAZA-positron emission tomography (PET)/X-ray computed tomography (CT) examinations before 131I therapy. Short-term response to radioiodine was assessed (mean follow-up, 19 months ± 9). PET parameters including [18F]-FDG-SUVmax, [18F]-FAZA-SUVmax, and [18F]-FAZA-tumor-to-muscle [T/M] were obtained. Mann-Whitney U, Wilcoxon signed-rank, or χ2 tests were used to assess differences between two quantitative variables or compare categorical data. Predictive factors for short-term progression were investigated with logistic regression analysis. RESULTS: Eleven lymph node metastatic lesions were identified in 9 patients and 46 distant metastatic lesions (lung, 19; bone, 17; and liver, 10) in 14 patients. A total of 24 131I-positive and 33 131I-negative lesions were detected. SUVmax was significantly lower with [18F]-FAZA-PET/CT (1.3 ± 0.6) than with [18F]-FDG-PET/CT (6.4 ± 5.9, p < 0.001). No significant correlation was observed between [18F]-FAZA-PET/CT and 131I imaging concerning visibility (p = 0.36). After 131I therapy, 31 of 57 metastatic lesions displayed short-term progression. Multivariate logistic regression revealed that [18F]-FDG-SUVmax (p = 0.022) and [18F]-FAZA-T/M (p = 0.002) showed significant associations with short-term progression. CONCLUSIONS: Although [18F]-FAZA uptake was low in metastatic thyroid cancers, not only glucose metabolism but also hypoxic conditions may be associated with progression after 131I therapy in patients with metastatic thyroid cancer.