Multiparametric approach with synthetic MR imaging for diagnosing salivary gland lesions.

PURPOSE: To determine whether synthetic MR imaging can distinguish between benign and malignant salivary gland lesions. METHODS: The study population included 44 patients with 33 benign and 11 malignant salivary gland lesions. All MR imaging was obtained using a 3 Tesla system. The QRAPMASTER pulse sequence was used to acquire images with four TI values and two TE values, from which quantitative images of T1 and T2 relaxation times and proton density (PD) were generated. The Mann-Whitney U test was used to compare T1, T2, PD, and ADC values among the subtypes of salivary gland lesions. ROC analysis was used to evaluate diagnostic capability between malignant tumors (MTs) and either pleomorphic adenomas (PAs) or Warthin tumors (WTs). We further calculated diagnostic accuracy for distinguishing malignant from benign lesions when combining these parameters. RESULTS: PAs demonstrated significantly higher T1, T2, PD, and ADC values than WTs (all p < 0.001). Compared to MTs, PAs had significantly higher T1, T2, and ADC values (all p < 0.001), whereas WTs had significantly lower T1, T2, and PD values (p < 0.001, p = 0.008, and p = 0.003, respectively). T2 and ADC were most effective in differentiating between MTs and PAs (AUC = 0.928 and 0.939, respectively), and T1 and PD values for differentiating between MTs and WTs (AUC = 0.915 and 0.833, respectively). Combining T1 with T2 or ADC achieved accuracy of 86.4% in distinguishing between malignant and benign tumors. Similarly, combining PD with T2 or ADC reached accuracy of 86.4% for differentiating between malignant and benign tumors. CONCLUSIONS: Utilizing a combination of synthetic MRI parameters may assist in differentiating malignant from benign salivary gland lesions.

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.

Differentiating primary central nervous system lymphoma from glioblastoma by time-dependent diffusion using oscillating gradient.

BACKGROUND: This study aimed to elucidate the impact of effective diffusion time setting on apparent diffusion coefficient (ADC)-based differentiation between primary central nervous system lymphomas (PCNSLs) and glioblastomas (GBMs) and to investigate the usage of time-dependent diffusion magnetic resonance imaging (MRI) parameters. METHODS: A retrospective study was conducted involving 21 patients with PCNSLs and 66 patients with GBMs using diffusion weighted imaging (DWI) sequences with oscillating gradient spin-echo (Δeff = 7.1 ms) and conventional pulsed gradient (Δeff = 44.5 ms). In addition to ADC maps at the two diffusion times (ADC7.1 ms and ADC44.5 ms), we generated maps of the ADC changes (cADC) and the relative ADC changes (rcADC) between the two diffusion times. Regions of interest were placed on enhancing regions and non-enhancing peritumoral regions. The mean and the fifth and 95th percentile values of each parameter were compared between PCNSLs and GBMs. The area under the receiver operating characteristic curve (AUC) values were used to compare the discriminating performances among the indices. RESULTS: In enhancing regions, the mean and fifth and 95th percentile values of ADC44.5 ms and ADC7.1 ms in PCNSLs were significantly lower than those in GBMs (p = 0.02 for 95th percentile of ADC44.5 ms, p = 0.04 for ADC7.1 ms, and p < 0.01 for others). Furthermore, the mean and fifth and 95th percentile values of cADC and rcADC were significantly higher in PCNSLs than in GBMs (each p < 0.01). The AUC of the best-performing index for ADC7.1 ms was significantly lower than that for ADC44.5 ms (p < 0.001). The mean rcADC showed the highest discriminating performance (AUC = 0.920) among all indices. In peritumoral regions, no significant difference in any of the three indices of ADC44.5 ms, ADC7.1 ms, cADC, and rcADC was observed between PCNSLs and GBMs. CONCLUSIONS: Effective diffusion time setting can have a crucial impact on the performance of ADC in differentiating between PCNSLs and GBMs. The time-dependent diffusion MRI parameters may be useful in the differentiation of these lesions.

Oscillating Gradient Diffusion-Weighted MRI for Risk Stratification of Uterine Endometrial Cancer.

BACKGROUND: Oscillating gradient diffusion-weighted imaging (DWI) enables elucidation of microstructural characteristics in cancers; however, there are limited data to evaluate its utility in patients with endometrial cancer. PURPOSE: To investigate the utility of oscillating gradient DWI for risk stratification in patients with uterine endometrial cancer compared with conventional pulsed gradient DWI. STUDY TYPE: Retrospective. SUBJECTS: Sixty-three women (mean age: 58 [range: 32-85] years) with endometrial cancer. FIELD STRENGTH/SEQUENCE: 3 T MRI including DWI using oscillating gradient spin-echo (OGSE) and pulsed gradient spin-echo (PGSE) research sequences. ASSESSMENT: Mean value of the apparent diffusion coefficient (ADC) values for OGSE (ADCOGSE ) and PGSE (ADCPGSE ) as well as the ADC ratio (ADCOGSE /ADCPGSE ) within endometrial cancer were measured using regions of interest. Prognostic factors (histological grade, deep myometrial invasion, lymphovascular invasion, International Federation of Gynecology and Obstetrics [FIGO] stage, and prognostic risk classification) were tabulated. STATISTICAL TESTS: Interobserver agreement was analyzed by calculating the intraclass correlation coefficient. The associations of ADCOGSE , ADCPGSE , and ADCOGSE /ADCPGSE with prognostic factors were examined using the Kendall rank correlation coefficient, Mann-Whitney U test, and receiver operating characteristic (ROC) curve. A P value of <0.05 was statistically significant. RESULTS: Compared with ADCOGSE and ADCPGSE , ADCOGSE /ADCPGSE was significantly and strongly correlated with histological grade (observer 1, τ = 0.563; observer 2, τ = 0.456), FIGO stage (observer 1, τ = 0.354; observer 2, τ = 0.324), and prognostic risk classification (observer 1, τ = 0.456; observer 2, τ = 0.385). The area under the ROC curves of ADCOGSE /ADCPGSE for histological grade (observer 1, 0.92, 95% confidence intervals [CIs]: 0.83-0.98; observer 2, 0.84, 95% CI: 0.73-0.92) and prognostic risk (observer 1, 0.80, 95% CI: 0.68-0.89; observer 2, 0.76, 95% CI: 0.63-0.86) were significantly higher than that of ADCOGSE and ADCPGSE . DATA CONCLUSION: The ADC ratio obtained via oscillating gradient and pulsed gradient DWIs might be useful imaging biomarkers for risk stratification in patients with endometrial cancer. LEVEL OF EVIDENCE: 3 TECHNICAL EFFICACY: Stage 2.

Alterations in EGFR and PDGFRA are associated with the localization of contrast-enhancing lesions in glioblastoma.

Background: Glioblastoma (GBM) is a malignant brain tumor, with radiological and genetic heterogeneity. We examined the association between radiological characteristics and driver gene alterations. Methods: We analyzed the driver genes of 124 patients with IDH wild-type GBM with contrast enhancement using magnetic resonance imaging. We used a next-generation sequencing panel to identify mutations in driver genes and matched them with radiological information. Contrast-enhancing lesion localization of GBMs was classified into 4 groups based on their relationship with the subventricular zone (SVZ) and cortex (Ctx). Results: The cohort included 69 men (55.6%) and 55 women (44.4%) with a mean age of 66.4 ±â€…13.3 years. EGFR and PDGFRA alterations were detected in 28.2% and 22.6% of the patients, respectively. Contrast-enhancing lesion touching both the SVZ and Ctx was excluded because it was difficult to determine whether it originated from the SVZ or Ctx. Contrast-enhancing lesions touching the SVZ but not the Ctx had significantly worse overall survival than non-SVZ lesions (441 days vs. 897 days, P = .002). GBM touching only the Ctx had a better prognosis (901 days vs. 473 days, P < .001) than non-Ctx lesions and was associated with EGFR alteration (39.4% vs. 13.2%, P = .015). Multiple contrast lesions were predominant in PDGFRA alteration and RB1-wild type (P = .036 and P = .031, respectively). Conclusions: EGFR alteration was associated with cortical lesions. And PDGFRA alteration correlated with multiple lesions. Our results suggest that clarifying the association between driver genes and tumor localization may be useful in clinical practice, including prognosis prediction.

Differentiating brain metastasis from glioblastoma by time-dependent diffusion MRI.

BACKGROUND: This study was designed to investigate the use of time-dependent diffusion magnetic resonance imaging (MRI) parameters in distinguishing between glioblastomas and brain metastases. METHODS: A retrospective study was conducted involving 65 patients with glioblastomas and 27 patients with metastases using a diffusion-weighted imaging sequence with oscillating gradient spin-echo (OGSE, 50 Hz) and a conventional pulsed gradient spin-echo (PGSE, 0 Hz) sequence. In addition to apparent diffusion coefficient (ADC) maps from two sequences (ADC50Hz and ADC0Hz), we generated maps of the ADC change (cADC): ADC50Hz - ADC0Hz and the relative ADC change (rcADC): (ADC50Hz - ADC0Hz)/ ADC0Hz × 100 (%). RESULTS: The mean and the fifth and 95th percentile values of each parameter in enhancing and peritumoral regions were compared between glioblastomas and metastases. The area under the receiver operating characteristic curve (AUC) values of the best discriminating indices were compared. In enhancing regions, none of the indices of ADC0Hz and ADC50Hz showed significant differences between metastases and glioblastomas. The mean cADC and rcADC values of metastases were significantly higher than those of glioblastomas (0.24 ± 0.12 × 10-3mm2/s vs. 0.14 ± 0.03 × 10-3mm2/s and 23.3 ± 9.4% vs. 14.0 ± 4.7%; all p < 0.01). In peritumoral regions, no significant difference in all ADC indices was observed between metastases and glioblastomas. The AUC values for the mean cADC (0.877) and rcADC (0.819) values in enhancing regions were significantly higher than those for ADC0Hz5th (0.595; all p < 0.001). CONCLUSIONS: The time-dependent diffusion MRI parameters may be useful for differentiating brain metastases from glioblastomas.

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.

A case of glioblastoma harboring non-amplified epidermal growth factor receptor variant III: Critical molecular detection using RNA-based panel analysis.

Amplification of the epidermal growth factor receptor gene (EGFR) and its variants are the most commonly detected pathogenic gene alterations in glioblastoma. Herein, we report a case of molecularly defined glioblastoma harboring an EGFR variant III (EGFRvIII) without EGFR amplification. The initial histological diagnosis was isocitrate dehydrogenase (IDH)-wildtype low-grade glioma, due to an absence of anaplasia, necrosis, and microvascular proliferation, and a low Ki-67 labeling index. DNA-based next-generation sequencing (NGS) panel analysis revealed a TERTp promoter mutation but no EGFR mutation or amplification, supporting the diagnosis of "molecular glioblastoma." However, RNA-based NGS panel analysis revealed mRNA expression of EGFRvIII. Therefore, the final integrative diagnosis was glioblastoma with non-amplified EGFRvIII. Our report suggests that non-amplified EGFRvIII might be an early molecular event in glioblastoma tumorigenesis. In addition to the usual DNA-based analysis, RNA-based analysis is required to identify exon-skipping EGFR variants without EGFR amplification.

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.

Extracellular volume fraction derived from equilibrium contrast-enhanced CT as a diagnostic parameter in anterior mediastinal tumors.

PURPOSE: To assess the usefulness of extracellular volume (ECV) fraction derived from equilibrium contrast-enhanced CT (CECT) for diagnosing anterior mediastinal tumors. METHOD: This study included 161 histologically confirmed anterior mediastinal tumors (55 low-risk thymomas, 57 high-risk thymomas, 32 thymic carcinomas, and 17 malignant lymphomas) that were assessed by pretreatment CECT. ECV fraction was calculated using measurements obtained within the lesion and the aorta on unenhanced and equilibrium phase CECT. ECV fraction was compared among anterior mediastinal tumors using one-way ANOVA or t-test. Receiver-operating characteristic (ROC) curve analysis was performed to evaluate the ability of ECV fraction to differentiate thymic carcinomas/lymphomas from thymomas. RESULTS: ECV fraction differed significantly among the anterior mediastinal tumors (p < 0.001). ECV fraction of thymic carcinomas was significantly higher than those of low-risk thymomas, high-risk thymomas, and lymphomas (p < 0.001, p < 0.001, and p = 0.006, respectively). ECV fraction of lymphomas was significantly higher than that of low-risk thymomas (p < 0.001). ECV fraction was significantly higher in thymic carcinomas/lymphomas than in thymomas (40.1 % vs. 27.7 %, p < 0.001). The optimal cutoff value to differentiate thymic carcinomas/lymphomas from thymomas was 38.5 % (AUC, 0.805; 95 %CI, 0.736-0.863). CONCLUSIONS: ECV fraction derived from equilibrium CECT is helpful in diagnosing anterior mediastinal tumors. High ECV fraction is indicative of thymic carcinomas/lymphomas, particularly thymic carcinomas.

Cine MR feature tracking analysis for diagnosing thymic epithelial tumors: a feasibility study.

BACKGROUND: To assess the feasibility of the cine MR feature tracking technique for the evaluation of cardiovascular-induced morphological deformation in the diagnosis of thymic epithelial tumors (TETs). METHODS: Our study population consisted of 43 patients with pathologically proven TETs including 10 low-grade thymomas, 23 high-grade thymomas, and 10 thymic carcinomas. Cine MR images were acquired using a balanced steady-state free precession sequence with short periods of breath-hold in the axial and oblique planes in the slice with the largest lesion cross-sectional area. The tumor margin was manually delineated in the diastolic phase and was automatically tracked for all other cardiac phases. The change rates of the long-to-short diameter ratio (∆LSR) and tumor area (∆area) associated with pulsation were compared between the three pathological groups using the Kruskal-Wallis H test and the Mann-Whitney U test. A receiver-operating characteristic (ROC) curve analysis was performed to assess the ability of each parameter to differentiate thymic carcinomas from thymomas. RESULTS: ∆LSR and ∆area were significantly different among the three groups in the axial plane (p = 0.028 and 0.006, respectively) and in the oblique plane (p = 0.034 and 0.043, respectively). ∆LSR and ∆area values were significantly lower in thymic carcinomas than in thymomas in the axial plane (for both, p = 0.012) and in the oblique plane (p = 0.015 and 0.011, respectively). The area under the ROC curves for ∆LSR and ∆area for the diagnosis of thymic carcinoma ranged from 0.755 to 0.764. CONCLUSIONS: Evaluation of morphological deformation using cine-MR feature tracking analysis can help diagnose histopathological subtypes of TETs and identify thymic carcinomas preoperatively.

Left atrial CT volume and CHA2DS2-VASc score predict early pulmonary vein stump thrombus after left upper lobectomy.

The purpose of this study is to clarify the feasibility of left atrial (LA) volume measurement and CHA2DS2-VASc score for predicting the development of pulmonary vein (PV) stump thrombus after left upper lobectomy (LUL). The study population comprised 50 patients who underwent LUL for pulmonary lesions. All patients were evaluated for the development of PV stump thrombus at 7 days after LUL. LA volume was measured using preoperative CT and the CHA2DS2-VASc score was evaluated. LA volume and CHA2DS2-VASc score were compared between patients with and without the development of PV stump thrombus using the Mann-Whitney U test. Receiver-operating characteristic (ROC) curve analysis was performed to evaluate the accuracy of prediction of PV stump thrombus development. PV stump thrombus was detected in 17 (33.4%) of the 50 patients. LA volume was significantly greater in patients who developed PV stump thrombus than in those without thrombus (79.7 ± 19.4 vs. 66.6 ± 17.0 mL, p = 0.040). CHA2DS2-VASc score was significantly higher in patients with PV stump thrombosis than in those without thrombus (3.4 ± 1.5 vs. 2.5 ± 1.5, p = 0.039). Area under the ROC curve values for predicting PV stump thrombus were 0.679, 0.676, and 0.714 for LA volume, CHA2DS2-VASc score, and their combination, respectively. In conclusion, LA volume measured using preoperative CT and CHA2DS2-VASc score may help predict the development of PV stump thrombus after LUL.

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.

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.

Feasibility of iodine concentration and extracellular volume fraction measurement derived from the equilibrium phase dual-energy CT for differentiating thymic epithelial tumors.

PURPOSE: To assess the diagnostic feasibility of iodine concentration (IC) and extracellular volume (ECV) fraction measurement using the equilibrium phase dual-energy CT (DECT) for the evaluation of thymic epithelial tumors (TETs). MATERIALS AND METHODS: This study included 33 TETs (11 low-risk thymomas, 11 high-risk thymomas, and 11 thymic carcinomas) that were assessed by pretreatment DECT. IC was measured during the equilibrium phases and ECV fraction was calculated using IC of the thymic lesion and the aorta. IC and ECV fraction were compared among TET subtypes using the Kruskal-Wallis H test and Mann-Whitney U test. Receiver-operating characteristic (ROC) curve analysis was performed to evaluate the ability of IC and ECV fraction to diagnose thymic carcinoma. RESULTS: IC during the equilibrium phase and ECV fraction differed among the three TET groups (both p < 0.001). IC during the equilibrium phase and ECV fraction was significantly higher in thymic carcinomas than in thymomas (1.9 mg/mL vs. 1.2 mg/mL, p < 0.001; 38.2% vs. 25.9%, p < 0.001; respectively). The optimal cutoff values of IC during the equilibrium phase and of ECV fraction to diagnose thymic carcinoma were 1.5 mg/mL (AUC, 0.955; sensitivity, 100%; specificity, 90.9%) and 26.8% (AUC, 0.888; sensitivity, 100%; specificity, 72.7%), respectively. CONCLUSION: IC and ECV fraction measurement using DECT are helpful in diagnosing TETs. High IC during the equilibrium phase and high ECV fraction are suggestive of thymic carcinoma.

Short-time-window Patlak imaging using a population-based arterial input function and optimized Bayesian penalized likelihood reconstruction: a feasibility study.

BACKGROUND: To explore the feasibility of short-time-window Ki imaging using a population-based arterial input function (IF) and optimized Bayesian penalized likelihood (BPL) reconstruction as a practical alternative to long-time-window Ki imaging with an individual patient-based IF. Myocardial Ki images were generated from 73 dynamic 18F-FDG-PET/CT scans of 30 patients with cardiac sarcoidosis. For each dynamic scan, the Ki images were obtained using the IF from each individual patient and a long time window (10-60 min). In addition, Ki images were obtained using the normalized averaged population-based IF and BPL algorithms with different beta values (350, 700, and 1000) with a short time window (40-60 min). The visual quality of each image was visually rated using a 4-point scale (0, not visible; 1, poor; 2, moderate; and 3, good), and the Ki parameters (Ki-max, Ki-mean, Ki-volume) of positive myocardial lesions were measured independently by two readers. Wilcoxon's rank sum test, McNemar's test, or linear regression analysis were performed to assess the differences or relationships between two quantitative variables. RESULTS: Both readers similarly rated 51 scans as positive (scores = 1-3) and 22 scans as negative (score = 0) for all four Ki images. Among the three types of population-based IF Ki images, the proportion of images with scores of 3 was highest with a beta of 1000 (78.4 and 72.5%, respectively) and lowest with a beta of 350 (33.3 and 23.5%) for both readers (all p < 0.001). The coefficients of determination between the Ki parameters obtained with the individual patient-based IF and those obtained with the population-based IF were highest with a beta of 1000 for both readers (Ki-max, 0.91 and 0.92, respectively; Ki-mean, 0.91 and 0.92, respectively; Ki-volume, 0.75 and 0.60, respectively; and all p < 0.001). CONCLUSIONS: Short-time-window Ki images with a population-based IF reconstructed using the BPL algorithm and a high beta value were closely correlated with long-time-window Ki images generated with an individual patient-based IF. Short-time-window Ki images using a population-based IF and BPL reconstruction might represent practical alternatives to long-time-window Ki images generated using an individual patient-based IF.

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.

Estimation of undistorted images in brain echo-planar images with distortions using the conjugate gradient method with anatomical regularization.

PURPOSE: Although echo-planar imaging (EPI) is widely used for diffusion magnetic resonance (MR) imaging, EPI images suffer from susceptibility-induced geometric distortions. We herein propose a new estimation method for undistorted EPI images using anatomical T1 -weighted images (T1 WIs) based on the physics of MR imaging. METHODS: Our proposed method estimates the undistorted EPI image in the image domain while estimating the magnetic field inhomogeneity map using the conjugate gradient method with anatomical regularization. Our method synthesizes the distorted image to match the measured EPI image containing geometric distortions by alternately updating the undistorted EPI image and the magnetic field inhomogeneity map. We evaluated our proposed method and compared it with a nonrigid registration-based distortion correction method using simulated data and using real data. In the evaluation of the estimation of the magnetic field inhomogeneity map, we used the normalized root-mean-squared error (NRMSE) between the estimated results and the ground truth. In the evaluation of the estimation of undistorted images, we used mutual information (MI) between the undistorted EPI image and the anatomical T1 WI. RESULTS: Using the simulated data, the means and standard deviations of the NRMSE values in the nonrigid registration-based method and proposed method were 1.29 ± 0.63 and 0.64 ± 0.30, respectively. The MI values in the proposed method were larger than those in the nonrigid registration-based method in all evaluated slices. For the real data, the proposed method improved the distortion, and the MI values in the proposed method were larger than those in the nonrigid registration-based method. In the estimation of the magnetic field inhomogeneity map, the NRMSE values in our method were smaller than those in the nonrigid registration-based method. CONCLUSIONS: We demonstrated that our proposed method can estimate the regions with compressed distortions that are not well represented by the nonrigid registration-based methods. The results suggest that the proposed method could be useful in analyses combining EPI images with T1 WIs.