Machine Learning Analysis of Predictors for Inhaled Nitric Oxide Therapy Administration Time Post Congenital Heart Disease Surgery: A Single-Center Observational Study.

Background Congenital heart disease (CHD) is a structural deformity of the heart present at birth. Pulmonary hypertension (PH) may arise from increased blood flow to the lungs, persistent pulmonary arterial pressure elevation, or the use of cardiopulmonary bypass (CPB) during surgical repair. Inhaled nitric oxide (iNO) selectively reduces high blood pressure in the pulmonary vessels without lowering systemic blood pressure, making it useful for treating children with postoperative PH due to heart disease. However, reducing or stopping iNO can exacerbate postoperative PH and hypoxemia, necessitating long-term administration and careful tapering. This study aimed to evaluate, using machine learning (ML), factors that predict the need for long-term iNO administration after open heart surgery in CHD patients in the postoperative ICU, primarily for PH management. Methods We used an ML approach to establish an algorithm to predict 'patients with long-term use of iNO' and validate its accuracy in 34 pediatric postoperative open heart surgery patients who survived and were discharged from the ICU at Kagoshima University Hospital between April 2016 and March 2019. All patients were started on iNO therapy upon ICU admission. Overall, 16 features reflecting patient and surgical characteristics were utilized to predict the patients who needed iNO for over 168 hours using ML analysis with AutoGluon. The dataset was randomly classified into training and test cohorts, comprising 80% and 20% of the data, respectively. In the training cohort, the ML model was constructed using the important features selected by the decrease in Gini impurity and a synthetic oversampling technique. In the testing cohort, the prediction performance of the ML model was evaluated by calculating the area under the receiver operating characteristics curve (AUC) and accuracy. Results Among 28 patients in the training cohort, five needed iNO for over 168 hours; among six patients in the testing cohort, one needed iNO for over 168 hours. CPB, aortic clamp time, in-out balance, and lactate were the four most important features for predicting the need for iNO for over 168 hours. In the training cohorts, the ML model achieved perfect classification with an AUC of 1.00. In the testing cohort, the ML model also achieved perfect classification with an AUC of 1.00 and an accuracy of 1.00. Conclusion The ML approach identified that four factors (CPB, in-out balance, aortic cross-clamp time, and lactate) are strongly associated with the need for long-term iNO administration after open heart surgery in CHD patients. By understanding the outcomes of this study, we can more effectively manage iNO administration in postoperative open heart surgery in CHD patients with PH, potentially preventing the recurrence of postoperative PH and hypoxemia, thereby contributing to safer patient management.

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.

Adult T-cell Leukemia/Lymphoma (ATL) in the Nasal and Paranasal Cavity: Four Cases Report.

Adult T-cell leukemia/lymphoma (ATL) is a form of leukemia caused by the human T-cell leukemia virus type I (HTLV-1). Otolaryngologists often diagnose ATL based on cervical lymphadenopathy or Waldeyer ring lesions. However, there are few reports of ATL occurring in the nasal and paranasal cavity. Here, we report four such cases of ATL. Case 1: An 82-year-old man diagnosed with acute-type ATL with a tumor in the nasal cavity underwent 5 courses of THP-COP, but died after 36 months due to ATL. Case 2: A 62-year-old woman diagnosed with lymphoma-type ATL with a tumor in the frontal sinus was treated with 5 courses of VCAP-AMP-VECP, and has survived for more than 10 years. Case 3: A 64-year-old man diagnosed with lymphoma-type ATL with a tumor in the maxillary sinus underwent 8 courses of VCAP-AMP-VECP and 2 courses of mogamulizumab, but died after 34 months due to ATL. Case 4: A 52-year-old woman diagnosed with lymphoma-type ATL with tumors in both ethmoid sinuses received 2 courses of CHOP, 2 courses of DeVIC, radiotherapy (32 Gy) and 2 courses of mogamulizumab, but died after 9 months due to ATL.

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.

Nuclear medicine practice in Japan: a report of the ninth nationwide survey in 2022.

Subcommittee on Survey of Nuclear Medicine Practice in Japan has performed a nationwide survey of nuclear medicine practice every 5 years since 1982 to survey contemporary nuclear medicine practice and its changes over the years. The subcommittee sent questionnaires, including the number and category of examinations as well as the kind of the radiopharmaceuticals during the 30 days of June 2022 to all nuclear medicine institutes in Japan. The total numbers of them for the year 2022 were estimated depends on the 1-month data. A total of 1095 institutes responded to the survey, including 364 positron emission tomography (PET) centers. The recovery rate was 90.6%. The number of gamma cameras installed was 1299 in total, with 2.5% decrease in 5 years. Dual-head cameras and hybrid SPECT/CT scanners accounted for 83.8% and 35.5%, respectively. The number of single-photon tracer studies in 2022 was 1.11 million which means increase in 2.7% in 5 years. Bone scintigraphy was a leading examination (31.0%), followed by myocardial scintigraphy (27.1%) and cerebral perfusion study (23.8%) in order. The percentage of SPECT studies showed an increase from 63.5% in previous survey to 66.8% in this survey. PET centers have also increased from 389 to 412, as compared with the previous one. One hundred and twenty-two PET centers have installed one or two in-house cyclotrons. Increasing trends of the PET studies were observed from 1992 to 2017, the trend changed and PET studies showed 1.5% decrease in 5 years. 18F-FDG accounted for 98.6% (610,497 examinations). PET examinations using 11C-methionine, 13N-NH3 and 11C-PIB have decreased, with 1624, 2146 and 525 examinations, respectively in 2022. The total number of nuclear medicine examination was eventually increased by 1.0%. Therapies for pheochromocytoma or paraganglioma (PPGL) with 131I-MIBG and for neuroendocrine tumor with 177Lu-DOTA-TATE were newly started, however, a total number of targeted radionuclide therapy was decreased by 17.7% because 131I-radioiodine and 223Ra targeted therapies were decreased and supply of some radioisotopes was discontinued. 131I-radioiodine targeted therapy showed a decrease in 5 years (- 15.9%), including 4099 patients for thyroid cancer. The number of out-patient thyroid bed ablation therapy with 1110 MBq of 131I was also decreased to 1015 per year. The number of admission rooms specialized for radionuclide targeted therapy increased from 157 to 160. The number of 223Ra targeted therapies for castration-resistant metastatic prostate cancer (mCRPC) was 1041 patients. This survey was performed during COVID-19 pandemic, however, total number of nuclear medicine examinations was almost same as previous survey (+ 1.0%). Radionuclide therapies with 131I-MIBG and 177Lu-DOTA-TATE were newly started, and new radionuclide therapy will be available in future, therefore, the development of radionuclide therapy will be continued. We are convinced that this survey report is useful in understanding the current status of the nuclear medicine practice in Japan, and in devising the new strategy to strengthen a role of nuclear medicine.

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.

Low-grade Fibromyxoid Sarcoma With Massive Degeneration: A Case of Unusual Gross and Histological Features.

BACKGROUND: Low-grade fibromyxoid sarcoma (LGFMS) is a rare type of sarcoma which is observed in the soft tissue of proximal extremities, typically in young and middle-aged adults. It consists of a solid proliferation of bland spindle cells within collagenous and myxoid stroma. CASE REPORT: Herein, we report a case of LGFMS with massive degeneration and hyalinization. A 30-year-old man presented with a well-circumscribed mass measuring 15 cm in diameter in his left biceps femoris muscle. Marginal tumor resection was performed under the clinical diagnosis of an ancient schwannoma or chronic expanding hematoma (CEH). The resected tissue revealed a well-demarcated tumor mass with massive degeneration and hyalinization with focal calcification. Proliferation of spindle tumor cells with abundant collagenous stroma, which resembled the fibrous capsule of CEH, was observed exclusively in a small area of the periphery of the tumor. No nuclear palisading, myxoid stroma, or collagen rosettes were identified. Immunohistochemical analysis demonstrated that the spindle tumor cells expressed mucin 4 and epithelial membrane antigen. Reverse transcriptase-polymerase chain reaction analysis detected mRNA expression of fused in sarcoma::CAMP-responsive element binding protein 3-like protein 2 (FUS::CREB3L2) fusion gene. Thus, a final diagnosis of LGFMS with massive degeneration and FUS::CREB3L2 fusion was made. CONCLUSION: The recognition of massive degeneration and hyalinization as unusual features of LGFMS might be helpful to differentiate it from CEH and other benign spindle-cell tumors.

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.

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.

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.

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.

Recent topics of the clinical utility of PET/MRI in oncology and neuroscience.

Since the inline positron emission tomography (PET)/magnetic resonance imaging (MRI) system appeared in clinical, more than a decade has passed. In this article, we have reviewed recently-published articles about PET/MRI. There have been articles about staging in rectal and breast cancers by PET/MRI using fluorodeoxyglucose (FDG) with higher diagnostic performance in oncology. Assessing possible metastatic bone lesions is considered a proper target by FDG PET/MRI. Other than FDG, PET/MRI with prostate specific membrane antigen (PSMA)-targeted tracers or fibroblast activation protein inhibitor have been reported. Especially, PSMA PET/MRI has been reported to be a promising tool for determining appropriate sites in biopsy. Independent of tracers, the clinical application of artificial intelligence (AI) for images obtained by PET/MRI is one of the current topics in this field, suggesting clinical usefulness for differentiating breast lesions or grading prostate cancer. In addition, AI has been reported to be helpful for noise reduction for reconstructing images, which would be promising for reducing radiation exposure. Furthermore, PET/MRI has a clinical role in neuroscience, including localization of the epileptogenic zone. PET/MRI with new PET tracers could be useful for differentiation among neurological disorders. Clinical applications of integrated PET/MRI in various fields are expected to be reported in the future.

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.