Initial validation of the clinical significance of the NETest in Japanese gastroenteropancreatic neuroendocrine tumor patients.

As novel biomarkers for gastroenteropancreatic neuroendocrine tumors (GEPNET) are in demand, we aimed to validate the clinical value of the NETest in Japanese patients. Between 2021 and 2023, blood and clinical data were collected from patients with GEPNET. Among 35 patients (median age: 59 [49-66] years), 27 cases originated from the pancreas and eight from the gastrointestinal tract. Of 69 samples sent to the laboratory, 56 (81.2%) underwent NETest. The diagnostic sensitivity was 97.1%. Among three patients who underwent R0 resection and four treated with peptide receptor radionuclide therapy, the changes in NETest scores closely correlated with disease progression. The NETest demonstrated high diagnostic efficacy and accurate therapeutic monitoring capabilities in a Japanese population.

Recent trends in AI applications for pelvic MRI: a comprehensive review.

Magnetic resonance imaging (MRI) is an essential tool for evaluating pelvic disorders affecting the prostate, bladder, uterus, ovaries, and/or rectum. Since the diagnostic pathway of pelvic MRI can involve various complex procedures depending on the affected organ, the Reporting and Data System (RADS) is used to standardize image acquisition and interpretation. Artificial intelligence (AI), which encompasses machine learning and deep learning algorithms, has been integrated into both pelvic MRI and the RADS, particularly for prostate MRI. This review outlines recent developments in the use of AI in various stages of the pelvic MRI diagnostic pathway, including image acquisition, image reconstruction, organ and lesion segmentation, lesion detection and classification, and risk stratification, with special emphasis on recent trends in multi-center studies, which can help to improve the generalizability of AI.

Maximum standardized uptake value in 11C-methionine positron emission tomography may predict the prognosis of patients with oral squamous cell carcinoma.

The present study aimed to elucidate the correlation between the uptake of 11C-methionine (MET) by a primary tumor and the survival of patients with oral squamous cell carcinoma (OSCC). This study enrolled 31 patients who underwent radical surgery for OSCC. The patients underwent pretreatment MET-positron emission tomography (PET) scanning. We analyzed correlations between the maximum standardized uptake value (SUVmax) of MET-PET in a primary tumor and the clinicopathological features. Further, we compared overall survival (OS), disease-specific survival (DSS), and loco-regional recurrence (LRR) rates between the two groups according to SUVmax of MET-PET. SUVmax of MET-PET in a primary tumor was higher in patients with advanced T-classification and advanced clinical stage, with significant differences (P = 0.001 and P = 0.016, respectively). The patients with SUVmax of MET-PET ≥ 4.4 showed significantly lower DSS rates and higher LRR rates than those with SUVmax of < 4.4 (P = 0.015 and P = 0.016, respectively). SUVmax of MET-PET and OS rates showed no significant correlation (P = 0.073). The present study revealed that SUVmax of MET-PET may predict clinical outcomes and prognosis in patients with OSCC who underwent radical surgery.

Stability of standardized uptake values for quantitative bone SPECT for jawbone lesions: a single-center cross-sectional study.

BACKGROUND: The long time required for bone uptake of radiopharmaceutical material after injection for bone scintigraphy is a burden for patients with poor health. Thus, to assess whether the uptake time could be reduced for single-photon emission computed tomography (SPECT) of the jawbone, this study evaluated differences in maximum standardized uptake values (SUVmax) within patients using SPECT imaging at 2 and 3 hours after radiopharmaceutical injection. METHODS: A total of 33 patients undergoing treatment or in post-treatment follow-up for medication-related osteonecrosis of the jaw, who visited our hospital between July 2020 and August 2021 and could receive SPECT twice on the same day, were enrolled in the study. Patients were injected with technetium-99 m hydroxymethylene diphosphonate (Tc-99 m HMDP) intravenously. The SUVmax for healthy parietal bones and jawbone lesions were calculated from the SPECT images using quantitative analysis software, and the SUVmax were compared between 2- and 3-hour uptake times. RESULTS: After exclusion, 30 patients were included in the study. In the 2-hour and 3-hour images, the median SUVmax of the parietal bones were 1.90 and 1.81, respectively, and those of the jawbone lesions were 9.25 and 9.39, respectively. The limits of agreement (LOA) ranged from - 0.33 to 0.25 in the parietal bones, and the %LOA ranged from - 9.8 to 17.3% in the jawbone lesions, showing high equivalence between the two uptake durations. The SUVmax showed no clinical differences between the 2- and 3-hour uptake durations for Tc-99 m HMDP SPECT of the jawbone. CONCLUSIONS: The results of this study justify a 2-3-hour uptake window when performing quantitative SPECT of the jawbone. Therefore, the minimum uptake time can potentially be reduced to only 2 hours.

Predictive factors of early FDG-PET response to [131I] MIBG treatment for unresectable or metastatic pheochromocytomas and paragangliomas (PPGLs).

Pheochromocytomas and paragangliomas (PPGLs) are rare neuroendocrine tumours that produce catecholamines. [131I] MIBG-avid unresectable or metastatic PPGLs are treated with [131I] MIBG therapy. A high metabolic tumour volume (MTV) and total lesion glycolysis (TLG) can be poor prognostic factors. Therefore, we evaluated the metabolic responses to [131I] MIBG therapy with respect to other clinical factors.A retrospective study was performed on a series of 20 patients who underwent FDG-PET before and after [131I] MIBG therapy. We administered a single dose comprising 5.5 GBq of [131I] MIBG. Semi-quantitative parameters (SUVmax, MTV, and TLG) were calculated using the liver SUV (mean + 3SD) as a threshold on Metavol software. The semi-quantitative FDG-PET parameters for determining response were complete response , partial remission, stable disease, and progressive disease (PD). We divided our study participants into the PD and non-PD groups and compared the overall survival between the two groups. Subsequently, we evaluated the relationships between metabolic response and age, sex, tumour type, metastatic site, chemotherapy or external radiation history, and 24-hour urine catecholamine levels by univariate logistic regression analyses. Both MTV-based and TLG-based criteria for PD vs. non-PD were significant prognostic factors (p = 0.014). However, treatment response as evaluated based on the SUVmax was not a significant predictor. Higher urinary dopamine levels were associated with poor metabolic response as assessed by MTV and TLG. The other clinical parameters were non-significant. Poor metabolic response (measured with MTV and TLG) to [131I] MIBG therapy in unresectable or metastatic PPGLs was related to shorter OS. The poor metabolic response can be predicted using the urinary dopamine level.

Safety and efficacy of tisagenlecleucel in patients with relapsed or refractory B-cell lymphoma: the first real-world evidence in Japan.

BACKGROUND: Tisagenlecleucel, an autologous CD19-directed T-cell immunotherapy, can induce a durable response in adult patients with relapsed/refractory (r/r) B-cell lymphoma. METHODS: To elucidate the outcome of chimeric antigen receptor (CAR) T-cell therapy in Japanese, we retrospectively analyzed the outcomes of 89 patients who received tisagenlecleucel for r/r diffuse large B-cell lymphoma (n = 71) or transformed follicular lymphoma (n = 18). RESULTS: With a median follow-up of 6.6-months, 65 (73.0%) patients achieved a clinical response. The overall survival (OS) and event-free survival (EFS) rates at 12 months were 67.0% and 46.3%, respectively. Overall, 80 patients (89.9%) had cytokine release syndrome (CRS), and 6 patients (6.7%) had a grade ≥ 3 event. ICANS occurred in 5 patients (5.6%); only 1 patient had grade 4 ICANS. Representative infectious events of any grade were cytomegalovirus viremia, bacteremia and sepsis. The most common other adverse events were ALT elevation, AST elevation, diarrhea, edema, and creatinine elevation. No treatment-related mortality was observed. A Sub-analysis showed that a high metabolic tumor volume (MTV; ≥ 80 ml) and stable disease /progressive disease before tisagenlecleucel infusion were both significantly associated with a poor EFS and OS in a multivariate analysis (P < 0.05). Notably, the combination of these 2 factors efficiently stratified the prognosis of these patients (HR 6.87 [95% CI 2.4-19.65; P < 0.05] into a high-risk group). CONCLUSION: We report the first real-world data on tisagenlecleucel for r/r B-cell lymphoma in Japan. Tisagenlecleucel is feasible and effective, even in late line treatment. In addition, our results support a new algorithm for predicting the outcomes of tisagenlecleucel.

New trend in artificial intelligence-based assistive technology for thoracic imaging.

Although there is no solid agreement for artificial intelligence (AI), it refers to a computer system with intelligence similar to that of humans. Deep learning appeared in 2006, and more than 10 years have passed since the third AI boom was triggered by improvements in computing power, algorithm development, and the use of big data. In recent years, the application and development of AI technology in the medical field have intensified internationally. There is no doubt that AI will be used in clinical practice to assist in diagnostic imaging in the future. In qualitative diagnosis, it is desirable to develop an explainable AI that at least represents the basis of the diagnostic process. However, it must be kept in mind that AI is a physician-assistant system, and the final decision should be made by the physician while understanding the limitations of AI. The aim of this article is to review the application of AI technology in diagnostic imaging from PubMed database while particularly focusing on diagnostic imaging in thorax such as lesion detection and qualitative diagnosis in order to help radiologists and clinicians to become more familiar with AI in thorax.

Clinical applications of artificial intelligence in liver imaging.

This review outlines the current status and challenges of the clinical applications of artificial intelligence in liver imaging using computed tomography or magnetic resonance imaging based on a topic analysis of PubMed search results using latent Dirichlet allocation. LDA revealed that "segmentation," "hepatocellular carcinoma and radiomics," "metastasis," "fibrosis," and "reconstruction" were current main topic keywords. Automatic liver segmentation technology using deep learning is beginning to assume new clinical significance as part of whole-body composition analysis. It has also been applied to the screening of large populations and the acquisition of training data for machine learning models and has resulted in the development of imaging biomarkers that have a significant impact on important clinical issues, such as the estimation of liver fibrosis, recurrence, and prognosis of malignant tumors. Deep learning reconstruction is expanding as a new technological clinical application of artificial intelligence and has shown results in reducing contrast and radiation doses. However, there is much missing evidence, such as external validation of machine learning models and the evaluation of the diagnostic performance of specific diseases using deep learning reconstruction, suggesting that the clinical application of these technologies is still in development.

Deep learning-based attenuation correction for whole-body PET - a multi-tracer study with 18F-FDG, 68 Ga-DOTATATE, and 18F-Fluciclovine.

A novel deep learning (DL)-based attenuation correction (AC) framework was applied to clinical whole-body oncology studies using 18F-FDG, 68 Ga-DOTATATE, and 18F-Fluciclovine. The framework used activity (λ-MLAA) and attenuation (µ-MLAA) maps estimated by the maximum likelihood reconstruction of activity and attenuation (MLAA) algorithm as inputs to a modified U-net neural network with a novel imaging physics-based loss function to learn a CT-derived attenuation map (µ-CT). METHODS: Clinical whole-body PET/CT datasets of 18F-FDG (N = 113), 68 Ga-DOTATATE (N = 76), and 18F-Fluciclovine (N = 90) were used to train and test tracer-specific neural networks. For each tracer, forty subjects were used to train the neural network to predict attenuation maps (µ-DL). µ-DL and µ-MLAA were compared to the gold-standard µ-CT. PET images reconstructed using the OSEM algorithm with µ-DL (OSEMDL) and µ-MLAA (OSEMMLAA) were compared to the CT-based reconstruction (OSEMCT). Tumor regions of interest were segmented by two radiologists and tumor SUV and volume measures were reported, as well as evaluation using conventional image analysis metrics. RESULTS: µ-DL yielded high resolution and fine detail recovery of the attenuation map, which was superior in quality as compared to µ-MLAA in all metrics for all tracers. Using OSEMCT as the gold-standard, OSEMDL provided more accurate tumor quantification than OSEMMLAA for all three tracers, e.g., error in SUVmax for OSEMMLAA vs. OSEMDL: - 3.6 ± 4.4% vs. - 1.7 ± 4.5% for 18F-FDG (N = 152), - 4.3 ± 5.1% vs. 0.4 ± 2.8% for 68 Ga-DOTATATE (N = 70), and - 7.3 ± 2.9% vs. - 2.8 ± 2.3% for 18F-Fluciclovine (N = 44). OSEMDL also yielded more accurate tumor volume measures than OSEMMLAA, i.e., - 8.4 ± 14.5% (OSEMMLAA) vs. - 3.0 ± 15.0% for 18F-FDG, - 14.1 ± 19.7% vs. 1.8 ± 11.6% for 68 Ga-DOTATATE, and - 15.9 ± 9.1% vs. - 6.4 ± 6.4% for 18F-Fluciclovine. CONCLUSIONS: The proposed framework provides accurate and robust attenuation correction for whole-body 18F-FDG, 68 Ga-DOTATATE and 18F-Fluciclovine in tumor SUV measures as well as tumor volume estimation. The proposed method provides clinically equivalent quality as compared to CT in attenuation correction for the three tracers.

Determination of brain tumor recurrence using 11 C-methionine positron emission tomography after radiotherapy.

We conducted a prospective multicenter trial to compare the usefulness of 11 C-methionine (MET) and 18 F-fluorodeoxyglucose (FDG) positron emission tomography (PET) for identifying tumor recurrence. Patients with clinically suspected tumor recurrence after radiotherapy underwent both 11 C-MET and 18 F-FDG PET. When a lesion showed a visually detected uptake of either tracer, it was surgically resected for histopathological analysis. Patients with a lesion negative to both tracers were revaluated by magnetic resonance imaging (MRI) at 3 months after the PET studies. The primary outcome measure was the sensitivity of each tracer in cases with histopathologically confirmed recurrence, as determined by the McNemar test. Sixty-one cases were enrolled, and 56 cases could be evaluated. The 38 cases where the lesions showed uptake of either 11 C-MET or 18 F-FDG underwent surgery; 32 of these cases were confirmed to be subject to recurrence. Eighteen cases where the lesions showed uptake of neither tracer received follow-up MRI; the lesion size increased in one of these cases. Among the cases with histologically confirmed recurrence, the sensitivities of 11 C-MET PET and 18 F-FDG PET were 0.97 (32/33, 95% confidence interval [CI]: 0.85-0.99) and 0.48 (16/33, 95% CI: 0.33-0.65), respectively, and the difference was statistically significant (P < .0001). The diagnostic accuracy of 11 C-MET PET was significantly better than that of 18 F-FDG PET (87.5% vs. 69.6%, P = .033). No examination-related adverse events were observed. The results of the study demonstrated that 11 C-MET PET was superior to 18 F-FDG PET for discriminating between tumor recurrence and radiation-induced necrosis.

Predicting tumor response and prognosis to neoadjuvant chemotherapy in esophageal squamous cell carcinoma patients using PERCIST: a multicenter study in Japan.

PURPOSE: To investigate the usefulness of the positron emission tomography response criteria in solid tumors 1.0 (PERCIST1.0) for predicting tumor response to neoadjuvant chemotherapy and prognosis and determine whether PERCIST improvements are necessary for esophageal squamous cell carcinoma (ESCC) patients. PATIENTS AND METHODS: We analyzed the cases of 177 ESCC patients and examined the association between PERCIST and their pathological responses. Associations of whole-PERCIST with progression-free survival (PFS) and overall survival (OS) were evaluated by a Kaplan-Meier analysis and Cox proportional hazards model. To investigate potential PERCIST improvements, we used the survival tree technique to understand patients' prognoses. RESULTS: There were significant correlations between the pathologic response and PERCIST of primary tumor (p < 0.001). The optimal cutoff value of the primary tumors' SULpeak response to classify pathologic responses was -50.0%. The diagnostic accuracy of SULpeak response was 87.3% sensitivity, 54.1% specificity, 68.9% accuracy, positive predictive value 60.5%, and negative predictive value 84.1%. Whole-PERCIST was significantly associated with PFS and OS. The survival tree results indicated that a high reduction of the whole SULpeak response was significantly correlated with the patients' prognoses. The cutoff values for the separation of prognoses were - 52.5 for PFS and - 47.1% for OS. CONCLUSION: PERCIST1.0 can help predict tumor responses and prognoses. However, 18F-FDG-PET/CT tends to underestimate residual tumors in histopathological response evaluations. Modified PERCIST, in which the partial metabolic response is further classified by the SULpeak response (-50%), might be more appropriate than PERCIST1.0 for evaluating tumor responses and stratifying high-risk patients for recurrence and poor prognosis.

Prediction of the local treatment outcome in patients with oropharyngeal squamous cell carcinoma using deep learning analysis of pretreatment FDG-PET images.

BACKGROUND: This study aimed to assess the utility of deep learning analysis using pretreatment FDG-PET images to predict local treatment outcome in oropharyngeal squamous cell carcinoma (OPSCC) patients. METHODS: One hundred fifty-four OPSCC patients who received pretreatment FDG-PET were included and divided into training (n = 102) and test (n = 52) sets. The diagnosis of local failure and local progression-free survival (PFS) rates were obtained from patient medical records. In deep learning analyses, axial and coronal images were assessed by three different architectures (AlexNet, GoogLeNET, and ResNet). In the training set, FDG-PET images were analyzed after the data augmentation process for the diagnostic model creation. A multivariate clinical model was also created using a binomial logistic regression model from a patient's clinical characteristics. The test data set was subsequently analyzed for confirmation of diagnostic accuracy. Assessment of local PFS rates was also performed. RESULTS: Training sessions were successfully performed with an accuracy of 74-89%. ROC curve analyses revealed an AUC of 0.61-0.85 by the deep learning model in the test set, whereas it was 0.62 by T-stage, 0.59 by clinical stage, and 0.74 by a multivariate clinical model. The highest AUC (0.85) was obtained with deep learning analysis of ResNet architecture. Cox proportional hazards regression analysis revealed deep learning-based classification by a multivariate clinical model (P < .05), and ResNet (P < .001) was a significant predictor of the treatment outcome. In the Kaplan-Meier analysis, the deep learning-based classification divided the patient's local PFS rate better than the T-stage, clinical stage, and a multivariate clinical model. CONCLUSIONS: Deep learning-based diagnostic model with FDG-PET images indicated its possibility to predict local treatment outcomes in OPSCCs.

18F-FMISO PET/CT detects hypoxic lesions of cardiac and extra-cardiac involvement in patients with sarcoidosis.

BACKGROUND: 18F-fluoromisonidazole (FMISO) is a hypoxia positron emission tomography (PET) tracer. Here, we evaluated cardiac and extra-cardiac sarcoidosis using both FMISO and 18F-fluorodeoxyglucose (FDG) PET/CT in a prospective cohort of patients with sarcoidosis. METHODS: Ten consecutive sarcoidosis patients with suspected cardiac involvement were prospectively enrolled. Each patient fasted overnight (for ≥ 18 hours) preceded by a low-carbohydrate diet before FDG PET/CT but not given special dietary instructions before the FMISO PET/CT scan. We visually and semiquantitatively assessed the uptakes of FMISO and FDG using the maximal standardized uptake value (SUVmax). The metabolic volume (MV) of FDG was calculated as the volume within the boundary determined by the threshold (mean SUV of blood pool × 1.5). RESULTS: Nine patients showed focal FDG uptake in the myocardium and were diagnosed with cardiac sarcoidosis. Among the patients with extra-cardiac lesions, FDG uptake was seen in 8 lymph nodes and 3 lung lesions. FMISO uptake was seen in the 7 cardiac (77.8%) and 6 extra-cardiac (54.5%) lesions. None of the patients showed physiological FMISO uptake in the myocardium. The SUVmax values of the lesions with FMISO uptake were higher than those of the lesions without FMISO uptake in both the cardiac (SUVmax: 9.9, IQR: 8.4-10.0 vs 7.3, IQR: 6.3-8.2) and non-cardiac lesions (SUVmax: 17.6, IQR: 14.5-19.3 vs 6.1, IQR: 5.9-6.2; P = 0.006). The MV values of the lesions with FMISO uptake were significantly higher than those of the lesions without FMISO uptake (111.3, IQR: 78.3-135.7 vs 6.4, IQR: 1.9-23.3; P = 0.0009). CONCLUSIONS: FMISO showed no physiological myocardial uptake and did not require special preparation. FMISO PET has the potential to detect hypoxic lesions in patients with sarcoidosis.

Correlation of active contact location with weight gain after subthalamic nucleus deep brain stimulation: a case series.

BACKGROUND: Weight gain (WG) is a frequently reported side effect of subthalamic deep brain stimulation; however, the underlying mechanisms remain unclear. The active contact locations influence the clinical outcomes of subthalamic deep brain stimulation, but it is unclear whether WG is directly associated with the active contact locations. We aimed to determine whether WG is associated with the subthalamic deep brain stimulation active contact locations. METHODS: We enrolled 14 patients with Parkinson's disease who underwent bilateral subthalamic deep brain stimulation between 2013 and 2019. Bodyweight and body mass index were measured before and one year following the surgery. The Lead-DBS Matlab toolbox was used to determine the active contact locations based on magnetic resonance imaging and computed tomography. We also created sweet spot maps for WG using voxel-wise statistics, based on volume of tissue activation and the WG of each patient. Fluorodeoxyglucose-positron emission tomography data were also acquired before and one year following surgery, and statistical parametric mapping was used to evaluate changes in brain metabolism. We examined which brain regions' metabolism fluctuation significantly correlated with increased body mass index scores and positron emission tomography data. RESULTS: One year after surgery, the body mass index increase was 2.03 kg/m2. The sweet spots for WG were bilateral, mainly located dorsally outside of the subthalamic nucleus (STN). Furthermore, WG was correlated with increased metabolism in the left limbic and associative regions, including the middle temporal gyrus, inferior frontal gyrus, and orbital gyrus. CONCLUSIONS: Although the mechanisms underlying WG following subthalamic deep brain stimulation are possibly multifactorial, our findings suggest that dorsal stimulation outside of STN may lead to WG. The metabolic changes in limbic and associative cortical regions after STN-DBS may also be one of the mechanisms underlying WG. Further studies are warranted to confirm whether dorsal stimulation outside of STN changes the activities of these cortical regions.

Influence of the scan time point when assessing hypoxia in 18F-fluoromisonidazole PET: 2 vs. 4 h.

PURPOSE: 18F-fluoromisonidazole (18F-FMISO) is the most widely used positron emission tomography (PET) tracer for imaging tumor hypoxia. Previous reports suggested that the time from injection to the scan may affect the assessment of 18F-FMISO uptake. Herein, we directly compared the images at 2 h and 4 h after a single injection of 18F-FMISO. METHODS: Twenty-three patients with or suspected of having a brain tumor were scanned twice at 2 and 4 h following an intravenous injection of 18F-FMISO. We estimated the mean standardized uptake value (SUV) of the gray matter and white matter and the gray-to-white matter ratio in the background brain tissue from the two scans. We also performed a semi-quantitative analysis using the SUVmax and maximum tumor-to-normal ratio (TNR) for the tumor. RESULTS: At 2 h, the SUVmean of gray matter was significantly higher than that of white matter (median 1.23, interquartile range (IQR) 1.10-1.32 vs. 1.04, IQR 0.95-1.16, p < 0.0001), whereas at 4 h, it significantly decreased to approach that of the white matter (1.10, IQR 1.00-1.23 vs. 1.02, IQR 0.93-1.13, p = NS). The gray-to-white matter ratio thus significantly declined from 1.17 (IQR 1.14-1.19) to 1.09 (IQR 1.07-1.10) (p < 0.0001). All 7 patients with glioblastoma showed significant increases in the SUVmax (2.20, IQR 1.67-3.32 at 2 h vs. 2.65, IQR 1.74-4.41 at 4 h, p = 0.016) and the TNR (1.75, IQR 1.40-2.38 at 2 h vs. 2.34, IQR 1.67-3.60 at 4 h, p = 0.016). CONCLUSION: In the assessment of hypoxic tumors, 18F-FMISO PET for hypoxia imaging should be obtained at 4 h rather than 2 h after the injection.

A convolutional neural network-based system to classify patients using FDG PET/CT examinations.

BACKGROUND: As the number of PET/CT scanners increases and FDG PET/CT becomes a common imaging modality for oncology, the demands for automated detection systems on artificial intelligence (AI) to prevent human oversight and misdiagnosis are rapidly growing. We aimed to develop a convolutional neural network (CNN)-based system that can classify whole-body FDG PET as 1) benign, 2) malignant or 3) equivocal. METHODS: This retrospective study investigated 3485 sequential patients with malignant or suspected malignant disease, who underwent whole-body FDG PET/CT at our institute. All the cases were classified into the 3 categories by a nuclear medicine physician. A residual network (ResNet)-based CNN architecture was built for classifying patients into the 3 categories. In addition, we performed a region-based analysis of CNN (head-and-neck, chest, abdomen, and pelvic region). RESULTS: There were 1280 (37%), 1450 (42%), and 755 (22%) patients classified as benign, malignant and equivocal, respectively. In the patient-based analysis, CNN predicted benign, malignant and equivocal images with 99.4, 99.4, and 87.5% accuracy, respectively. In region-based analysis, the prediction was correct with the probability of 97.3% (head-and-neck), 96.6% (chest), 92.8% (abdomen) and 99.6% (pelvic region), respectively. CONCLUSION: The CNN-based system reliably classified FDG PET images into 3 categories, indicating that it could be helpful for physicians as a double-checking system to prevent oversight and misdiagnosis.

Quantification of myocardial blood flow with 11C-hydroxyephedrine dynamic PET: comparison with 15O-H2O PET.

BACKGROUND: 11C-hydroxyephedrine (HED) PET has been used to evaluate the myocardial sympathetic nervous system (SNS). Here we sought to establish a simultaneous approach for quantifying both myocardial blood flow (MBF) and the SNS from a single HED PET scan. METHODS: Ten controls and 13 patients with suspected cardiac disease were enrolled. The inflow rate of 11C-HED (K1) was obtained using a one-tissue-compartment model. We compared this rate with the MBF derived from 15O-H2O PET. In the controls, the relationship between K1 from 11C-HED PET and the MBF from 15O-H2O PET was linked by the Renkin-Crone model. RESULTS: The relationship between K1 from 11C-HED PET and the MBF from 15O-H2O PET from the controls' data was approximated as follows: K1  =  (1 - 0.891 * exp(- 0.146/MBF)) * MBF. In the validation set, the correlation coefficient demonstrated a significantly high relationship for both the whole left ventricle (r = 0.95, P < 0.001) and three coronary territories (left anterior descending artery: r = 0.96, left circumflex artery: r = 0.81, right coronary artery: r =  0.86; P < 0.001, respectively). CONCLUSION: 11C-HED can simultaneously estimate MBF and sympathetic nervous function without requiring an additional MBF scan for assessing mismatch areas between MBF and SNS.

Use of 18F-FDG PET/CT texture analysis to diagnose cardiac sarcoidosis.

PURPOSE: 18F-fluorodeoxyglocose positron emission tomography (FDG PET) plays a significant role in the diagnosis of cardiac sarcoidosis (CS). Texture analysis is a group of computational methods for evaluating the inhomogeneity among adjacent pixels or voxels. We investigated whether texture analysis applied to myocardial FDG uptake has diagnostic value in patients with CS. METHODS: Thirty-seven CS patients (CS group), and 52 patients who underwent FDG PET/CT to detect malignant tumors with any FDG cardiac uptake (non-CS group) were studied. A total of 36 texture features from the histogram, gray-level co-occurrence matrix (GLCM), gray-level run length matrix (GLRLM), gray-level zone size matrix (GLZSM) and neighborhood gray-level difference matrix (NGLDM), were computed using polar map images. First, the inter-operator and inter-scan reproducibility of the texture features of the CS group were evaluated. Then, texture features of the patients with CS were compared to those without CS lesions. RESULTS: Twenty-eight of the 36 texture features showed high inter-operator reproducibility with intraclass correlation coefficients (ICCs) over 0.80. In addition, 17 of the 36 showed high inter-scan reproducibility with ICCs over 0.80. The SUVmax showed no difference between the CS and non-CS group [7.36 ± 2.77 vs. 8.78 ± 4.65, p = 0.45, area under the curve (AUC) = 0.60]. By contrast, 16 of the 36 texture features could distinguish CS from non-CS grsoup with AUC > 0.80. Multivariate logistic regression analysis after hierarchical clustering concluded that long-run emphasis (LRE; P = 0.0004) and short-run low gray-level emphasis (SRLGE; P = 0.016) were significant independent factors that could distinguish between the CS and non-CS groups. Specifically, LRE was significantly higher in CS than in non-CS (30.1 ± 25.4 vs. 11.4 ± 4.6, P < 0.0001), with high diagnostic ability (AUC = 0.91), and had high inter-operator reproducibility (ICC = 0.98). CONCLUSIONS: The texture analysis had high inter-operator and high inter-scan reproducibility. Some of texture features showed higher diagnostic value than SUVmax for CS diagnosis. Therefore, texture analysis may have a role in semi-automated systems for diagnosing CS.

Volume-based glucose metabolic analysis of FDG PET/CT: The optimum threshold and conditions to suppress physiological myocardial uptake.

OBJECTIVE: FDG PET/CT plays a significant role in the diagnosis of inflammatory heart diseases and cardiac tumors. We attempted to determine the optimal FDG uptake threshold for volume-based analyses and to evaluate the relationship between the myocardial physiological uptake volume in FDG PET and several clinical factors. METHODS: A total of 190 patients were retrospectively analyzed. The cardiac metabolic volume (CMV) was defined as a volume within the boundary determined by a threshold (SUVmean of blood pool × 1.5). RESULTS: The SUVmean of the blood pool measured in the descending aorta (DA) (r = 0.86, intraclass correlation coefficient [ICC] = 0.93, P < 0.0001) and that in the left ventricle (LV) cavity (r = 0.87, ICC = 0.90, P < 0.0001) showed high inter-operator reproducibility. However, the SUVmean in the LV cavity showed a significant correlation with the CMV (P = 0.0002, r = 0.26). The CMV in the patients who fasted < 18 hours were significantly higher (49.7  ±  73.2 vs. 18.0  ±  53.8 mL, P = 0.0013) compared to the patients with > 18-hour fasting. The multivariate analysis demonstrated that only the fasting period > 18 hours was independently associated with CMV = 0. CONCLUSION: Our findings revealed that the DA is suitable to decide the threshold for the volume-based analysis. The fasting time was significantly associated with the cardiac FDG uptake.