Solitary Fibrous Tumor With an Acute Subdural Hematoma: A Case Report and Review of the Literature.

Solitary fibrous tumor (SFT) is a rare interstitial tumor that originates from various soft tissues, and SFTs occurring within the cranium are extremely rare. While intracranial SFTs with cerebral hemorrhage or subarachnoid hemorrhage have been reported, there have been no reports of intracranial SFTs causing subdural hematoma. In this case, we report on an intracranial SFT accompanied by a subdural hematoma. A 29-year-old female was emergently transported due to the sudden onset of persistent headache and vomiting that began the night before. CT and MRI imaging revealed a hemorrhagic tumor under the tentorium and an acute subdural hematoma extending along the tentorium. The excised tumor was diagnosed as an SFT through histopathological examination. After undergoing radiation therapy, no recurrence has been observed. This is the first case report of an SFT accompanied by a subdural hematoma, and it is vital to recognize that SFTs can be associated with subdural hematomas for proper diagnosis and treatment planning.

Diversity of flavour characteristics of table grapes and their contributing volatile compounds analysed by the solvent-assisted flavour evaporation method.

To identify the compounds that contribute to the diverse flavours of table grapes, the flavours and volatile compounds of 38 grape cultivars harvested over 3 years are evaluated through sensory analysis and solvent-assisted flavour evaporation (SAFE). The cultivars are characterized and grouped into seven clusters by hierarchical cluster analysis (HCA) using sensory evaluation data with a flavour wheel specific to table grapes. These clusters were similar to conventional flavour classifications, except that the foxy and neutral cultivars form multiple clusters, highlighting the flavour diversity of table grapes. The SAFE method provides a comprehensive profile of the volatile compounds, including slightly volatile compounds whose profiles are lacking in hybrid grapes and Vitis rotundifolia. The sensory evaluation is supported by the volatile compound profiles, and relationships between the datasets are clarified by multivariate analysis. Specific accumulations and combinations of compounds (α-pinene, ß-pinene, phenylethyl alcohol, furaneol, mesifurane, methyl N-formylanthranilate, and mixed ethyl ester and monoterpenoid) were also identified that contribute to the diversity of flavours (fresh green, floral, fruity, fatty green, sweet, fermented/sour) in table grapes, including linalool and linalool analogues (muscat flavour) along with ethyl ester and hydroxyethyl esters (foxy flavour). The accumulation of these compounds was positively related to a higher flavour intensity. Their specific accumulation and combination supported the flavour diversity of table grapes. This study identified novel flavour-associated compound profiles in table grapes through in-depth volatile compound analysis and non-conventional multivariate analysis.

Development and web deployment of prediction model for pulmonary arterial pressure in chronic thromboembolic pulmonary hypertension using machine learning.

BACKGROUND AND PURPOSE: Mean pulmonary artery pressure (mPAP) is a key index for chronic thromboembolic pulmonary hypertension (CTEPH). Using machine learning, we attempted to construct an accurate prediction model for mPAP in patients with CTEPH. METHODS: A total of 136 patients diagnosed with CTEPH were included, for whom mPAP was measured. The following patient data were used as explanatory variables in the model: basic patient information (age and sex), blood tests (brain natriuretic peptide (BNP)), echocardiography (tricuspid valve pressure gradient (TRPG)), and chest radiography (cardiothoracic ratio (CTR), right second arc ratio, and presence of avascular area). Seven machine learning methods including linear regression were used for the multivariable prediction models. Additionally, prediction models were constructed using the AutoML software. Among the 136 patients, 2/3 and 1/3 were used as training and validation sets, respectively. The average of R squared was obtained from 10 different data splittings of the training and validation sets. RESULTS: The optimal machine learning model was linear regression (averaged R squared, 0.360). The optimal combination of explanatory variables with linear regression was age, BNP level, TRPG level, and CTR (averaged R squared, 0.388). The R squared of the optimal multivariable linear regression model was higher than that of the univariable linear regression model with only TRPG. CONCLUSION: We constructed a more accurate prediction model for mPAP in patients with CTEPH than a model of TRPG only. The prediction performance of our model was improved by selecting the optimal machine learning method and combination of explanatory variables.

Development of Pericardial Fat Count Images Using a Combination of Three Different Deep-Learning Models: Image Translation Model From Chest Radiograph Image to Projection Image of Three-Dimensional Computed Tomography.

RATIONALE AND OBJECTIVES: Pericardial fat (PF)-the thoracic visceral fat surrounding the heart-promotes the development of coronary artery disease by inducing inflammation of the coronary arteries. To evaluate PF, we generated pericardial fat count images (PFCIs) from chest radiographs (CXRs) using a dedicated deep-learning model. MATERIALS AND METHODS: We reviewed data of 269 consecutive patients who underwent coronary computed tomography (CT). We excluded patients with metal implants, pleural effusion, history of thoracic surgery, or malignancy. Thus, the data of 191 patients were used. We generated PFCIs from the projection of three-dimensional CT images, wherein fat accumulation was represented by a high pixel value. Three different deep-learning models, including CycleGAN were combined in the proposed method to generate PFCIs from CXRs. A single CycleGAN-based model was used to generate PFCIs from CXRs for comparison with the proposed method. To evaluate the image quality of the generated PFCIs, structural similarity index measure (SSIM), mean squared error (MSE), and mean absolute error (MAE) of (i) the PFCI generated using the proposed method and (ii) the PFCI generated using the single model were compared. RESULTS: The mean SSIM, MSE, and MAE were 8.56 × 10-1, 1.28 × 10-2, and 3.57 × 10-2, respectively, for the proposed model, and 7.62 × 10-1, 1.98 × 10-2, and 5.04 × 10-2, respectively, for the single CycleGAN-based model. CONCLUSION: PFCIs generated from CXRs with the proposed model showed better performance than those generated with the single model. The evaluation of PF without CT may be possible using the proposed method.

Computer-aided diagnosis of chest X-ray for COVID-19 diagnosis in external validation study by radiologists with and without deep learning system.

To evaluate the diagnostic performance of our deep learning (DL) model of COVID-19 and investigate whether the diagnostic performance of radiologists was improved by referring to our model. Our datasets contained chest X-rays (CXRs) for the following three categories: normal (NORMAL), non-COVID-19 pneumonia (PNEUMONIA), and COVID-19 pneumonia (COVID). We used two public datasets and private dataset collected from eight hospitals for the development and external validation of our DL model (26,393 CXRs). Eight radiologists performed two reading sessions: one session was performed with reference to CXRs only, and the other was performed with reference to both CXRs and the results of the DL model. The evaluation metrics for the reading session were accuracy, sensitivity, specificity, and area under the curve (AUC). The accuracy of our DL model was 0.733, and that of the eight radiologists without DL was 0.696 ± 0.031. There was a significant difference in AUC between the radiologists with and without DL for COVID versus NORMAL or PNEUMONIA (p = 0.0038). Our DL model alone showed better diagnostic performance than that of most radiologists. In addition, our model significantly improved the diagnostic performance of radiologists for COVID versus NORMAL or PNEUMONIA.

Prognosis prediction of patients with malignant pleural mesothelioma using conditional variational autoencoder on 3D PET images and clinical data.

BACKGROUND: Deep learning (DL) has been widely used for diagnosis and prognosis prediction of numerous frequently occurring diseases. Generally, DL models require large datasets to perform accurate and reliable prognosis prediction and avoid overlearning. However, prognosis prediction of rare diseases is still limited owing to the small number of cases, resulting in small datasets. PURPOSE: This paper proposes a multimodal DL method to predict the prognosis of patients with malignant pleural mesothelioma (MPM) with a small number of 3D positron emission tomography-computed tomography (PET/CT) images and clinical data. METHODS: A 3D convolutional conditional variational autoencoder (3D-CCVAE), which adds a 3D-convolutional layer and conditional VAE to process 3D images, was used for dimensionality reduction of PET images. We developed a two-step model that performs dimensionality reduction using the 3D-CCVAE, which is resistant to overlearning. In the first step, clinical data were input to condition the model and perform dimensionality reduction of PET images, resulting in more efficient dimension reduction. In the second step, a subset of the dimensionally reduced features and clinical data were combined to predict 1-year survival of patients using the random forest classifier. To demonstrate the usefulness of the 3D-CCVAE, we created a model without the conditional mechanism (3D-CVAE), one without the variational mechanism (3D-CCAE), and one without an autoencoder (without AE), and compared their prediction results. We used PET images and clinical data of 520 patients with histologically proven MPM. The data were randomly split in a 2:1 ratio (train : test) and three-fold cross-validation was performed. The models were trained on the training set and evaluated based on the test set results. The area under the receiver operating characteristic curve (AUC) for all models was calculated using their 1-year survival predictions, and the results were compared. RESULTS: We obtained AUC values of 0.76 (95% confidence interval [CI], 0.72-0.80) for the 3D-CCVAE model, 0.72 (95% CI, 0.68-0.77) for the 3D-CVAE model, 0.70 (95% CI, 0.66-0.75) for the 3D-CCAE model, and 0.69 (95% CI 0.65-0.74) for the without AE model. The 3D-CCVAE model performed better than the other models (3D-CVAE, p = 0.039; 3D-CCAE, p = 0.0032; and without AE, p = 0.0011). CONCLUSIONS: This study demonstrates the usefulness of the 3D-CCVAE in multimodal DL models learned using a small number of datasets. Additionally, it shows that dimensionality reduction via AE can be used to learn a DL model without increasing the overlearning risk. Moreover, the VAE mechanism can overcome the uncertainty of the model parameters that commonly occurs for small datasets, thereby eliminating the risk of overlearning. Additionally, more efficient dimensionality reduction of PET images can be performed by providing clinical data as conditions and ignoring clinical data-related features.

Comparison of Conventional Imaging and 18F-Fluorodeoxyglucose Positron Emission Tomography/Computed Tomography in the Diagnostic Accuracy of Staging in Patients with Intrahepatic Cholangiocarcinoma.

We aimed to examine the accuracy of tumor staging of intrahepatic cholangiocarcinoma (ICC) by using 18F-fluorodeoxyglucose positron emission tomography/computed tomography (18F-FDG PET-CT). From January 2001 to December 2021, 202 patients underwent PET-CT, CT, and MRI for the initial staging of ICC in two institutions. Among them, 102 patients had undergone surgical treatment. Ninety patients who had a histopathological diagnosis of ICC were retrospectively reviewed. The sensitivity and specificity of 18F-FDG PET-CT, CT, and magnetic resonance imaging (MRI) in detecting tumors, satellite focus, vascular invasion, and lymph node metastases were analyzed. Ninety patients with histologically diagnosed ICC were included. PET-CT demonstrated no statistically significant advantage over CT and MR in the diagnosis of multiple tumors and macrovascular invasion, and bile duct invasion. The overall sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and accuracy of PET-CT in lymph node metastases were 84%, 86%, 91%, 84%, and 86%, respectively. PET-CT revealed a significantly higher accuracy compared to CT or MRI (86%, 67%, and 76%, p < 0.01, respectively) in the diagnosis of regional lymph node metastases. The accuracy of tumor staging by PET-CT was higher than that by CT/MRI (PET-CT vs. CT vs. MRI: 68/90 vs. 47/90 vs. 51/90, p < 0.05). 18F-FDG PET-CT had sensitivity and specificity values for diagnosing satellite focus and vascular and bile duct invasion similar to those of CT or MRI; however, PET-CT showed higher accuracy in diagnosing regional lymph node metastases. 18F-FDG PET-CT exhibited higher tumor staging accuracy than that of CT/MRI. Thus, 18FDG PET-CT may support tumor staging in ICC.

Genetic architecture of berry aroma compounds in a QTL (quantitative trait loci) mapping population of interspecific hybrid grapes (Vitis labruscana × Vitis vinifera).

BACKGROUND: Although grapes accumulate diverse groups of volatile compounds, their genetic regulation in different cultivars remains unelucidated. Therefore, this study investigated the volatile composition in the berries of an interspecific hybrid population from a Vitis labruscana 'Campbell Early' (CE) × Vitis vinifera 'Muscat of Alexandria' (MA) cross to understand the relationship among volatile compounds and their genetic regulation. Then, a quantitative trait locus (QTL) analysis of its volatile compounds was conducted. RESULTS: While MA contained higher concentrations of monoterpenes and norisoprenoids, CE contained higher concentrations of C6 compounds, lactones and shikimic acid derivatives, including volatiles characteristic to American hybrids, i.e., methyl anthranilate, o-aminoacetophenone and mesifurane. Furthermore, a cluster analysis of volatile profiles in the hybrid population discovered ten coordinately modulated free and bound volatile clusters. QTL analysis identified a major QTL on linkage group (LG) 5 in the MA map for 14 monoterpene concentrations, consistent with a previously reported locus. Additionally, several QTLs detected in the CE map affected the concentrations of specific monoterpenes, such as linalool, citronellol and 1,8-cineol, modifying the monoterpene composition in the berries. As for the concentrations of five norisoprenoids, a major common QTL on LG2 was discovered first in this study. Several QTLs with minor effects were also discovered in various volatile groups, such as lactones, alcohols and shikimic acid derivatives. CONCLUSIONS: An overview of the profiles of aroma compounds and their underlying QTLs in a population of interspecific hybrid grapes in which muscat flavor compounds and many other aroma compounds were mixed variously were elucidated. Coordinate modulation of the volatile clusters in the hybrid population suggested an independent mechanism for controlling the volatiles of each group. Accordingly, specific QTLs with significant effects were observed for terpenoids, norisoprenoids and some volatiles highly contained in CE berries.

Microvasculopathy Evaluated by Dual-Energy Computed Tomography in Patients with Chronic Thromboembolic Pulmonary Hypertension and Pulmonary Arterial Hypertension.

Background: Poor subpleural perfusion (PSP) on dual-energy computed tomography (DE-CT) suggests microvasculopathy in chronic thromboembolic pulmonary hypertension (CTEPH). However, whether the microvasculopathy findings are equivalent to those in pulmonary arterial hypertension (PAH) remains unclear. The aim of this study was to elucidate the characteristics of microvasculopathy in CTEPH compared to those of that in PAH. Methods: We retrospectively reviewed subpleural perfusion on DE-CT and the hemodynamics of 23 patients with PAH and 113 with inoperable CTEPH. Subpleural perfusion on DE-CT was classified as poor (subpleural spaces in all segments with little or no perfusion) or normal. Results: PSP was observed in 51% of patients with CTEPH and in 4% of those with PAH (p < 0.01). CTEPH patients with PSP had poorer baseline hemodynamics and lower diffusing capacity for carbon monoxide divided by the alveolar volume (DLCO/VA) than those with CTEPH with normal perfusion (pulmonary vascular resistance [PVR]: 768 ± 445 dynes-sec/cm5 vs. 463 ± 284 dynes-sec/cm5, p < 0.01; DLCO/VA, 60.4 ± 16.8% vs. 75.9 ± 15.7%, p < 0.001). Despite the existence of PSP, hemodynamics improved to nearly normal in both groups after balloon pulmonary angioplasty. Conclusions: PSP on DE-CT, which is one of the specific imaging findings in CTEPH, might suggest a different mechanism of microvasculopathy from that in PAH.

Unsupervised-learning-based method for chest MRI-CT transformation using structure constrained unsupervised generative attention networks.

The integrated positron emission tomography/magnetic resonance imaging (PET/MRI) scanner simultaneously acquires metabolic information via PET and morphological information using MRI. However, attenuation correction, which is necessary for quantitative PET evaluation, is difficult as it requires the generation of attenuation-correction maps from MRI, which has no direct relationship with the gamma-ray attenuation information. MRI-based bone tissue segmentation is potentially available for attenuation correction in relatively rigid and fixed organs such as the head and pelvis regions. However, this is challenging for the chest region because of respiratory and cardiac motions in the chest, its anatomically complicated structure, and the thin bone cortex. We propose a new method using unsupervised generative attentional networks with adaptive layer-instance normalisation for image-to-image translation (U-GAT-IT), which specialised in unpaired image transformation based on attention maps for image transformation. We added the modality-independent neighbourhood descriptor (MIND) to the loss of U-GAT-IT to guarantee anatomical consistency in the image transformation between different domains. Our proposed method obtained a synthesised computed tomography of the chest. Experimental results showed that our method outperforms current approaches. The study findings suggest the possibility of synthesising clinically acceptable computed tomography images from chest MRI with minimal changes in anatomical structures without human annotation.

The impact of the atrial wall thickness in normal/mild late-gadolinium enhancement areas on atrial fibrillation rotors in persistent atrial fibrillation patients.

Background: Some of atrial fibrillation (AF) drivers are found in normal/mild late-gadolinium enhancement (LGE) areas, as well as moderate ones. The atrial wall thickness (AWT) has been reported to be important as a possible AF substrate. However, the AWT and degree of LGEs as an AF substrate has not been fully validated in humans. Objective: The purpose of this study was to evaluate the impact of the AWT in normal/mild LGE areas on AF drivers. Methods: A total of 287 segments in 15 persistent AF patients were assessed. AF drivers were defined as non-passively activated areas (NPAs), where rotational activation was frequently observed, and were detected by the novel real-time phase mapping (ExTRa Mapping), mild LGE areas were defined as areas with a volume ratio of the enhancement voxel of 0% to <10%. The AWT was defined as the minimum distance from the manually determined endocardium to the epicardial border on the LGE-MRI. Results: NPAs were found in 20 (18.0%) of 131 normal/mild LGE areas where AWT was significantly thicker than that in the passively activated areas (PAs) (2.5 ± 0.3 vs. 2.2 ± 0.3 mm, p < .001). However, NPAs were found in 41 (26.3%) of 156 moderate LGE areas where AWT was thinner than that of PAs (2.1 ± 0.2 mm vs. 2.23 ± 0.3 mm, p = .02). An ROC curve analysis yielded an optimal cutoff value of 2.2 mm for predicting the presence of an NPA in normal/mild LGE areas. Conclusion: The location of AF drivers in normal/mild LGE areas might be more accurately identified by evaluating AWT.

Efficacy of myocardial washout of 99mTc-MIBI/Tetrofosmin for the evaluation of inflammation in patients with cardiac sarcoidosis: comparison with 18F-fluorodeoxyglucose positron emission tomography findings.

OBJECTIVE: Both myocardial perfusion scintigraphy and 18F-fluorodeoxyglucose positron emission tomography (FDG PET) are useful for the diagnosis of cardiac sarcoidosis (CS). However, the association between the washout of 99mTc-labeled tracer and FDG PET has not been established. This study aimed to evaluate the association between the washout of 99mTc-labeled tracer and FDG PET findings in patients with CS. METHODS: We retrospectively analyzed 64 patients (65.0 ± 11.2 years, 53% male) with suspected CS who underwent myocardial single-photon emission computed tomography (SPECT) with 99mTc-labeled tracer and FDG PET. The SPECT images were acquired at 15 min (early images) and 3 h (delayed images) after injection and scored visually using a 17-segment model with a 5-point scoring system. The washout score was defined as the difference between the early and delayed total defect scores. FDG positivity was considered as focal or focal on diffuse patterns on visual assessment, and FDG uptake was quantified by measuring the standardized uptake value (SUV) of each of the 17 segments. RESULTS: The washout score was significantly higher for the CS group than for the non-CS group (3.0 [-1.0-5.0] vs. 0.0 [-0.5-1.0], p = 0.010). Receiver operating characteristic analysis showed that a washout score of ≥ 2 had the best accuracy for detecting CS (88% sensitivity and 56% specificity) and FDG positivity (71% sensitivity and 89% specificity). In the segment-based analysis of 833 segments from 49 patients, excluding 15 patients with diffuse FDG uptake, the median SUVs for FDG uptake for the washout scores of ≤ 0, 1, and 2 were 2.3 (1.8-3.6), 4.2 (2.9-7.8), and 8.3 (6.5-9.4), respectively (p < 0.001). CONCLUSIONS: The washout of 99mTc-labeled tracer can be a useful marker for the evaluation of FDG PET findings in patients with CS.

Voxel-based analysis of age and gender effects on striatal [123I] FP-CIT binding in healthy Japanese adults.

OBJECTIVE: Although previous studies have investigated age and gender effects on striatal subregional dopamine transporter (DaT) binding, these studies were mostly based on a conventional regions of interest-based analysis. Here, we investigated age and gender effects on striatal DaT binding at the voxel level, using a multicenter database of [(123)I] N-omega-fluoropropyl-2beta-carbomethoxy-3beta-{4-iodophenyl}nortropane ([(123)I] FP-CIT)-single photon emission computed tomography (SPECT) scans in 256 healthy Japanese adults. METHODS: We used the Southampton method to calculate the specific binding ratios (SBRs) of each subject's striatum and then converted the [123I] FP-CIT SPECT images to quantitative SBRs images. To investigate the effects of age and gender effects on striatal DaT binding, we performed a voxel-based analysis using statistical parametric mapping. Gender differences were also compared between young to middle-aged subjects and elderly subjects (age threshold: 60 years). RESULTS: When all subjects were explored as a group, DaT binding throughout the striatum decreased with advancing age. Among all subjects, the females showed higher DaT binding in the bilateral caudate compared to the males. In the young to middle-aged subjects, the females showed higher DaT binding throughout the striatum (with a slight caudate predominance) versus the males. In the elderly, there were no gender differences in striatal DaT binding. CONCLUSION: Our findings of striatal subregional age- and gender-related differences may provide useful information to construct a more detailed DaT database in healthy Japanese subjects.

Diversity and determinants of the sigmoid septum and its impact on morphology of the outflow tract as revealed using cardiac computed tomography.

BACKGROUND: The sigmoid septum has been generally evaluated subjectively and qualitatively, without detailed examination of its diversity, impact on the morphology of the left ventricular outflow tract (LVOT), and anatomical background. METHODS: We enrolled 100 patients without any background cardiac diseases (67.5 ± 12.8 years old; 43% women) who underwent cardiac computed tomography. Basal septal morphology was evaluated using antero-superior and medial bulging angles (bidirectional angulation of the basal septum relative to the LVOT). The eccentricity index of the LVOT, area narrowing ratio (LVOT/virtual basal ring area), aortic-to-left ventricular axial angle (angulation of the aortic root relative to the left ventricle), and wedged height (non-coronary aortic sinus to inferior epicardium distance) were also quantified. RESULTS: The antero-superior bulging, medial bulging, aortic-to-left ventricular axial angles, LVOT eccentricity index, area narrowing ratio, and wedged height were 76° ± 17°, 166° ± 27°, 127° ± 9°, 1.8 ± 0.5, 1.0 ± 0.2, and 41.2 ± 9.1 mm, respectively. Both bulging angles were correlated with each other and contributed to the narrowing and deformation of the LVOT. Angulated aortic root was not correlated with either bidirectional septal bulge or LVOT narrowing. Clockwise rotation of the aortic root rotation was an independent predictor of prominent antero-superior septal bulge. Deeper aortic wedging was a common independent predictor of bidirectional septal bulge. CONCLUSIONS: The extent of septal bulge varies in normal hearts. Along with deep aortic wedging, the bidirectional bulge of the basal septum deforms and narrows the LVOT without affecting the virtual basal ring morphology.

The impact of computed tomography-derived aortic atheroma volume on prognosis after transcatheter aortic valve replacement.

BACKGROUND: The impact of the extent of aortic atheroma on patients' prognosis after transcatheter aortic valve replacement (TAVR) has not been completely evaluated. This study aimed to evaluate the prognostic value of the aortic atheroma volume (AAV) derived from computed tomography, and the effect of its differences among the segments of the aorta, in patients undergoing TAVR. METHODS: In total, 143 patients with symptomatic severe aortic stenosis who underwent pre-procedural computed tomography before TAVR procedure indication were evaluated. AAV was calculated by measuring the aortic lumen and vessel volume using every 1-mm axial image and was further divided into thoracic (TAAV) and abdominal segments (AbAAV). RESULTS: During a median follow-up of 651 days, 24 all-cause and 14 cardiac deaths occurred. In the Kaplan-Meier analysis, the high AAV group had significantly higher all-cause and cardiac mortalities than the low AAV group (p = 0.016 and 0.023, respectively). Regarding segmental AAV, all-cause and cardiac mortalities did not have significant differences between the high and low TAAV groups. Moreover, all-cause and cardiac mortalities were significantly higher in the high AbAAV group than in the low AbAAV group (p = 0.0043 and 0.023, respectively). The multivariable analysis showed that only AbAAV was an independent predictor for all-cause mortality (hazard ratio: 1.06, p = 0.046). CONCLUSION: AAV was significantly associated with the mortality after TAVR. The current study suggests the pre-procedural assessment of AAV is valuable in predicting prognosis after TAVR. However, further investigation with a larger sample size is needed to validate our findings.

Varied Extent of Mitral Annular Disjunction Among Cases With Different Phenotypes of Mitral Valve Prolapse.

Detailed 3-dimensional analysis of mitral annular disjunction was undertaken in 3 comparative cases of mitral valve prolapse. A case of Barlow disease showed extensive disjunction, whereas cases of fibroelastic deficiency and forme fruste demonstrated less extensive disjunction. Considering the current controversies surrounding disjunction, these observations call for detailed research in the future. (Level of Difficulty: Advanced.).

Prognostic Impact of Myocardial Extracellular Volume Fraction Assessment Using Dual-Energy Computed Tomography in Patients Treated With Aortic Valve Replacement for Severe Aortic Stenosis.

Background Myocardial extracellular volume fraction (ECV), measured by cardiac magnetic resonance imaging, is a useful prognostic marker for patients who have undergone aortic valve replacement (AVR) for aortic stenosis. However, the prognostic significance of ECV measurements based on computed tomography (CT) is unclear. This study evaluated the association between ECV measured with dual-energy CT and clinical outcomes in patients with aortic stenosis who underwent transcatheter or surgical AVR. Methods and Results We retrospectively enrolled 95 consecutive patients (age, 84.0±5.0 years; 75% women) with severe aortic stenosis who underwent preprocedural CT for transcatheter AVR planning. ECV was measured using iodine density images obtained by delayed enhancement dual-energy CT. The primary end point was a composite outcome of all-cause death and hospitalization for heart failure after AVR. The mean ECV measured with CT was 28.1±3.8%. During a median follow-up of 2.6 years, 22 composite outcomes were observed, including 15 all-cause deaths and 11 hospitalizations for heart failure. In Kaplan-Meier analysis, the high ECV group (≥27.8% [median value]) had significantly higher rates of composite outcomes than the low ECV group (<27.8%) (log-rank test, P=0.012). ECV was the only independent predictor of adverse outcomes on multivariable Cox regression analysis (hazards ratio, 1.25; 95% CI, 1.10‒1.41; P<0.001). Conclusions Myocardial ECV measured with dual-energy CT in patients who underwent aortic valve intervention was an independent predictor of adverse outcomes after AVR.

Deep learning with deep convolutional neural network using FDG-PET/CT for malignant pleural mesothelioma diagnosis.

OBJECTIVES: This study analyzed an artificial intelligence (AI) deep learning method with a three-dimensional deep convolutional neural network (3D DCNN) in regard to diagnostic accuracy to differentiate malignant pleural mesothelioma (MPM) from benign pleural disease using FDG-PET/CT results. RESULTS: For protocol A, the area under the ROC curve (AUC)/sensitivity/specificity/accuracy values were 0.825/77.9% (81/104)/76.4% (55/72)/77.3% (136/176), while those for protocol B were 0.854/80.8% (84/104)/77.8% (56/72)/79.5% (140/176), for protocol C were 0.881/85.6% (89/104)/75.0% (54/72)/81.3% (143/176), and for protocol D were 0.896/88.5% (92/104)/73.6% (53/72)/82.4% (145/176). Protocol D showed significantly better diagnostic performance as compared to A, B, and C in ROC analysis (p = 0.031, p = 0.0020, p = 0.041, respectively). MATERIALS AND METHODS: Eight hundred seventy-five consecutive patients with histologically proven or suspected MPM, shown by history, physical examination findings, and chest CT results, who underwent FDG-PET/CT examinations between 2007 and 2017 were investigated in a retrospective manner. There were 525 patients (314 MPM, 211 benign pleural disease) in the deep learning training set, 174 (102 MPM, 72 benign pleural disease) in the validation set, and 176 (104 MPM, 72 benign pleural disease) in the test set. Using AI with PET/CT alone (protocol A), human visual reading (protocol B), a quantitative method that incorporated maximum standardized uptake value (SUVmax) (protocol C), and a combination of PET/CT, SUVmax, gender, and age (protocol D), obtained data were subjected to ROC curve analyses. CONCLUSIONS: Deep learning with 3D DCNN in combination with FDG-PET/CT imaging results as well as clinical features comprise a novel potential tool shows flexibility for differential diagnosis of MPM.

Deep learning model for predicting gestational age after the first trimester using fetal MRI.

OBJECTIVES: To evaluate a deep learning model for predicting gestational age from fetal brain MRI acquired after the first trimester in comparison to biparietal diameter (BPD). MATERIALS AND METHODS: Our Institutional Review Board approved this retrospective study, and a total of 184 T2-weighted MRI acquisitions from 184 fetuses (mean gestational age: 29.4 weeks) who underwent MRI between January 2014 and June 2019 were included. The reference standard gestational age was based on the last menstruation and ultrasonography measurements in the first trimester. The deep learning model was trained with T2-weighted images from 126 training cases and 29 validation cases. The remaining 29 cases were used as test data, with fetal age estimated by both the model and BPD measurement. The relationship between the estimated gestational age and the reference standard was evaluated with Lin's concordance correlation coefficient (ρc) and a Bland-Altman plot. The ρc was assessed with McBride's definition. RESULTS: The ρc of the model prediction was substantial (ρc = 0.964), but the ρc of the BPD prediction was moderate (ρc = 0.920). Both the model and BPD predictions had greater differences from the reference standard at increasing gestational age. However, the upper limit of the model's prediction (2.45 weeks) was significantly shorter than that of BPD (5.62 weeks). CONCLUSIONS: Deep learning can accurately predict gestational age from fetal brain MR acquired after the first trimester. KEY POINTS: • The prediction of gestational age using ultrasound is accurate in the first trimester but becomes inaccurate as gestational age increases. • Deep learning can accurately predict gestational age from fetal brain MRI acquired in the second and third trimester. • Prediction of gestational age by deep learning may have benefits for prenatal care in pregnancies that are underserved during the first trimester.