Deep learning to assess right ventricular ejection fraction from two-dimensional echocardiograms in precapillary pulmonary hypertension.

BACKGROUND: Precapillary pulmonary hypertension (PH) is characterized by a sustained increase in right ventricular (RV) afterload, impairing systolic function. Two-dimensional (2D) echocardiography is the most performed cardiac imaging tool to assess RV systolic function; however, an accurate evaluation requires expertise. We aimed to develop a fully automated deep learning (DL)-based tool to estimate the RV ejection fraction (RVEF) from 2D echocardiographic videos of apical four-chamber views in patients with precapillary PH. METHODS: We identified 85 patients with suspected precapillary PH who underwent cardiac magnetic resonance imaging (MRI) and echocardiography. The data was divided into training (80%) and testing (20%) datasets, and a regression model was constructed using 3D-ResNet50. Accuracy was assessed using five-fold cross validation. RESULTS: The DL model predicted the cardiac MRI-derived RVEF with a mean absolute error of 7.67%. The DL model identified severe RV systolic dysfunction (defined as cardiac MRI-derived RVEF < 37%) with an area under the curve (AUC) of .84, which was comparable to the AUC of RV fractional area change (FAC) and tricuspid annular plane systolic excursion (TAPSE) measured by experienced sonographers (.87 and .72, respectively). To detect mild RV systolic dysfunction (defined as RVEF ≤ 45%), the AUC from the DL-predicted RVEF also demonstrated a high discriminatory power of .87, comparable to that of FAC (.90), and significantly higher than that of TAPSE (.67). CONCLUSION: The fully automated DL-based tool using 2D echocardiography could accurately estimate RVEF and exhibited a diagnostic performance for RV systolic dysfunction comparable to that of human readers.

Comparison of Echo-Planar Imaging and Compressed Sensing in the Estimation of Flow Metrics from Aortic 4D Flow MR Imaging: A Healthy Volunteer Study.

PURPOSE: Prolonged scanning of time-resolved 3D phase-contrast MRI (4D flow MRI) limits its routine use in clinical practice. An echo-planar imaging (EPI)-based sequence and compressed sensing can reduce the scan duration. We aimed to determine the impact of EPI for 4D flow MRI on the scan duration, image quality, and quantitative flow metrics. METHODS: This was a prospective study of 15 healthy volunteers (all male, mean age 33 ± 5 years). Conventional sensitivity encoding (SENSE), EPI with SENSE (EPI), and compressed SENSE (CS) (reduction factors: 6 and 12, respectively) were scanned.Scan duration, qualitative indexes of image quality, and quantitative flow parameters of net flow volume, maximum flow velocity, wall shear stress (WSS), and energy loss (EL) in the ascending aorta were assessed. Two-dimensional phase-contrast cine MRI (2D-PC) was considered the gold standard of net flow volume and maximum flow velocity. RESULTS: Compared to SENSE, EPI and CS12 shortened scan durations by 71% and 73% (EPI, 4 min 39 sec; CS6, 7 min 29 sec; CS12, 4 min 14 sec; and SENSE, 15 min 51 sec). Visual image quality was significantly better for EPI than for SENSE and CS (P < 0.001). The net flow volumes obtained with SENSE, EPI, and CS12 and those obtained with 2D-PC were correlated well (r = 0.950, 0.871, and 0.850, respectively). However, the maximum velocity obtained with EPI was significantly underestimated (P < 0.010). The average WSS was significantly higher with EPI than with SENSE, CS6, and CS12 (P < 0.001, P = 0.040, and P = 0.012, respectively). The EL was significantly lower with EPI than with CS6 and CS12 (P = 0.002 and P = 0.007, respectively). CONCLUSION: EPI reduced the scan duration, improved visual image quality, and was associated with more accurate net flow volume than CS. However, the flow velocity, WSS, and EL values obtained with EPI and other sequences may not be directly comparable.

Echocardiographic estimation of right ventricular diastolic stiffness based on pulmonary regurgitant velocity waveform analysis in precapillary pulmonary hypertension.

Right ventricular (RV) diastolic stiffness is an independent predictor of survival and is strongly associated with disease severity in patients with precapillary pulmonary hypertension (PH). Therefore, a fully validated echocardiographic method for assessing RV diastolic stiffness needs to be established. This study aimed to compare echocardiography-derived RV diastolic stiffness and invasively measured pressure-volume loop-derived RV diastolic stiffness in patients with precapillary PH. We studied 50 consecutive patients with suspected or confirmed precapillary PH who underwent cardiac catheterization, magnetic resonance imaging, and echocardiography within a 1-week interval. Single-beat RV pressure-volume analysis was performed to determine the gold standard for RV diastolic stiffness. Elevated RV end-diastolic pressure (RVEDP) was defined as RVEDP ≥ 8 mmHg. Using continuous-wave Doppler and M-mode echocardiography, an echocardiographic index of RV diastolic stiffness was calculated as the ratio of the atrial-systolic descent of the pulmonary artery-RV pressure gradient derived from pulmonary regurgitant velocity (PRPGDAC) to the tricuspid annular plane movement during atrial contraction (TAPMAC). PRPGDAC/TAPMAC showed significant correlation with ß (r = 0.54, p < 0.001) and RVEDP (r = 0.61, p < 0.001). A cut-off value of 0.74 mmHg/mm for PRPGDAC/TAPMAC showed 83% sensitivity and 93% specificity for identifying elevated RVEDP. Multivariate analyses indicated that PRPGDAC/TAPMAC was independently associated with disease severity in patients with precapillary PH, including substantial PH symptoms, stroke volume index, right atrial size, and pressure. PRPGDAC/TAPMAC, based on pulmonary regurgitation velocity waveform analysis, is useful for the noninvasive assessment of RV diastolic stiffness and is associated with prognostic risk factors in precapillary PH.

Influence of epicardial adipose tissue inflammation and adipocyte size on postoperative atrial fibrillation in patients after cardiovascular surgery.

Epicardial adipose tissue (EAT) is an active endocrine organ that is closely associated with occurrence of atrial fibrillation (AF). However, the role of EAT in the development of postoperative AF (POAF) remains unclear. We aimed to investigate the association between EAT profile and POAF occurrence in patients who underwent cardiovascular surgery. We obtained EAT samples from 53 patients to evaluate gene expression, histological changes, mitochondrial oxidative phosphorylation (OXPHOS) capacity in the EAT, and protein secretion in EAT-conditioned medium. EAT volume was measured using computed tomography scan. Eighteen patients (34%) experienced POAF within 7 days after surgery. Although no significant difference was observed in EAT profile between patients with and without POAF, logistic regression analysis identified that the mRNA expression levels of tumor necrosis factor-alpha (TNF-α) were positively correlated and adipocyte size in the EAT was inversely correlated with onset of POAF, respectively. Mitochondrial OXPHOS capacity in the EAT was not associated with POAF occurrence; however, it showed an inverse correlation with adipocyte size and a positive correlation with adiponectin secretion. In conclusion, changes in the secretory profile and adipocyte morphology of the EAT, which represent qualitative aspects of the adipose tissue, were present before the onset of AF.

Differences in blood flow dynamics between balloon- and self-expandable valves in patients with aortic stenosis undergoing transcatheter aortic valve replacement.

BACKGROUND: The differences in pre- and early post-procedural blood flow dynamics between the two major types of bioprosthetic valves, the balloon-expandable valve (BEV) and self-expandable valve (SEV), in patients with aortic stenosis (AS) undergoing transcatheter aortic valve replacement (TAVR), have not been investigated. We aimed to investigate the differences in blood flow dynamics between the BEV and SEV using four-dimensional flow cardiovascular magnetic resonance (4D flow CMR). METHODS: We prospectively examined 98 consecutive patients with severe AS who underwent TAVR between May 2018 and November 2021 (58 BEV and 40 SEV) after excluding those without CMR because of a contraindication, inadequate imaging from the analyses, or patients' refusal. CMR was performed in all participants before (median interval, 22 [interquartile range (IQR) 4-39] days) and after (median interval, 6 [IQR 3-6] days) TAVR. We compared the changes in blood flow patterns, wall shear stress (WSS), and energy loss (EL) in the ascending aorta (AAo) between the BEV and SEV using 4D flow CMR. RESULTS: The absolute reductions in helical flow and flow eccentricity were significantly higher in the SEV group compared in the BEV group after TAVR (BEV: - 0.22 ± 0.86 vs. SEV: - 0.85 ± 0.80, P < 0.001 and BEV: - 0.11 ± 0.79 vs. SEV: - 0.50 ± 0.88, P = 0.037, respectively); there were no significant differences in vortical flow between the groups. The absolute reduction of average WSS was significantly higher in the SEV group compared to the BEV group after TAVR (BEV: - 0.6 [- 2.1 to 0.5] Pa vs. SEV: - 1.8 [- 3.5 to - 0.8] Pa, P = 0.006). The systolic EL in the AAo significantly decreased after TAVR in both the groups, while the absolute reduction was comparable between the groups. CONCLUSIONS: Helical flow, flow eccentricity, and average WSS in the AAo were significantly decreased after SEV implantation compared to BEV implantation, providing functional insights for valve selection in patients with AS undergoing TAVR. Our findings offer valuable insights into blood flow dynamics, aiding in the selection of valves for patients with AS undergoing TAVR. Further larger-scale studies are warranted to confirm the prognostic significance of hemodynamic changes in these patients.

Prognostic Value of Liver Fibrotic Markers in Patients With Heart Failure.

Several liver fibrotic markers are associated with prognosis in patients with heart failure (HF). However, the optimal markers for outcome prediction remain unclear. This study aimed to simultaneously investigate the prognostic value of liver fibrotic markers and the associations between these markers and clinical parameters in patients with HF without organic liver disease. We prospectively examined 211 consecutive patients with chronic HF between April 2018 and August 2021, excluding those with organic liver disease, using liver magnetic resonance imaging and ultrasound. A total of 7 representative liver fibrotic markers were measured in all patients. The primary outcome of interest was the composite of all-cause death and hospitalization for worsening HF. During a median follow-up period of 747 (interquartile range 465 to 1,042) days, the primary outcome occurred in 45 patients. Patients with higher hyaluronic acid and type III procollagen N-terminal peptide (P-III-P) levels showed a significantly higher incidence of the primary outcome than those without (p <0.001 and p = 0.005, respectively). The multivariable Cox regression analysis revealed that hyaluronic acid and P-III-P levels were independently associated with the risk of adverse events (hazard ratio 1.84, 95% confidence interval 1.18 to 2.87 and hazard ratio 2.89, 95% confidence interval 1.32 to 6.34, respectively) even after adjustment for a mortality prediction model, whereas the other 5 markers were not associated with the primary outcome. In conclusion, among the representative liver fibrotic markers, hyaluronic acid and P-III-P might be the optimal markers for outcome prediction in patients with HF.

Clinical utility of single-shot echo-planar diffusion-weighted imaging using L1-regularized iterative sensitivity encoding in prostate MRI.

We investigated the ability of echo-planar imaging with L1-regularized iterative sensitivity encoding-based diffusion-weighted imaging (DWI) to improve the image quality and reduce the scanning time in prostate magnetic resonance imaging. We retrospectively analyzed 109 cases of prostate magnetic resonance imaging. We compared variables in the quantitative and qualitative assessments among 3 imaging groups: conventional parallel imaging-based DWI (PI-DWI) with an acquisition time of 3 minutes 15 seconds; echo-planar imaging with L1-regularized iterative sensitivity encoding-based DWI (L1-DWI) with a normal acquisition time (L1-DWINEX12) of 3 minutes 15 seconds; and L1-DWI with a half acquisition time (L1-DWINEX6) of 1 minute 45 seconds. As a quantitative assessment, the signal-to-noise ratio (SNR) of DWI (SNR-DWI), the contrast-to-noise ratio (CNR) of DWI (CNR-DWI), and the CNR of apparent diffusion coefficient were measured. As a qualitative assessment, the image quality and visual detectability of prostate carcinoma were evaluated. In the quantitative analysis, L1-DWINEX12 showed significantly higher SNR-DWI than PI-DWI (P = .0058) and L1-DWINEX6 (P < .0001). In the qualitative analysis, the image quality score for L1-DWINEX12 was significantly higher than those of PI-DWI and L1-DWINEX6. A non-inferiority assessment demonstrated that L1-DWINEX6 was non-inferior to PI-DWI in terms of both quantitative CNR-DWI and qualitative grading of image quality with a <20% inferior margin. L1-DWI successfully demonstrated a reduced scanning time while maintaining good image quality.

Clinical and Hemodynamic Responses to Imatinib in Pulmonary Veno-Occlusive Disease/Pulmonary Capillary Hemangiomatosis: A Retrospective Pilot Study of Five Cases and Review of the Literature.

BACKGROUND: Pulmonary veno-occlusive disease (PVOD) and pulmonary capillary hemangiomatosis (PCH) are rare types of pulmonary arterial hypertension with dismal prognoses; there is no established medical treatment for these conditions. Possible efficacy of imatinib against these conditions has been reported in 15 cases; however, how and in whom imatinib is effective remain unknown. METHODS: We retrospectively evaluated clinical data from consecutive patients with PVOD/PCH treated with imatinib at our institution. The diagnosis of PVOD/PCH was established using the following criteria: pre-capillary pulmonary hypertension; diffusion capacity of the lung for carbon monoxide < 60%; and two or more high-resolution computed tomography findings of interlobular septal thickening, centrilobular opacities, and mediastinal lymphadenopathy. The dose of pulmonary vasodilators remained unchanged during the assessment of imatinib. RESULTS: The medical records of five patients with PVOD/PCH were reviewed. The patients were aged 67 ± 13 years, their diffusion capacity of the lung for carbon monoxide was 29 ± 8%, and their mean pulmonary artery pressure was 40 ± 7 mmHg. Imatinib was administered at 50-100 mg/day; consequently, the World Health Organization functional class improved in one patient. In addition, imatinib improved the arterial oxygen partial pressure in this and another patient (these two also experienced a decreased mean pulmonary artery pressure and pulmonary vascular resistance after imatinib usage). CONCLUSIONS: This study indicated that imatinib improves the clinical condition, including pulmonary hemodynamics, of some patients with PVOD/PCH. In addition, patients with a certain high-resolution computed tomography pattern or PCH-dominant vasculopathy may respond favorably to imatinib.

Impact of right ventricular stiffness on discordance between hemodynamic parameter and regurgitant volume in patients with pulmonary regurgitation.

BACKGROUND: Accurate detection of significant pulmonary regurgitation (PR) is critical in management of patients after right ventricular (RV) outflow reconstruction in Tetralogy of Fallot (TOF) patients, because of its influence on adverse outcomes. Although pressure half time (PHT) of PR velocity is one of the widely used echocardiographic markers of the severity, shortened PHT is suggested to be seen in conditions with increased RV stiffness with mild PR. However, little has been reported about the exact characteristics of patients showing discrepancy between PHT and PR volume in this population. METHODS: Echocardiography and cardiac magnetic resonance imaging (MRI) were performed in 74 TOF patients after right ventricular outflow tract (RVOT) reconstruction [32 ± 10 years old]. PHT was measured from the continuous Doppler PR flow velocity profile and PHT < 100 ms was used as a sign of significant PR. Presence of end-diastolic RVOT forward flow was defined as RV restrictive physiology. By using phase-contrast MRI, forward and regurgitant volumes through the RVOT were measured and regurgitation fraction was calculated. Significant PR was defined as regurgitant fraction ≥ 25%. RESULTS: Significant PR was observed in 54 of 74 patients. While PHT < 100 ms well predicted significant PR with sensitivity of 96%, specificity of 52%, and c-index of 0.72, 10 patients showed shortened PHT despite regurgitant fraction < 25% (discordant group). Tricuspid annular plane systolic excursion and left ventricular (LV) ejection fraction were comparable between discordant group and patients showing PHT < 100 ms and regurgitant fraction ≥ 25% (concordant group). However, discordant group showed significantly smaller mid RV diameter (30.7 ± 4.5 vs. 39.2 ± 7.3 mm, P < 0.001) and higher prevalence of restrictive physiology (100% vs. 42%, P < 0.01) than concordant group. When mid RV diameter ≥ 32 mm and presence of restrictive physiology were added to PHT, the predictive value was significantly improved (sensitivity: 81%, specificity: 90%, and c-index: 0.89, P < 0.001 vs. PHT alone by multivariable logistic regression model). CONCLUSION: Patients with increased RV stiffness and non-enlarged right ventricle showed short PHT despite mild PR. Although it has been expected, this was the first study to demonstrate the exact characteristics of patients showing discrepancy between PHT and PR volume in TOF patients after RVOT reconstruction.

Fragmented QRS on 12-lead electrocardiogram predicts long-term prognosis in patients with cardiac sarcoidosis.

Fragmented QRS (fQRS) on a 12-lead electrocardiogram is a known marker of fatal arrhythmias or cardiac adverse events in ischemic and non-ischemic cardiomyopathy patients. Nonetheless, the association between fQRS and clinical outcomes in patients with cardiac sarcoidosis (CS) remains unclear. Herein, we investigated whether fQRS is associated with long-term clinical outcomes in CS patients. A total of 78 patients who received immunosuppressive therapy (IST) for clinically diagnosed CS were retrospectively examined. Patients were classified into two groups according to the presence (n = 19) or absence (n = 59) of fQRS on electrocardiogram before IST. The primary outcome was the composite event of all-cause death, ventricular tachyarrhythmias (VTs), and hospitalization for heart failure. Results of late gadolinium enhancement on cardiac magnetic resonance imaging were also analyzed. During a median follow-up period of 3.7 years (interquartile range: 1.6-6.2 years), the primary outcome occurred more frequently in patients with fQRS than in those without (47% vs. 13%, log-rank p = 0.002). Multivariable Cox regression analyses showed that fQRS was an independent determinant of the primary outcome. The incidence of VTs, within 12 months of IST initiation, was comparable between the two groups; however, late-onset VTs, defined as those occurring ≥ 12 months after IST initiation, occurred more frequently in the fQRS group (21% vs. 2%, log-rank p = 0.002). The scar zone and scar border zone were greater in patients with fQRS than in those without it. In conclusion, our analysis suggests that fQRS is an independent predictor of adverse events, particularly late-onset VTs, in patients with CS.

Beneficial effects of nintedanib on cardiomyopathy in patients with systemic sclerosis: a pilot study.

OBJECTIVES: Nintedanib is an inhibitor of tyrosine kinases that has been shown to slow the progression of interstitial lung disease (ILD), including ILD associated with SSc. The aim of this study was to explore the effect of nintedanib on cardiomyopathy associated with systemic sclerosis (SSc). METHODS: Twenty consecutively hospitalized patients with SSc-ILD were enrolled and prospectively followed. The rate of change at 6 months in cardiac magnetic resonance (CMR) parametric mapping, including myocardial extracellular volume, was primarily evaluated. Other endpoints included changes in CMR functional parameters, echocardiographic parameters, modified Rodnan skin score, serum biomarkers and pulmonary function test. RESULTS: Nintedanib was administered in 10 patients, whereas the other 10 were treated without nintedanib or watched, according to ILD severity and progression. Baseline values of CMR parametric mapping were not different between the two groups. The rate of change at 6 months in myocardial extracellular volume was highly different, almost divergent, between the nintedanib group and the control group (-1.62% vs +2.00%, P = 0.0001). Among other endpoints, the change in right ventricular ejection fraction was significantly different between the two groups (P = 0.02), with a preferential change in the nintedanib group. CONCLUSION: Our data indicate beneficial signals of nintedanib on cardiomyopathy associated with SSc. The anti-fibrotic effect of nintedanib might not be limited to the lung.

Liver stiffness assessed by magnetic resonance elastography predicts clinical outcomes in patients with heart failure and without chronic liver disease.

OBJECTIVES: Evaluation of liver stiffness (LS) by magnetic resonance elastography (MRE) is useful for estimating right atrial pressure (RAP) in patients with heart failure (HF). However, its prognostic implications are unclear. We sought to investigate whether LS measured by MRE (LS-MRE) could predict clinical outcomes in patients with HF. METHODS: We prospectively examined 207 consecutive HF patients between April 2018 and May 2021 after excluding those with organic liver disease. All patients underwent 3.0-T MRE. The primary outcome of interest was the composite of all-cause death and hospitalisation for HF. RESULTS: During a median follow-up period of 720 (interquartile range [IQR] 434-1013) days, the primary outcome occurred in 44 patients (21%), including 15 (7%) all-cause deaths and 29 (14%) hospitalisations for HF. The patients were divided into two groups according to median LS-MRE of 2.54 (IQR 2.34-2.82) kPa. Patients with higher LS-MRE showed a higher incidence of the primary outcome compared to those with lower LS-MRE (p < 0.001). Multivariable Cox regression analyses revealed that LS-MRE value was independently associated with the risk of adverse events (hazard ratio 2.49, 95% confidence interval 1.46-4.24). In multivariable linear regression, RAP showed a stronger correlation with LS-MRE (ß coefficient = 0.31, p < 0.001) compared to markers related to liver fibrosis. CONCLUSIONS: In patients without chronic liver disease and presenting with HF, elevated LS-MRE was independently associated with worse clinical outcomes. Elevated LS-MRE may be useful for risk stratification in patients with HF and without chronic liver disease. KEY POINTS: • Magnetic resonance elastography (MRE) is an emerging non-invasive imaging technique for evaluating liver stiffness (LS) which can estimate right atrial pressure. • Elevated LS-MRE, which mainly reflects liver congestion, was independently associated with worse clinical outcomes in patients with heart failure. • The assessment of LS-MRE would be useful for stratifying the risk of adverse events in heart failure patients without chronic liver disease.

Determinants of exercise capacity in patients with heart failure without left ventricular hypertrophy.

BACKGROUND: Determinants of exercise intolerance in a phenotype of heart failure with preserved ejection fraction (HFpEF) with normal left ventricular (LV) structure have not been fully elucidated. METHODS: Cardiopulmonary exercise testing and exercise-stress echocardiography were performed in 44 HFpEF patients without LV hypertrophy. Exercise capacity was determined by peak oxygen consumption (peak VO2). Doppler-derived cardiac output (CO), transmitral E velocity, systolic (LV-s') and early diastolic mitral annular velocities (e'), systolic pulmonary artery (PA) pressure (SPAP), tricuspid annular plane systolic excursion (TAPSE), and peak systolic right ventricular (RV) free wall velocity (RV-s') were measured at rest and exercise. E/e' and TAPSE/SPAP were used as an LV filling pressure parameter and RV-PA coupling, respectively. RESULTS: During exercise, CO, LV-s', RV-s', e', and SPAP were significantly increased (p < 0.05 for all), whereas E/e' remained unchanged and TAPSE/SPAP was significantly reduced (p < 0.001). SPAP was higher and TAPSE/SPAP was lower at peak exercise in patients showing lower-half peak VO2. In univariable analyses, LV-s' (R = 0.35, p = 0.022), SPAP (R = -0.40, p = 0.008), RV-s' (R = 0.47, p = 0.002), and TAPSE/SPAP (R = 0.42, p = 0.005) were significantly correlated with peak VO2. In multivariable analyses, not only SPAP, but also TAPSE/SPAP independently determined peak VO2 even after the adjustment for clinically relevant parameters. CONCLUSIONS: In HFpEF patients without LV hypertrophy, altered RV-PA coupling by exercise could be associated with exercise intolerance, which might not be caused by elevated LV filling pressure.

Efficacy and safety of oral pulmonary vasodilators in pulmonary veno-occlusive disease.

Pulmonary veno-occlusive disease (PVOD) or pulmonary capillary hemangiomatosis (PCH) is a rare subtype of pulmonary hypertension with dismal prognosis. Limited data are available on the efficacy and safety of orally administered pulmonary vasodilators for PVOD/PCH. Whether and how systemic sclerosis (SSc) affects the clinical outcomes of PVOD/PCH is also unknown. This study aimed to determine the clinical and hemodynamic efficacy and safety of oral pulmonary vasodilators for PVOD/PCH and clarify the possible effects of SSc on the clinical presentation of PVOD/PCH. We retrospectively analyzed the clinical data of 15 patients with PVOD/PCH treated with oral pulmonary vasodilators in our department since 2001. Six of them had SSc. Oral pulmonary vasodilators were administered either as single agents (n = 10) or in combination (n = 5). Treatment improved the functional class of five patients, and pulmonary arterial pressure and pulmonary vascular resistance decreased by 10 ± 12 mmHg and 36 ± 19%, respectively (p < 0.05 for both, n = 13), whereas pulmonary edema developed in three patients. The mean survival was 3.9 years, and the 1- and 3-year survival rates were 93% and 65%, respectively. The clinical presentation, including survival, was similar between patients with and without SSc. In our PVOD/PCH cohort, oral pulmonary vasodilators caused pulmonary edema in 20% of patients, but more than 80% of patients experienced significant pulmonary vasodilatory effects, and the overall prognosis was better than that previously reported. SSc does not adversely affect the clinical outcomes of PVOD/PCH.

Utility of the deep learning technique for the diagnosis of orbital invasion on CT in patients with a nasal or sinonasal tumor.

BACKGROUND: In nasal or sinonasal tumors, orbital invasion beyond periorbita by the tumor is one of the important criteria in the selection of the surgical procedure. We investigated the usefulness of the convolutional neural network (CNN)-based deep learning technique for the diagnosis of orbital invasion, using computed tomography (CT) images. METHODS: A total of 168 lesions with malignant nasal or sinonasal tumors were divided into a training dataset (n = 119) and a test dataset (n = 49). The final diagnosis (invasion-positive or -negative) was determined by experienced radiologists who carefully reviewed all of the CT images. In a CNN-based deep learning analysis, a slice of the square target region that included the orbital bone wall was extracted and fed into a deep-learning training session to create a diagnostic model using transfer learning with the Visual Geometry Group 16 (VGG16) model. The test dataset was subsequently tested in CNN-based diagnostic models and by two other radiologists who were not specialized in head and neck radiology. At approx. 2 months after the first reading session, two radiologists again reviewed all of the images in the test dataset, referring to the diagnoses provided by the trained CNN-based diagnostic model. RESULTS: The diagnostic accuracy was 0.92 by the CNN-based diagnostic models, whereas the diagnostic accuracies by the two radiologists at the first reading session were 0.49 and 0.45, respectively. In the second reading session by two radiologists (diagnosing with the assistance by the CNN-based diagnostic model), marked elevations of the diagnostic accuracy were observed (0.94 and 1.00, respectively). CONCLUSION: The CNN-based deep learning technique can be a useful support tool in assessing the presence of orbital invasion on CT images, especially for non-specialized radiologists.

Underdiagnosis of cardiac sarcoidosis by ECG and echocardiography in cases of extracardiac sarcoidosis.

Background: Although screening with 12-lead electrocardiography and transthoracic echocardiography for cardiac involvement has been recommended for patients with biopsy-proven extracardiac sarcoidosis, cardiac sarcoidosis has been reported even in patients with normal electrocardiography and echocardiography findings. We investigated the prevalence and characteristics of these patient cohorts. Methods: We studied 112 consecutive patients (age, 55±17 years, 64% females) with biopsy-proven extracardiac sarcoidosis who had undergone 18F-fluorodeoxyglucose positron emission tomography and cardiac magnetic resonance imaging for cardiac sarcoidosis evaluation. The patients were categorised as those showing normal findings both in electrocardiography and transthoracic echocardiography (normal group) and those showing abnormal findings in one or both examinations (abnormal group). Results: 33 (29%) and 79 (71%) patients were categorised into the normal and abnormal groups, respectively, of which 6 (18%) and 43 (54%) patients, respectively, were diagnosed with cardiac sarcoidosis (p<0.01). Of these six patients in the normal group, two with multiple-organ sarcoidosis showed clinical deterioration of cardiac involvement and required steroid therapy; three with small cardiac involvement showed natural remission over follow-up assessments; and one underwent steroid therapy and showed an improvement in the left ventricular ejection fraction to within normal limits. Conclusions: The prevalence of cardiac sarcoidosis in patients with biopsy-proven extracardiac sarcoidosis and normal electrocardiography and transthoracic echocardiography findings was ∼20%. Electrocardiography and transthoracic echocardiography may not detect cardiac sarcoidosis in patients without conduction and morphological abnormalities. However, some of these patients may subsequently show clinically manifested cardiac sarcoidosis. Physicians should be mindful of this population.