RESUMO
The Asian Society of Cardiovascular Imaging-Practical Tutorial (ASCI-PT) is an instructional initiative of the ASCI School designed to enhance educational standards. In 2021, the ASCI-PT was convened with the goal of formulating a consensus statement on the assessment of coronary stenosis and coronary plaque using coronary CT angiography (CCTA). Nineteen experts from four countries conducted thorough reviews of current guidelines and deliberated on eight key issues to refine the process and improve the clarity of reporting CCTA findings. The experts engaged in both online and on-site sessions to establish a unified agreement. This document presents a summary of the ASCI-PT 2021 deliberations and offers a comprehensive consensus statement on the evaluation of coronary stenosis and coronary plaque in CCTA.
RESUMO
Objective@#In Korea, radiology has been positioned towards the early adoption of artificial intelligence-based software as medical devices (AI-SaMDs); however, little is known about the current usage, implementation, and future needs of AI-SaMDs.We surveyed the current trends and expectations for AI-SaMDs among members of the Korean Society of Radiology (KSR). @*Materials and Methods@#An anonymous and voluntary online survey was open to all KSR members between April 17 and May 15, 2023. The survey was focused on the experiences of using AI-SaMDs, patterns of usage, levels of satisfaction, and expectations regarding the use of AI-SaMDs, including the roles of the industry, government, and KSR regarding the clinical use of AI-SaMDs. @*Results@#Among the 370 respondents (response rate: 7.7% [370/4792]; 340 board-certified radiologists; 210 from academic institutions), 60.3% (223/370) had experience using AI-SaMDs. The two most common use-case of AI-SaMDs among the respondents were lesion detection (82.1%, 183/223), lesion diagnosis/classification (55.2%, 123/223), with the target imaging modalities being plain radiography (62.3%, 139/223), CT (42.6%, 95/223), mammography (29.1%, 65/223), and MRI (28.7%, 64/223). Most users were satisfied with AI-SaMDs (67.6% [115/170, for improvement of patient management] to 85.1% [189/222, for performance]). Regarding the expansion of clinical applications, most respondents expressed a preference for AI-SaMDs to assist in detection/diagnosis (77.0%, 285/370) and to perform automated measurement/quantification (63.5%, 235/370). Most respondents indicated that future development of AI-SaMDs should focus on improving practice efficiency (81.9%, 303/370) and quality (71.4%, 264/370). Overall, 91.9% of the respondents (340/370) agreed that there is a need for education or guidelines driven by the KSR regarding the use of AI-SaMDs. @*Conclusion@#The penetration rate of AI-SaMDs in clinical practice and the corresponding satisfaction levels were high among members of the KSR. Most AI-SaMDs have been used for lesion detection, diagnosis, and classification. Most respondents requested KSR-driven education or guidelines on the use of AI-SaMDs.
RESUMO
Purpose@#Assessing the metastasis status of the sentinel lymph nodes (SLNs) for hematoxylin and eosin–stained frozen tissue sections by pathologists is an essential but tedious and time-consuming task that contributes to accurate breast cancer staging. This study aimed to review a challenge competition (HeLP 2019) for the development of automated solutions for classifying the metastasis status of breast cancer patients. @*Materials and Methods@#A total of 524 digital slides were obtained from frozen SLN sections: 297 (56.7%) from Asan Medical Center (AMC) and 227 (43.4%) from Seoul National University Bundang Hospital (SNUBH), South Korea. The slides were divided into training, development, and validation sets, where the development set comprised slides from both institutions and training and validation set included slides from only AMC and SNUBH, respectively. The algorithms were assessed for area under the receiver operating characteristic curve (AUC) and measurement of the longest metastatic tumor diameter. The final total scores were calculated as the mean of the two metrics, and the three teams with AUC values greater than 0.500 were selected for review and analysis in this study. @*Results@#The top three teams showed AUC values of 0.891, 0.809, and 0.736 and major axis prediction scores of 0.525, 0.459, and 0.387 for the validation set. The major factor that lowered the diagnostic accuracy was micro-metastasis. @*Conclusion@#In this challenge competition, accurate deep learning algorithms were developed that can be helpful for making a diagnosis on intraoperative SLN biopsy. The clinical utility of this approach was evaluated by including an external validation set from SNUBH.
RESUMO
Cardiac CT has been proven to provide diagnostic and prognostic evaluation of coronary artery disease for cardiovascular risk stratification and treatment decision-making based on rapid technological development and various research evidence. Coronary CT angiography has emerged as a gateway test for coronary artery disease that can reduce invasive angiography due to its high negative predictive value, but the diagnostic specificity is relatively low. However, coronary CT angiography is likely to overcome its limitations through functional evaluation to identify the hemodynamic significance of coronary artery disease by analyzing myocardial perfusion and fractional flow reserve through cardiac CT. Recently, studies have been actively conducted to incorporate artificial intelligence to make this more objective and reproducible. In this review, functional imaging techniques of cardiac computerized tomography are explored.
RESUMO
Objective@#This study aimed to evaluate the effect of implementing the consensus statement from the Asian Society of Cardiovascular Imaging-Practical Tutorial 2020 (ASCI-PT 2020) on the reliability of cardiac MR with late gadolinium enhancement (CMR-LGE) myocardial viability scoring between observers in the context of ischemic cardiomyopathy. @*Materials and Methods@#A total of 17 cardiovascular imaging experts from five different countries evaluated CMR obtained in 26 patients (male:female, 23:3; median age [interquartile range], 55.5 years [50–61.8]) with ischemic cardiomyopathy. For LGE scoring, based on the 17 segments, the extent of LGE in each segment was graded using a five-point scoring system ranging from 0 to 4 before and after exposure according to the consensus statement. All scoring was performed via webbased review. Scores for slices, vascular territories, and total scores were obtained as the sum of the relevant segmental scores. Interobserver reliability for segment scores was assessed using Fleiss’ kappa, while the intraclass correlation coefficient (ICC) was used for slice score, vascular territory score, and total score. Inter-observer agreement was assessed using the limits of agreement from the mean (LoA). @*Results@#Interobserver reliability (Fleiss’ kappa) in each segment ranged 0.242–0.662 before the consensus and increased to 0.301–0.774 after the consensus. The interobserver reliability (ICC) for each slice, each vascular territory, and total score increased after the consensus (slice, 0.728–0.805 and 0.849–0.884; vascular territory, 0.756–0.902 and 0.852–0.941; total score, 0.847 and 0.913, before and after implementing the consensus statement, respectively. Interobserver agreement in scoring also improved with the implementation of the consensus for all slices, vascular territories, and total score. The LoA for the total score narrowed from ± 10.36 points to ± 7.12 points. @*Conclusion@#The interobserver reliability and agreement for CMR-LGE scoring for ischemic cardiomyopathy improved when following guidance from the ASCI-PT 2020 consensus statement.
RESUMO
Objective@#To investigate the prognostic value of preoperative cardiac magnetic resonance imaging (MRI) for long-term major adverse cardiac and cerebrovascular events (MACCEs) in patients undergoing tricuspid valve (TV) surgery for functional tricuspid regurgitation (TR). @*Materials and Methods@#The preoperative cardiac MR images, New York Heart Association functional class, comorbidities, and clinical events of 78 patients (median [interquartile range], 59 [51–66.3] years, 28.2% male) who underwent TV surgery for functional TR were comprehensively reviewed. Cox proportional hazards analyses were performed to assess the associations of clinical and imaging parameters with MACCEs and all-cause mortality. @*Results@#For the median follow-up duration of 5.4 years (interquartile range, 1.2–6.6), MACCEs and all-cause mortality were 51.3% and 23.1%, respectively. The right ventricular (RV) end-systolic volume index (ESVI) and the systolic RV mass index (RVMI) were higher in patients with MACCEs than those without them (77 vs. 68 mL/m2 , p = 0.048; 23.5 vs. 18.0%, p = 0.011, respectively). A high RV ESVI was associated with all-cause mortality (hazard ratio [HR] per value of 10 higher ESVI = 1.10, p = 0.03). A high RVMI was also associated with all-cause mortality (HR per increase of 5 mL/m2 RVMI = 1.75, p < 0.001).After adjusting for age and sex, only RVMI remained a significant predictor of MACCEs and all-cause mortality (p < 0.05 for both). After adjusting for multiple clinical variables, RVMI remained significantly associated with all-cause mortality (p = 0.005). @*Conclusion@#RVMI measured on preoperative cardiac MRI was an independent predictor of long-term outcomes in patients who underwent TV surgery for functional TR.
RESUMO
Objective@#We implemented a novel resectable myocardial model for mock myectomy using a hybrid method of threedimensional (3D) printing and silicone molding for patients with apical hypertrophic cardiomyopathy (ApHCM). @*Materials and Methods@#From January 2019 through May 2020, 3D models from three patients with ApHCM were generated using the end-diastolic cardiac CT phase image. After computer-aided designing of measures to prevent structural deformation during silicone injection into molding, 3D printing was performed to reproduce anatomic details and molds for the left ventricular (LV) myocardial mass. We compared the myocardial thickness of each cardiac segment and the LV myocardial mass and cavity volumes between the myocardial model images and cardiac CT images. The surgeon performed mock surgery, and we compared the volume and weight of the resected silicone and myocardium. @*Results@#During the mock surgery, the surgeon could determine an ideal site for the incision and the optimal extent of myocardial resection. The mean differences in the measured myocardial thickness of the model (0.3, 1.0, 6.9, and 7.3 mm in the basal, midventricular, apical segments, and apex, respectively) and volume of the LV myocardial mass and chamber (36.9 mL and 14.8 mL, 2.9 mL and -9.4 mL, and 6.0 mL and -3.0 mL in basal, mid-ventricular and apical segments, respectively) were consistent with cardiac CT. The volume and weight of the resected silicone were similar to those of the resected myocardium (6 mL [6.2 g] of silicone and 5 mL [5.3 g] of the myocardium in patient 2; 12 mL [12.5 g] of silicone and 11.2 mL [11.8 g] of the myocardium in patient 3). @*Conclusion@#Our 3D model created using hybrid 3D printing and silicone molding may be useful for determining the extent of surgery and planning surgery guided by a rehearsal platform for ApHCM.
RESUMO
Objective@#Arrhythmogenic mitral valve prolapse (MVP) is an important cause of sudden cardiac death characterized by fibrosis of the papillary muscles or left ventricle (LV) wall, and an association between late gadolinium enhancement (LGE) of the LV papillary muscles and ventricular arrhythmia in MVP has been reported. However, LGE of the papillary muscles may be observed in other causes of mitral regurgitation, and it is not limited to patients with MVP. This study was to evaluate the association of LGE of the LV papillary muscles or ventricular wall on cardiac magnetic resonance imaging (CMR) and ventricular arrhythmia in patients with mitral regurgitation. @*Materials and Methods@#This study included 88 patients (mean age ± standard deviation, 58.3 ± 12.0 years; male, 42%) with mitral regurgitation who underwent CMR. They were allocated to the MVP (n = 43) and non-MVP (n = 45) groups, and their LGE images on CMR, clinical characteristics, echocardiographic findings, and presence of arrhythmia were compared. @*Results@#LV myocardial wall enhancement was more frequent in the MVP group than in the non-MVP group (28% vs. 11%, p = 0.046). Papillary muscle enhancement was observed in 7 (7.9%) patients. Of the 43 patients with MVP, 15 (34.8%) showed LGE in the papillary muscles or LV myocardium, including 12 (27.9%) with LV myocardial wall enhancement and 4 (9.3%) with papillary muscle enhancement. One patient with bilateral diffuse papillary muscle enhancement experienced sudden cardiac arrest due to ventricular fibrillation. Univariable logistic regression analysis showed that high systolic blood pressure (BP; odds ratio [OR], 1.05; 95% confidence interval [CI], 1.01–1.09; p = 0.027) and ventricular arrhythmia (OR, 6.84; 95% CI, 1.29–36.19; p = 0.024) were significantly associated with LGE of the papillary muscles. @*Conclusion@#LGE of the papillary muscles was present not only in patients with MVP, but also in patients with other etiologies of mitral regurgitation, and it was associated with high systolic BP and ventricular arrhythmia. Papillary muscle enhancement on CMR should not be overlooked.
RESUMO
Cardiovascular computed tomography (CT) is among the most active fields with ongoing technical innovation related to image acquisition and analysis. Artificial intelligence can be incorporated into various clinical applications of cardiovascular CT, including imaging of the heart valves and coronary arteries, as well as imaging to evaluate myocardial function and congenital heart disease. This review summarizes the latest research on the application of deep learning to cardiovascular CT. The areas covered range from image quality improvement to automatic analysis of CT images, including methods such as calcium scoring, image segmentation, and coronary artery evaluation.
RESUMO
Behçet’s disease is a chronic inflammatory disorder involving vessels of various sizes and organs, including the skin, joints, gastrointestinal tract, lungs, and cardiovascular system. The etiology of Behçet’s disease is unclear, and clinical diagnosis is important in the absence of definitive laboratory or pathological findings diagnostic of Behçet’s disease. Cardiac involvement is rare but might present as endocarditis, myocarditis, pericarditis, or intracardiac thrombosis. This report presents a case of Behçet’s disease involving the heart in a 22-year-old man with unusual manifestations of right ventricular fibrosis and intracardiac thrombosis. Cardiac magnetic resonance imaging revealed multiple intracardiac thrombi and delayed diffuse subendocardial enhancement involving the right ventricle. No peripheral eosinophilia was detected. Endomyocardial biopsy showed mixed inflammatory cell infiltrates. Based on the patient’s clinical history of oral ulcer and arthritis, a diagnosis of Behçet’s disease was made considering the clinical, radiological, and histological findings. Intracardiac thrombi and endomyocardial fibrosis are rare manifestations of Behçet’s disease, and the diagnosis is often a clinical challenge. Early diagnosis is important for appropriate management. Behçet’s disease should be considered in the differential diagnosis of patients with intracardiac thrombosis and endomyocardial fibrosis of the right chamber.
RESUMO
Cardiac computed tomography (CT) and cardiac magnetic resonance imaging (CMR) can reveal the detailed anatomy and function of the tricuspid valve and right ventricle (RV). Quantification of tricuspid regurgitation (TR) and analysis of RV function have prognostic implications. With the recently available transcatheter treatment options for diseases of the tricuspid valve, evaluation of the tricuspid valve using CT and CMR has become important in terms of patient selection and procedural guidance. Moreover, CT enables post-procedural investigation of the causes of valve dysfunction, such as pannus or thrombus. This review describes the anatomy of the tricuspid valve and CT and CMR imaging protocols for right heart evaluation, including RV function and TR analyses. We also demonstrate the pre-procedural planning for transcatheter treatment of TR and imaging of postoperative complications using CT.
RESUMO
Objective@#This study aimed to validate a deep learning-based fully automatic calcium scoring (coronary artery calcium [CAC]_auto) system using previously published cardiac computed tomography (CT) cohort data with the manually segmented coronary calcium scoring (CAC_hand) system as the reference standard. @*Materials and Methods@#We developed the CAC_auto system using 100 co-registered, non-enhanced and contrast-enhanced CT scans. For the validation of the CAC_auto system, three previously published CT cohorts (n = 2985) were chosen to represent different clinical scenarios (i.e., 2647 asymptomatic, 220 symptomatic, 118 valve disease) and four CT models. The performance of the CAC_auto system in detecting coronary calcium was determined. The reliability of the system in measuring the Agatston score as compared with CAC_hand was also evaluated per vessel and per patient using intraclass correlation coefficients (ICCs) and Bland-Altman analysis. The agreement between CAC_auto and CAC_hand based on the cardiovascular risk stratification categories (Agatston score: 0, 1–10, 11–100, 101–400, > 400) was evaluated. @*Results@#In 2985 patients, 6218 coronary calcium lesions were identified using CAC_hand. The per-lesion sensitivity and falsepositive rate of the CAC_auto system in detecting coronary calcium were 93.3% (5800 of 6218) and 0.11 false-positive lesions per patient, respectively. The CAC_auto system, in measuring the Agatston score, yielded ICCs of 0.99 for all the vessels (left main 0.91, left anterior descending 0.99, left circumflex 0.96, right coronary 0.99). The limits of agreement between CAC_auto and CAC_hand were 1.6 ± 52.2. The linearly weighted kappa value for the Agatston score categorization was 0.94. The main causes of false-positive results were image noise (29.1%, 97/333 lesions), aortic wall calcification (25.5%, 85/333 lesions), and pericardial calcification (24.3%, 81/333 lesions). @*Conclusion@#The atlas-based CAC_auto empowered by deep learning provided accurate calcium score measurement as compared with manual method and risk category classification, which could potentially streamline CAC imaging workflows.
RESUMO
Objective@#To investigate the prognostic value of preoperative cardiac magnetic resonance imaging (MRI) for long-term major adverse cardiac and cerebrovascular events (MACCEs) in patients undergoing tricuspid valve (TV) surgery for functional tricuspid regurgitation (TR). @*Materials and Methods@#The preoperative cardiac MR images, New York Heart Association functional class, comorbidities, and clinical events of 78 patients (median [interquartile range], 59 [51–66.3] years, 28.2% male) who underwent TV surgery for functional TR were comprehensively reviewed. Cox proportional hazards analyses were performed to assess the associations of clinical and imaging parameters with MACCEs and all-cause mortality. @*Results@#For the median follow-up duration of 5.4 years (interquartile range, 1.2–6.6), MACCEs and all-cause mortality were 51.3% and 23.1%, respectively. The right ventricular (RV) end-systolic volume index (ESVI) and the systolic RV mass index (RVMI) were higher in patients with MACCEs than those without them (77 vs. 68 mL/m2 , p = 0.048; 23.5 vs. 18.0%, p = 0.011, respectively). A high RV ESVI was associated with all-cause mortality (hazard ratio [HR] per value of 10 higher ESVI = 1.10, p = 0.03). A high RVMI was also associated with all-cause mortality (HR per increase of 5 mL/m2 RVMI = 1.75, p < 0.001).After adjusting for age and sex, only RVMI remained a significant predictor of MACCEs and all-cause mortality (p < 0.05 for both). After adjusting for multiple clinical variables, RVMI remained significantly associated with all-cause mortality (p = 0.005). @*Conclusion@#RVMI measured on preoperative cardiac MRI was an independent predictor of long-term outcomes in patients who underwent TV surgery for functional TR.
RESUMO
Objective@#We implemented a novel resectable myocardial model for mock myectomy using a hybrid method of threedimensional (3D) printing and silicone molding for patients with apical hypertrophic cardiomyopathy (ApHCM). @*Materials and Methods@#From January 2019 through May 2020, 3D models from three patients with ApHCM were generated using the end-diastolic cardiac CT phase image. After computer-aided designing of measures to prevent structural deformation during silicone injection into molding, 3D printing was performed to reproduce anatomic details and molds for the left ventricular (LV) myocardial mass. We compared the myocardial thickness of each cardiac segment and the LV myocardial mass and cavity volumes between the myocardial model images and cardiac CT images. The surgeon performed mock surgery, and we compared the volume and weight of the resected silicone and myocardium. @*Results@#During the mock surgery, the surgeon could determine an ideal site for the incision and the optimal extent of myocardial resection. The mean differences in the measured myocardial thickness of the model (0.3, 1.0, 6.9, and 7.3 mm in the basal, midventricular, apical segments, and apex, respectively) and volume of the LV myocardial mass and chamber (36.9 mL and 14.8 mL, 2.9 mL and -9.4 mL, and 6.0 mL and -3.0 mL in basal, mid-ventricular and apical segments, respectively) were consistent with cardiac CT. The volume and weight of the resected silicone were similar to those of the resected myocardium (6 mL [6.2 g] of silicone and 5 mL [5.3 g] of the myocardium in patient 2; 12 mL [12.5 g] of silicone and 11.2 mL [11.8 g] of the myocardium in patient 3). @*Conclusion@#Our 3D model created using hybrid 3D printing and silicone molding may be useful for determining the extent of surgery and planning surgery guided by a rehearsal platform for ApHCM.
RESUMO
Objective@#Arrhythmogenic mitral valve prolapse (MVP) is an important cause of sudden cardiac death characterized by fibrosis of the papillary muscles or left ventricle (LV) wall, and an association between late gadolinium enhancement (LGE) of the LV papillary muscles and ventricular arrhythmia in MVP has been reported. However, LGE of the papillary muscles may be observed in other causes of mitral regurgitation, and it is not limited to patients with MVP. This study was to evaluate the association of LGE of the LV papillary muscles or ventricular wall on cardiac magnetic resonance imaging (CMR) and ventricular arrhythmia in patients with mitral regurgitation. @*Materials and Methods@#This study included 88 patients (mean age ± standard deviation, 58.3 ± 12.0 years; male, 42%) with mitral regurgitation who underwent CMR. They were allocated to the MVP (n = 43) and non-MVP (n = 45) groups, and their LGE images on CMR, clinical characteristics, echocardiographic findings, and presence of arrhythmia were compared. @*Results@#LV myocardial wall enhancement was more frequent in the MVP group than in the non-MVP group (28% vs. 11%, p = 0.046). Papillary muscle enhancement was observed in 7 (7.9%) patients. Of the 43 patients with MVP, 15 (34.8%) showed LGE in the papillary muscles or LV myocardium, including 12 (27.9%) with LV myocardial wall enhancement and 4 (9.3%) with papillary muscle enhancement. One patient with bilateral diffuse papillary muscle enhancement experienced sudden cardiac arrest due to ventricular fibrillation. Univariable logistic regression analysis showed that high systolic blood pressure (BP; odds ratio [OR], 1.05; 95% confidence interval [CI], 1.01–1.09; p = 0.027) and ventricular arrhythmia (OR, 6.84; 95% CI, 1.29–36.19; p = 0.024) were significantly associated with LGE of the papillary muscles. @*Conclusion@#LGE of the papillary muscles was present not only in patients with MVP, but also in patients with other etiologies of mitral regurgitation, and it was associated with high systolic BP and ventricular arrhythmia. Papillary muscle enhancement on CMR should not be overlooked.
RESUMO
Cardiovascular computed tomography (CT) is among the most active fields with ongoing technical innovation related to image acquisition and analysis. Artificial intelligence can be incorporated into various clinical applications of cardiovascular CT, including imaging of the heart valves and coronary arteries, as well as imaging to evaluate myocardial function and congenital heart disease. This review summarizes the latest research on the application of deep learning to cardiovascular CT. The areas covered range from image quality improvement to automatic analysis of CT images, including methods such as calcium scoring, image segmentation, and coronary artery evaluation.
RESUMO
Purpose@#This study aimed to evaluate changes of subprosthetic pannus on cardiac CT and determine its relationship to echocardiographic findings in patients with mechanical aortic valve replacement (AVR). @*Materials and Methods@#Between April 2011 and November 2017, 17 AVR patients (56.8 ± 8.9 years, 12% male) who showed pannus formation on CT and had undergone both follow-up CT and echocardiography were included. The mean interval from AVR to the date of pannus detection was 10.5 ± 7.1 years. In the initial and follow-up CT and echocardiography, the pannus extent and echocardiographic parameters were compared using paired t-tests. The relationship between the opening angle of the prosthetic valve and the pannus extent was evaluated using Pearson correlation analysis. @*Results@#The pannus extent was significantly increased on CT (p < 0.05). The peak velocity (3.9 ± 0.8 m/s vs. 4.2 ± 0.8 m/s, p = 0.03) and mean pressure gradient (36.4 ± 15.5 mm Hg vs. 42.1 ± 15.8 mm Hg, p = 0.03) were significantly increased. The mean opening angles of the mechanical aortic leaflets were slightly decreased, but there was no statistical significance (73.1 ± 8.3° vs. 69.4 ± 12.1°, p = 0.12). The opening angle of the prosthetic leaflets was inversely correlated with the pannus extent (r = −0.57, p < 0.001). @*Conclusion@#The pannus extent increases over time, increasing transvalvular peak velocity and the pressure gradient. CT can be used to evaluate the pannus extent associated with hemodynamic changes that need to be managed by surgical intervention.
RESUMO
Background and Objectives@#Leaflet thrombosis after transcatheter aortic valve replacement (TAVR) has been reported recently, whereas thrombus formation in sinus of Valsalva has yet to be fully evaluated. This study describes clinical and cardiac computed tomography (CT) findings of patients with sinus of Valsalva thrombosis. @*Methods@#Between March 2011 and Aug 2019, 192 patients underwent cardiac CT after TAVR. After a retrospective review of CT images, 9 patients (82 years, male:female=2:7) who had sinus of Valsalva thrombosis identified by cardiac CT were selected for this study. Patient demographics, interval between TAVR and cardiac CT scan, location and CT attenuation of sinus of Valsalva thrombosis, and presence of concurrent leaflet thrombosis were evaluated. @*Results@#The median interval between TAVR and cardiac CT was 11 days. Sinus of Valsalva thrombosis was frequently detected in the non-coronary sinus (89%, 8/9), and predominantly located in the bottom of the sinus extending upward towards the sinotubular junction. Three patients had concomitant leaflet thrombosis, and 3 patients had subclinical embolic stroke noted on brain magnetic resonance imaging. All patients had been prescribed aspirin and clopidogrel after TAVR for at least 6 months without anticoagulants. @*Conclusions@#Cardiac CT after TAVR can detect sinus of Valsalva thrombosis, and attention should be paid to this potential source of subsequent systemic embolization.
RESUMO
Objective@#To evaluate the accuracy of a deep learning-based automated segmentation of the left ventricle (LV) myocardium using cardiac CT. @*Materials and Methods@#To develop a fully automated algorithm, 100 subjects with coronary artery disease were randomly selected as a development set (50 training / 20 validation / 30 internal test). An experienced cardiac radiologist generated the manual segmentation of the development set. The trained model was evaluated using 1000 validation set generated by an experienced technician. Visual assessment was performed to compare the manual and automatic segmentations. In a quantitative analysis, sensitivity and specificity were calculated according to the number of pixels where two three-dimensional masks of the manual and deep learning segmentations overlapped. Similarity indices, such as the Dice similarity coefficient (DSC), were used to evaluate the margin of each segmented masks. @*Results@#The sensitivity and specificity of automated segmentation for each segment (1–16 segments) were high (85.5– 100.0%). The DSC was 88.3 ± 6.2%. Among randomly selected 100 cases, all manual segmentation and deep learning masks for visual analysis were classified as very accurate to mostly accurate and there were no inaccurate cases (manual vs. deep learning: very accurate, 31 vs. 53; accurate, 64 vs. 39; mostly accurate, 15 vs. 8). The number of very accurate cases for deep learning masks was greater than that for manually segmented masks. @*Conclusion@#We present deep learning-based automatic segmentation of the LV myocardium and the results are comparable to manual segmentation data with high sensitivity, specificity, and high similarity scores.
RESUMO
The surgical technique of mitral valvuloplasty or transcatheter mitral valve (MV) replacement has been developed recently. Surgeons and interventionists require detailed anatomical information on the MV for the purpose of treatment planning. In this review, we discussed the anatomic features of the MV on CT and the method of evaluating the MV for treatment planning, as well as its preservation, for interventional procedures.