[Visualization of Borderline Coronary Artery Lesions by CT Angiography and Coronary Artery Disease Reporting and Data System]. / 관상동맥 질환 íŒë ê³¼ 자료 체계와 CT í˜ˆê´€ì¡°ì˜ìˆ ì—ì„œì˜ 경계성 관상동맥 병변.

Coronary artery disease (CAD) narrows vessel lumens at the sites of atherosclerosis, increasing the risk of myocardial ischemia or infarction. Early and accurate diagnosis of CAD is crucial to significantly improve prognosis and management. CT angiography (CTA) is a noninvasive imaging technique that enables assessment of vascular structure and stenosis with high resolution and contrast. Coronary CTA is useful in the diagnosis of CAD. Recently, the CAD-reporting and data system (CAD-RADS), a diagnostic classification system based on coronary CTA, has been developed to improve intervention efficacy in patients suspected of CAD. While the CAD-RAD is based on CTA, it includes borderline categories where interpreting the coronary artery status solely based on CTA findings may be challenging. This review introduces CTA findings that fall within the CAD-RADS categories that necessitate additional tests to decide to perform invasive coronary angiography and discusses appropriate management strategies.

Effects of Polybutylene Succinate Content on the Rheological Properties of Polylactic Acid/Polybutylene Succinate Blends and the Characteristics of Their Fibers.

Polylactic acid (PLA) and polybutylene succinate (PBS) are gaining prominence as environmentally friendly alternatives to petroleum-based polymers due to their inherent biodegradability. For their textile applications, this research is focused on exploring the effects of PBS content on the rheological properties of PLA/PBS blends and the characteristics of PLA/PBS blend fibers. PLA/PBS blends and fibers with varying PBS contents (0 to 10 wt.%) were prepared using melt-blending and spinning methods. Uniform morphologies of the PLA/PBS blends indicated that PBS was compatible with PLA, except at 10% PBS content, where phase separation occurred. The introduction of PBS reduced the complex viscosity of the blends, influencing fiber properties. Notably, PLA/PBS fibers with 7% PBS exhibited improved crystallinity, orientation factor, and elasticity (~16.58%), with a similar tensile strength to PLA fiber (~3.58 MPa). The results suggest that an optimal amount of PBS enhances alignment along the drawing direction and improves the molecular motion in PLA/PBS blend fiber. This study highlights the potential of strategically blending PBS to improve PLA fiber characteristics, promising advancement in textile applications.

Edge-Triggered Three-Dimensional Object Detection Using a LiDAR Ring.

Autonomous driving recognition technology that can quickly and accurately recognize even small objects must be developed in high-speed situations. This study proposes an object point extraction method using rule-based LiDAR ring data and edge triggers to increase both speed and performance. The LiDAR's ring information is interpreted as a digital pulse to remove the ground, and object points are extracted by detecting discontinuous edges of the z value aligned with the ring ID and azimuth. A bounding box was simply created using DBSCAN and PCA to check recognition performance from the extracted object points. Verification of the results of removing the ground and extracting points through Ring Edge was conducted using SemanticKITTI and Waymo Open Dataset, and it was confirmed that both F1 scores were superior to RANSAC. In addition, extracting bounding boxes of objects also showed higher PDR index performance when verified in open datasets, virtual driving environments, and actual driving environments.

2024 Consensus Statement on Coronary Stenosis and Plaque Evaluation in CT Angiography From the Asian Society of Cardiovascular Imaging-Practical Tutorial (ASCI-PT).

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.

Computed Tomography Radiomics for Preoperative Prediction of Spread Through Air Spaces in the Early Stage of Surgically Resected Lung Adenocarcinomas.

PURPOSE: To assess the added value of radiomics models from preoperative chest CT in predicting the presence of spread through air spaces (STAS) in the early stage of surgically resected lung adenocarcinomas using multiple validation datasets. MATERIALS AND METHODS: This retrospective study included 550 early-stage surgically resected lung adenocarcinomas in 521 patients, classified into training, test, internal validation, and temporal validation sets (n=211, 90, 91, and 158, respectively). Radiomics features were extracted from the segmented tumors on preoperative chest CT, and a radiomics score (Rad-score) was calculated to predict the presence of STAS. Diagnostic performance of the conventional model and the combined model, based on a combination of conventional and radiomics features, for the diagnosis of the presence of STAS were compared using the area under the curve (AUC) of the receiver operating characteristic curve. RESULTS: Rad-score was significantly higher in the STAS-positive group compared to the STAS-negative group in the training, test, internal, and temporal validation sets. The performance of the combined model was significantly higher than that of the conventional model in the training set {AUC: 0.784 [95% confidence interval (CI): 0.722-0.846] vs. AUC: 0.815 (95% CI: 0.759-0.872), p=0.042}. In the temporal validation set, the combined model showed a significantly higher AUC than that of the conventional model (p=0.001). The combined model showed a higher AUC than the conventional model in the test and internal validation sets, albeit with no statistical significance. CONCLUSION: A quantitative CT radiomics model can assist in the non-invasive prediction of the presence of STAS in the early stage of lung adenocarcinomas.

Changes in total volatile organic compound concentration in Seoul subway stations before (2019) and after (2021) the COVID-19 outbreak.

Volatile organic compounds (VOCs) are major air pollutants often designated as specific hazardous or toxic. This study analyzed the trends in concentration changes and influencing factors of VOCs in underground subway stations in the Seoul Metro before (2019) and after (2021) the COVID-19 pandemic. A total of 506 samples were collected from 253 stations on lines 1-8 between May 2019 and September 2021. Total VOC concentrations in Seoul Metro increased after the COVID-19 pandemic 3.8 times over. The deeper the underground station platform, the greater the difference in the VOC concentrations between 2019 and 2021, which was positively related. Average VOC concentration was the highest (52.8 µg/m3) at a depth of 25-30 m and the lowest (23.9 µg/m3) at a depth of < 10 m in 2019. In conclusion, excessive disinfection during the COVID-19 pandemic resulted in increased VOC concentrations in the Seoul Metro, especially in the deeper underground stations. Less frequent quarantine disinfection is recommended to improve air quality.

Aortic Annulus Detection Based on Deep Learning for Transcatheter Aortic Valve Replacement Using Cardiac Computed Tomography.

BACKGROUND: To propose a deep learning architecture for automatically detecting the complex structure of the aortic annulus plane using cardiac computed tomography (CT) for transcatheter aortic valve replacement (TAVR). METHODS: This study retrospectively reviewed consecutive patients who underwent TAVR between January 2017 and July 2020 at a tertiary medical center. Annulus Detection Permuted AdaIN network (ADPANet) based on a three-dimensional (3D) U-net architecture was developed to detect and localize the aortic annulus plane using cardiac CT. Patients (N = 72) who underwent TAVR between January 2017 and July 2020 at a tertiary medical center were enrolled. Ground truth using a limited dataset was delineated manually by three cardiac radiologists. Training, tuning, and testing sets (70:10:20) were used to build the deep learning model. The performance of ADPANet for detecting the aortic annulus plane was analyzed using the root mean square error (RMSE) and dice similarity coefficient (DSC). RESULTS: In this study, the total dataset consisted of 72 selected scans from patients who underwent TAVR. The RMSE and DSC values for the aortic annulus plane using ADPANet were 55.078 ± 35.794 and 0.496 ± 0.217, respectively. CONCLUSION: Our deep learning framework was feasible to detect the 3D complex structure of the aortic annulus plane using cardiac CT for TAVR. The performance of our algorithms was higher than other convolutional neural networks.

[Expert Opinion Questionnaire About Chest CT Scan Using A Negative Pressure Isolation Strecher in COVID-19 Patients: Image Quality and Infection Risk]. / COVID-19 환자에서 음압격리들것을 이용한 흉부 CT 검사에 대한 ì „ë¬¸ê°€ 의견 설문: 영상품질과 감염위험.

Purpose: To survey perceptions of certified physicians on the protocol of chest CT in patients with coronavirus (COVID-19) using a negative pressure isolation stretcher (NPIS). Materials and Methods: This study collected questionnaire responses from a total of 27 certified physicians who had previously performed chest CT with NPIS in COVID-19 isolation hospitals. Results: The nine surveyed hospitals performed an average of 116 chest CT examinations with NPIS each year. Of these, an average of 24 cases (21%) were contrast chest CT. Of the 9 pulmonologists we surveyed, 5 (56%) agreed that patients who showed abnormalities in serum D-dimer required contrast chest CT. All 9 surveyed radiologists agreed that the image quality of the chest CT with NPIS was sufficient for CT image interpretation regarding pneumonia or pulmonary embolism. Furthermore, in our 9 surveyed infectionologists, 5 (56%) agreed that a risk of secondary infection in the CT room after temporary opening of NPIS could be prevented through a process of disinfection. Conclusion: Experienced physicians considered that the effects of NIPS on chest CT image quality was minimal in patients with COVID-19, and the risk of CT room contamination was easily controlled.

Two Years of Experience and Methodology of Korean COVID-19 Living Clinical Practice Guideline Development.

BACKGROUND: In Korea, during the early phase of the coronavirus disease 2019 (COVID-19) pandemic, we responded to the uncertainty of treatments under various conditions, consistently playing catch up with the speed of evidence updates. Therefore, there was high demand for national-level evidence-based clinical practice guidelines for clinicians in a timely manner. We developed evidence-based and updated living recommendations for clinicians through a transparent development process and multidisciplinary expert collaboration. METHODS: The National Evidence-based Healthcare Collaborating Agency (NECA) and the Korean Academy of Medical Sciences (KAMS) collaborated to develop trustworthy Korean living guidelines. The NECA-supported methodological sections and 8 professional medical societies of the KAMS worked with clinical experts, and 31 clinicians were involved annually. We developed a total of 35 clinical questions, including medications, respiratory/critical care, pediatric care, emergency care, diagnostic tests, and radiological examinations. RESULTS: An evidence-based search for treatments began in March 2021 and monthly updates were performed. It was expanded to other areas, and the search interval was organized by a steering committee owing to priority changes. Evidence synthesis and recommendation review was performed by researchers, and living recommendations were updated within 3-4 months. CONCLUSION: We provided timely recommendations on living schemes and disseminated them to the public, policymakers and various stakeholders using webpages and social media. Although the output was successful, there were some limitations. The rigor of development issues, urgent timelines for public dissemination, education for new developers, and spread of several new COVID-19 variants have worked as barriers. Therefore, we must prepare systematic processes and funding for future pandemics.

Electronic Cigarette or Vaping-Associated Lung Injury Manifested as Acute Eosinophilic Pneumonia: A Case Report.

Electronic cigarette or vaping-associated lung injury (EVALI) is a disease defined by lung injuries caused by e-cigarette use. It predominantly manifests in forms of organized pneumonia or diffuse alveolar damage but rarely as acute eosinophilic pneumonia (AEP). This report describes a 34-year-old male with acute respiratory symptoms and a vaping history of only nicotine. Chest CT revealed peripheral distributing multiple patchy consolidations and ground-glass opacities dominant in both lower lobes, bilateral diffuse interlobular septal thickening, and bilateral pleural effusion without cardiomegaly. Bronchoalveolar lavage fluids showed increased eosinophilia levels, while infectious laboratory results were all negative, enabling the diagnosis of both AEP and EVALI. Herein, we report a rare case of only-nicotine vaping EVALI manifested as AEP.

Indoor exposure assessment for levels of dust mite and total volatile organic compounds (TVOCs) in living houses.

The purpose of this study is to measure the levels of dust mites (Dermatophagoides farina group 1 [Der f1] and Dermatophagoides pteronyssinus group 1 [Der p1]) and total volatile organic compounds (TVOCs) in the resident environments with living conditions such as the number of ventilation; the number of window, floor, and temperature; and relative humidity (RH) from vulnerable class in South Korea. Information on residents is designed to be prepared by residents on their general characteristics (daily residence time, heating and cooking type, and cleaning on the day of sampling). Dust mites levels ranged from 24.0 to 1087.5 ng/g with a mean of 215.4 ng/g for Der f1 and from 0.6 to 489.9 ng/g with a mean of 489.9 ng/g for Der p1. Total TVOC levels ranged from 15.3 to 1642.1 µg/m3 with a mean of 219.7 µg/m3. The correlation analysis showed a positive association between Der f1 levels and xylene levels in fall (r = 0.49, r < 0.05) of this study.

Multicentre external validation of a commercial artificial intelligence software to analyse chest radiographs in health screening environments with low disease prevalence.

OBJECTIVES: To externally validate the performance of a commercial AI software program for interpreting CXRs in a large, consecutive, real-world cohort from primary healthcare centres. METHODS: A total of 3047 CXRs were collected from two primary healthcare centres, characterised by low disease prevalence, between January and December 2018. All CXRs were labelled as normal or abnormal according to CT findings. Four radiology residents read all CXRs twice with and without AI assistance. The performances of the AI and readers with and without AI assistance were measured in terms of area under the receiver operating characteristic curve (AUROC), sensitivity, and specificity. RESULTS: The prevalence of clinically significant lesions was 2.2% (68 of 3047). The AUROC, sensitivity, and specificity of the AI were 0.648 (95% confidence interval [CI] 0.630-0.665), 35.3% (CI, 24.7-47.8), and 94.2% (CI, 93.3-95.0), respectively. AI detected 12 of 41 pneumonia, 3 of 5 tuberculosis, and 9 of 22 tumours. AI-undetected lesions tended to be smaller than true-positive lesions. The readers' AUROCs ranged from 0.534-0.676 without AI and 0.571-0.688 with AI (all p values < 0.05). For all readers, the mean reading time was 2.96-10.27 s longer with AI assistance (all p values < 0.05). CONCLUSIONS: The performance of commercial AI in these high-volume, low-prevalence settings was poorer than expected, although it modestly boosted the performance of less-experienced readers. The technical prowess of AI demonstrated in experimental settings and approved by regulatory bodies may not directly translate to real-world practice, especially where the demand for AI assistance is highest. KEY POINTS: • This study shows the limited applicability of commercial AI software for detecting abnormalities in CXRs in a health screening population. • When using AI software in a specific clinical setting that differs from the training setting, it is necessary to adjust the threshold or perform additional training with such data that reflects this environment well. • Prospective test accuracy studies, randomised controlled trials, or cohort studies are needed to examine AI software to be implemented in real clinical practice.

Identifying fragile calcifications of the aortic valve in transcatheter aortic valve replacement: iodine concentration of aortic valvular calcification by spectral CT.

OBJECTIVE: To demonstrate the relationship between spectral computed tomography (CT) measured iodine concentration and strength of aortic valvular calcification (AVC) in patients with aortic valve stenosis (AVS). METHODS: A retrospective study was performed on patients who underwent transcatheter aortic valve replacement (TAVR) for symptomatic AVS and underwent both pre and postprocedural electrocardiogram gated CT scans using a spectral CT system. Preprocedural CT was used to evaluate the volume and iodine concentration (IC) in the AVC. Postprocedural CT data were used to calculate the volume reduction percentage (VRP) of AVC. Multiple linear regression analysis was used to identify the independent variables related to the VRP in AVCs. RESULTS: A total of 94 AVCs were selected from 22 patients. The mean volume and IC of the AVCs before TAVR were 0.37 mL ± 0.15 mL and 7 mg/mL ± 10.5 mg/mL, respectively. After TAVR, a median VRP of all 94 AVCs was 18.5%. Multiple linear regression analysis showed that the IC was independently associated with the VRP (coefficient = 1.64, p < 0.001). When an optimal IC cutoff point was set at 4 mg/mL in the assessment of a fragile AVC which showed the VRP was > 18.5%, the sensitivity was 63%; specificity, 91%; positive predictive value, 88%; and negative predictive value, 71%. CONCLUSIONS: When using spectral CT to prepare the TAVR, measuring the IC of the AVC may be useful to assess the probability of AVC deformity after TAVR. KEY POINTS: • A dual-layer detector-based spectral CT enables quantifying iodine of contrast media in the aortic valve calcification (AVC) on contrast-enhanced CT images. • The AVC including iodine of contrast media on contrast-enhanced CT image may have loose compositions, associated with the deformity of AVC after TAVR. • Measuring the iodine concentration in AVC may have the potential to assess the probability of AVC deformity, which may be associated with the outcome and complications after TAVR.2.

Association between levels of radon and bioaerosols (bacteria and fungi) by living conditions.

This study aimed to measure the levels of airborne radon Rn and bioaerosols - culturable airborne bacteria (CAB) and culturable airborne fungi (CAF)-in South Korea's residential environments, considering living conditions such as the number of ventilations, number of windows, floors, temperature, and relative humidity. . The range of Rn levels was 0.43-7.439 pCi/L with a median of 0.70 pCi/L. The CAB levels were 239-488 colony-forming unit (CFU)/m3 with a median of 309 CFU/m3, and CAF levels were 174-366 CFU/m3 with a median of 233 CFU/m3. Thus, this study found that semi-basement residential indoor environments negatively affected Rn and bioaerosol levels, and living in such residences resulted in high health condition scores on the bad side. Given the correlation between airborne Rn and bioaerosol levels, further large-scale studies are needed to identify more reliable and representative of research.

Evaluation of fully automated commercial software for Agatston calcium scoring on non-ECG-gated low-dose chest CT with different slice thickness.

OBJECTIVES: To evaluate commercial deep learning-based software for fully automated coronary artery calcium (CAC) scoring on non-electrocardiogram (ECG)-gated low-dose CT (LDCT) with different slice thicknesses compared with manual ECG-gated calcium-scoring CT (CSCT). METHODS: This retrospective study included 567 patients who underwent both LDCT and CSCT. All LDCT images were reconstructed with a 2.5-mm slice thickness (LDCT2.5-mm), and 453 LDCT scans were reconstructed with a 1.0-mm slice thickness (LDCT1.0-mm). Automated CAC scoring was performed on CSCT (CSCTauto), LDCT1.0-mm, and LDCT2.5-mm images. The reliability of CSCTauto, LDCT1.0-mm, and LDCT2.5-mm was compared with manual CSCT scoring (CSCTmanual) using intraclass correlation coefficients (ICCs) and Bland-Altman analysis. Agreement, in CAC severity category, was analyzed using weighted kappa statistics. Diagnostic performance at various Agatston score cutoffs was also calculated. RESULTS: CSCTauto, LDCT1.0-mm, and LDCT2.5-mm demonstrated excellent agreement with CSCTmanual (ICC [95% confidence interval, CI]: 1.000 [1.000, 1.000], 0.937 [0.917, 0.952], and 0.955 [0.946, 0.963], respectively). The mean difference with 95% limits of agreement was lower with LDCT1.0-mm than with LDCT2.5-mm (19.94 [95% CI, -244.0, 283.9] vs. 45.26 [-248.2, 338.7]). Regarding CAC severity, LDCT1.0-mm achieved almost perfect agreement, and LDCT2.5-mm achieved substantial agreement (kappa [95% CI]: 0.809 [0.776, 0.838], 0.776 [0.740, 0.809], respectively). Diagnostic performance for detecting Agatston score ≥ 400 was also higher with LDCT1.0-mm than with LDCT2.5-mm (F1 score, 0.929 vs. 0.855). CONCLUSIONS: Fully automated CAC-scoring software with both CSCT and LDCT yielded excellent reliability and agreement with CSCTmanual. LDCT1.0-mm yielded more accurate Agatston scoring than LDCT2.5-mm using fully automated commercial software. KEY POINTS: • Total Agatston scores and all vessels of CSCTauto, LDCT1.0-mm, and LDCT2.5-mm demonstrated excellent agreement with CSCTmanual (all ICC > 0.85). • The diagnostic performance for detecting all Agatston score cutoffs was better with LDCT1.0-mm than with LDCT2.5-mm. • This automated software yielded a lower degree of underestimation compared with methods described in previous studies, and the degree of underestimation was lower with LDCT1.0-mm than with LDCT2.5-mm.

Solitary Pulmonary Capillary Hemangioma: CT and PET-CT Features with Clinicopathologic Correlation.

The aim of this study was to evaluate the CT and PET-CT features of solitary pulmonary capillary hemangioma (SPCH) with clinicopathologic correlations. This retrospective study included 17 patients with histologically proven SPCH from four tertiary institutions. The clinical, pathological and imaging findings of SPCH were reviewed. The CT features assessed included lesion location, size, density, contour, margin, enhancement, presence of air bronchogram, perivascular lucency and pleural retraction, and 18F-fluorodeoxyglucose uptake on PET-CT. Changes in the size during the follow-up period were also evaluated. Imaging features were correlated with the clinicopathologic findings. The mean age of the patients was 47 years (range 30-60 years). All SPCHs were incidentally detected during screening CT examinations (n = 13, 76%) or during cancer work-up (n = 4, 24%). Most SPCHs appeared as part-solid nodules (n = 15, 88%), the remaining appeared as a pure ground-glass nodule or a pure solid nodule, respectively. Most had smooth contours (n = 16, 94%), while one had a lobulated contour. Nine SPCHs (53%) showed ill-defined margins. Air bronchogram was present in ten (59%) SPCHs, and perivascular lucency in two (12%). All SPCHs exhibited hypoattenuation on contrast-enhanced CT and hypometabolism on PET-CT. During the follow-up period (mean 14.8 ± 17.7 months), the lesions showed no change in size or density in ten SPCHs (59%), decreased or fluctuation in size and density in three (18%). SPCH is often incidentally detected in young and middle-aged adults, commonly as an ill-defined part-solid nodule that may accompany air bronchogram, perivascular lucency, and fluctuation in size or density on CT and hypometabolism on PET-CT.

[Korean Clinical Imaging Guidelines for Justification of Diagnostic Imaging Study for COVID-19]. / 한국형 COVID-19 흉부영상 진단 시행 가이드라인.

To develop Korean coronavirus disease (COVID-19) chest imaging justification guidelines, eight key questions were selected and the following recommendations were made with the evidence-based clinical imaging guideline adaptation methodology. It is appropriate not to use chest imaging tests (chest radiograph or CT) for the diagnosis of COVID-19 in asymptomatic patients. If reverse transcription-polymerase chain reaction testing is not available or if results are delayed or are initially negative in the presence of symptoms suggestive of COVID-19, chest imaging tests may be considered. In addition to clinical evaluations and laboratory tests, chest imaging may be contemplated to determine hospital admission for asymptomatic or mildly symptomatic unhospitalized patients with confirmed COVID-19. In hospitalized patients with confirmed COVID-19, chest imaging may be advised to determine or modify treatment alternatives. CT angiography may be considered if hemoptysis or pulmonary embolism is clinically suspected in a patient with confirmed COVID-19. For COVID-19 patients with improved symptoms, chest imaging is not recommended to make decisions regarding hospital discharge. For patients with functional impairment after recovery from COVID-19, chest imaging may be considered to distinguish a potentially treatable disease.

Left Atrial Dysfunction, Fibrosis and the Risk of Thromboembolism in Patients With Paroxysmal and Persistent Atrial Fibrillation.

Background and Objectives: Left atrial (LA) fibrosis is an important component of the arrhythmogenic substrate and is related to LA dysfunction in patients with atrial fibrillation (AF). However, its relationship with functional changes and the risk of thrombus in patients with paroxysmal AF (PAF) and persistent AF (PeAF) remains unclear. Methods: We included 139 patients with preprocedural cardiac magnetic resonance imaging (CMR) and transesophageal echocardiography (TEE) for the first AF catheter ablation. Spontaneous echo contrast (SEC) and multiple parameters of LA were measured from TEE and CMR. LA fibrosis was evaluated by late gadolinium enhancement of LA (LA-LGE) of CMR. Results: The presence of SEC was higher in patients with PeAF than in patients with PAF (26.4% vs. 11.9%, p=0.03). The patients with SEC had more enlarged LA size and impaired function of LA and LAA, regardless of AF type. However, the area of LA-LGE was more extensive in patients with SEC in PeAF (27.5±15.9 vs. 20.1±10.3, p=0.033), not in PAF. In PAF, maximal LA volume index was closely related to the presence of SEC with marginal trend toward significance (odd ratio [OR], 1.07; 95% confidence interval [CI], 0.99-1.16; p=0.072). Whereas, a larger area of LA-LGE and lower emptying flux of LA appendage were independently related with SEC (OR, 1.10; 95% CI, 1.0-1.20; p=0.049 and OR, 0.93; 95% CI, 0.86-0.99; p=0.022, respectively) after adjusting related cardiovascular risk factors of SEC. Conclusions: In this study, we suggest that the risk of thrombus is provoked by LA enlargement with dysfunction in early-stage AF and by stiffened LA with fibrosis rather than LA size when it becomes PeAF.

Efficient Segmentation for Left Atrium With Convolution Neural Network Based on Active Learning in Late Gadolinium Enhancement Magnetic Resonance Imaging.

BACKGROUND: To propose fully automatic segmentation of left atrium using active learning with limited dataset in late gadolinium enhancement in cardiac magnetic resonance imaging (LGE-CMRI). METHODS: An active learning framework was developed to segment the left atrium in cardiac LGE-CMRI. Patients (n = 98) with atrial fibrillation from the Korea University Anam Hospital were enrolled. First, 20 cases were delineated for ground truths by two experts and used for training a draft model. Second, the 20 cases from the first step and 50 new cases, corrected in a human-in-the-loop manner after predicting using the draft model, were used to train the next model; all 98 cases (70 cases from the second step and 28 new cases) were trained. An additional 20 LGE-CMRI were evaluated in each step. RESULTS: The Dice coefficients for the three steps were 0.85 ± 0.06, 0.89 ± 0.02, and 0.90 ± 0.02, respectively. The biases (95% confidence interval) in the Bland-Altman plots of each step were 6.36% (-14.90-27.61), 6.21% (-9.62-22.03), and 2.68% (-8.57-13.93). Deep active learning-based annotation times were 218 ± 31 seconds, 36.70 ± 18 seconds, and 36.56 ± 15 seconds, respectively. CONCLUSION: Deep active learning reduced annotation time and enabled efficient training on limited LGE-CMRI.

Artificial Intelligence-Based Identification of Normal Chest Radiographs: A Simulation Study in a Multicenter Health Screening Cohort.

OBJECTIVE: This study aimed to investigate the feasibility of using artificial intelligence (AI) to identify normal chest radiography (CXR) from the worklist of radiologists in a health-screening environment. MATERIALS AND METHODS: This retrospective simulation study was conducted using the CXRs of 5887 adults (mean age ± standard deviation, 55.4 ± 11.8 years; male, 4329) from three health screening centers in South Korea using a commercial AI (Lunit INSIGHT CXR3, version 3.5.8.8). Three board-certified thoracic radiologists reviewed CXR images for referable thoracic abnormalities and grouped the images into those with visible referable abnormalities (identified as abnormal by at least one reader) and those with clearly visible referable abnormalities (identified as abnormal by at least two readers). With AI-based simulated exclusion of normal CXR images, the percentages of normal images sorted and abnormal images erroneously removed were analyzed. Additionally, in a random subsample of 480 patients, the ability to identify visible referable abnormalities was compared among AI-unassisted reading (i.e., all images read by human readers without AI), AI-assisted reading (i.e., all images read by human readers with AI assistance as concurrent readers), and reading with AI triage (i.e., human reading of only those rendered abnormal by AI). RESULTS: Of 5887 CXR images, 405 (6.9%) and 227 (3.9%) contained visible and clearly visible abnormalities, respectively. With AI-based triage, 42.9% (2354/5482) of normal CXR images were removed at the cost of erroneous removal of 3.5% (14/405) and 1.8% (4/227) of CXR images with visible and clearly visible abnormalities, respectively. In the diagnostic performance study, AI triage removed 41.6% (188/452) of normal images from the worklist without missing visible abnormalities and increased the specificity for some readers without decreasing sensitivity. CONCLUSION: This study suggests the feasibility of sorting and removing normal CXRs using AI with a tailored cut-off to increase efficiency and reduce the workload of radiologists.