Dataset Information

Automated Measurements of Body Composition in Abdominal CT Scans Using Artificial Intelligence Can Predict Mortality in Patients With Cirrhosis.

ABSTRACT: Body composition measures derived from already available electronic medical records (computed tomography [CT] scans) can have significant value, but automation of measurements is needed for clinical implementation. We sought to use artificial intelligence to develop an automated method to measure body composition and test the algorithm on a clinical cohort to predict mortality. We constructed a deep learning algorithm using Google's DeepLabv3+ on a cohort of de-identified CT scans (n = 12,067). To test for the accuracy and clinical usefulness of the algorithm, we used a unique cohort of prospectively followed patients with cirrhosis (n = 238) who had CT scans performed. To assess model performance, we used the confusion matrix and calculated the mean accuracy of 0.977 ± 0.02 (0.975 ± 0.018 for the training and test sets, respectively). To assess for spatial overlap, we measured the mean intersection over union and mean boundary contour scores and found excellent overlap between the manual and automated methods with mean scores of 0.954 ± 0.030, 0.987 ± 0.009, and 0.948 ± 0.039 (0.983 ± 0.013 for the training and test set, respectively). Using these automated measurements, we found that body composition features were predictive of mortality in patients with cirrhosis. On multivariate analysis, the addition of body composition measures significantly improved prediction of mortality for patients with cirrhosis over Model for End-Stage Liver Disease alone (P < 0.001). Conclusion: The measurement of body composition can be automated using artificial intelligence and add significant value for incidental CTs performed for other clinical indications. This is proof of concept that this methodology could allow for wider implementation into the clinical arena.

SUBMITTER: Zou WY

PROVIDER: S-EPMC8557320 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:BackgroundArtificial intelligence (AI) in diagnostic radiology is undergoing rapid development. Its potential utility to improve diagnostic performance for cardiopulmonary events is widely recognized, but the accuracy and precision have yet to be demonstrated in the context of current screening modalities. Here, we present findings on the performance of an AI convolutional neural network (CNN) prototype (AI-RAD Companion, Siemens Healthineers) that automatically detects pulmonary nodules and quantifies coronary artery calcium volume (CACV) on low-dose chest CT (LDCT), and compare results to expert radiologists. We also correlate AI findings with adverse cardiopulmonary outcomes in a retrospective cohort of 117 patients who underwent LDCT.MethodsA total of 117 patients were enrolled in this study. Two CNNs were used to identify lung nodules and CACV on LDCT scans. All subjects were used for lung nodule analysis, and 96 subjects met the criteria for coronary artery calcium volume analysis. Interobserver concordance was measured using ICC and Cohen's kappa. Multivariate logistic regression and partial least squares regression were used for outcomes analysis.ResultsAgreement of the AI findings with experts was excellent (CACV ICC = 0.904, lung nodules Cohen's kappa = 0.846) with high sensitivity and specificity (CACV: sensitivity = .929, specificity = .960; lung nodules: sensitivity = 1, specificity = 0.708). The AI findings improved the prediction of major cardiopulmonary outcomes at 1-year follow-up including major adverse cardiac events and lung cancer (AUCMACE = 0.911, AUCLung Cancer = 0.942).ConclusionWe conclude the AI prototype rapidly and accurately identifies significant risk factors for cardiopulmonary disease on standard screening low-dose chest CT. This information can be used to improve diagnostic ability, facilitate intervention, improve morbidity and mortality, and decrease healthcare costs. There is also potential application in countries with limited numbers of cardiothoracic radiologists.

Project description:BackgroundAlthough lung ultrasound has been reported to be a portable, cost-effective, and accurate method to detect pneumonia, it has not been widely used because of the difficulty in its interpretation. Here, we aimed to investigate the effectiveness of a novel artificial intelligence-based automated pneumonia detection method using point-of-care lung ultrasound (AI-POCUS) for the coronavirus disease 2019 (COVID-19).MethodsWe enrolled consecutive patients admitted with COVID-19 who underwent computed tomography (CT) in August and September 2021. A 12-zone AI-POCUS was performed by a novice observer using a pocket-size device within 24 h of the CT scan. Fifteen control subjects were also scanned. Additionally, the accuracy of the simplified 8-zone scan excluding the dorsal chest, was assessed. More than three B-lines detected in one lung zone were considered zone-level positive, and the presence of positive AI-POCUS in any lung zone was considered patient-level positive. The sample size calculation was not performed given the retrospective all-comer nature of the study.ResultsA total of 577 lung zones from 56 subjects (59.4 ± 14.8 years, 23% female) were evaluated using AI-POCUS. The mean number of days from disease onset was 9, and 14% of patients were under mechanical ventilation. The CT-validated pneumonia was seen in 71.4% of patients at total 577 lung zones (53.3%). The 12-zone AI-POCUS for detecting CT-validated pneumonia in the patient-level showed the accuracy of 94.5% (85.1%- 98.1%), sensitivity of 92.3% (79.7%- 97.3%), specificity of 100% (80.6%- 100%), positive predictive value of 95.0% (89.6% - 97.7%), and Kappa of 0.33 (0.27-0.40). When simplified with 8-zone scan, the accuracy, sensitivity, and sensitivity were 83.9% (72.2%- 91.3%), 77.5% (62.5%- 87.7%), and 100% (80.6%- 100%), respectively. The zone-level accuracy, sensitivity, and specificity of AI-POCUS were 65.3% (61.4%- 69.1%), 37.2% (32.0%- 42.7%), and 97.8% (95.2%- 99.0%), respectively.InterpretationAI-POCUS using the novel pocket-size ultrasound system showed excellent agreement with CT-validated COVID-19 pneumonia, even when used by a novice observer.

Project description:BackgroundThe coronary artery calcium score (CACS) has been shown to be an independent predictor of cardiovascular events. The traditional coronary artery calcium scoring algorithm has been optimized for electrocardiogram (ECG)-gated images, which are acquired with specific settings and timing. Therefore, if the artificial intelligence-based coronary artery calcium score (AI-CACS) could be calculated from a chest low-dose computed tomography (LDCT) examination, it could be valuable in assessing the risk of coronary artery disease (CAD) in advance, and it could potentially reduce the occurrence of cardiovascular events in patients. This study aimed to assess the performance of an AI-CACS algorithm in non-gated chest scans with three different slice thicknesses (1, 3, and 5 mm).MethodsA total of 135 patients who underwent both LDCT of the chest and ECG-gated non-contrast enhanced cardiac CT were prospectively included in this study. The Agatston scores were automatically derived from chest CT images reconstructed at slice thicknesses of 1, 3, and 5 mm using the AI-CACS software. These scores were then compared to those obtained from the ECG-gated cardiac CT data using a conventional semi-automatic method that served as the reference. The correlations between the AI-CACS and electrocardiogram-gated coronary artery calcium score (ECG-CACS) were analyzed, and Bland-Altman plots were used to assess agreement. Risk stratification was based on the calculated CACS, and the concordance rate was determined.ResultsA total of 112 patients were included in the final analysis. The correlations between the AI-CACS at three different thicknesses (1, 3, and 5 mm) and the ECG-CACS were 0.973, 0.941, and 0.834 (all P<0.01), respectively. The Bland-Altman plots showed mean differences in the AI-CACS for the three thicknesses of -6.5, 15.4, and 53.1, respectively. The risk category agreement for the three AI-CACS groups was 0.868, 0.772, and 0.412 (all P<0.01), respectively. While the concordance rates were 91%, 84.8%, and 62.5%, respectively.ConclusionsThe AI-based algorithm successfully calculated the CACS from LDCT scans of the chest, demonstrating its utility in risk categorization. Furthermore, the CACS derived from images with a slice thickness of 1 mm was more accurate than those obtained from images with slice thicknesses of 3 and 5 mm.

Dataset Information

Automated Measurements of Body Composition in Abdominal CT Scans Using Artificial Intelligence Can Predict Mortality in Patients With Cirrhosis.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets