Dataset Information

Deep learning segmentation and quantification method for assessing epicardial adipose tissue in CT calcium score scans.

ABSTRACT: Epicardial adipose tissue volume (EAT) has been linked to coronary artery disease and the risk of major adverse cardiac events. As manual quantification of EAT is time-consuming, requires specialized training, and is prone to human error, we developed a deep learning method (DeepFat) for the automatic assessment of EAT on non-contrast low-dose CT calcium score images. Our DeepFat intuitively segmented the tissue enclosed by the pericardial sac on axial slices, using two preprocessing steps. First, we applied a HU-attention-window with a window/level 350/40-HU to draw attention to the sac and reduce numerical errors. Second, we applied a novel look ahead slab-of-slices with bisection ("bisect") in which we split the heart into halves and sequenced the lower half from bottom-to-middle and the upper half from top-to-middle, thereby presenting an always increasing curvature of the sac to the network. EAT volume was obtained by thresholding voxels within the sac in the fat window (- 190/- 30-HU). Compared to manual segmentation, our algorithm gave excellent results with volume Dice = 88.52% ± 3.3, slice Dice = 87.70% ± 7.5, EAT error = 0.5% ± 8.1, and R = 98.52% (p < 0.001). HU-attention-window and bisect improved Dice volume scores by 0.49% and 3.2% absolute, respectively. Variability between analysts was comparable to variability with DeepFat. Results compared favorably to those of previous publications.

SUBMITTER: Hoori A

PROVIDER: S-EPMC8831577 | biostudies-literature | 2022 Feb

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Deep learning segmentation and quantification method for assessing epicardial adipose tissue in CT calcium score scans.

Hoori Ammar A Hu Tao T Lee Juhwan J Al-Kindi Sadeer S Rajagopalan Sanjay S Wilson David L DL

Scientific reports 20220210 1

Epicardial adipose tissue volume (EAT) has been linked to coronary artery disease and the risk of major adverse cardiac events. As manual quantification of EAT is time-consuming, requires specialized training, and is prone to human error, we developed a deep learning method (DeepFat) for the automatic assessment of EAT on non-contrast low-dose CT calcium score images. Our DeepFat intuitively segmented the tissue enclosed by the pericardial sac on axial slices, using two preprocessing steps. Firs ...[more]

PMID: 35145186

Similar Datasets

Project description:For image-guided small animal irradiations, the whole workflow of imaging, organ contouring, irradiation planning, and delivery is typically performed in a single session requiring continuous administration of anaesthetic agents. Automating contouring leads to a faster workflow, which limits exposure to anaesthesia and thereby, reducing its impact on experimental results and on animal wellbeing. Here, we trained the 2D and 3D U-Net architectures of no-new-Net (nnU-Net) for autocontouring of the thorax in mouse micro-CT images. We trained the models only on native CTs and evaluated their performance using an independent testing dataset (i.e., native CTs not included in the training and validation). Unlike previous studies, we also tested the model performance on an external dataset (i.e., contrast-enhanced CTs) to see how well they predict on CTs completely different from what they were trained on. We also assessed the interobserver variability using the generalized conformity index ([Formula: see text]) among three observers, providing a stronger human baseline for evaluating automated contours than previous studies. Lastly, we showed the benefit on the contouring time compared to manual contouring. The results show that 3D models of nnU-Net achieve superior segmentation accuracy and are more robust to unseen data than 2D models. For all target organs, the mean surface distance (MSD) and the Hausdorff distance (95p HD) of the best performing model for this task (nnU-Net 3d_fullres) are within 0.16 mm and 0.60 mm, respectively. These values are below the minimum required contouring accuracy of 1 mm for small animal irradiations, and improve significantly upon state-of-the-art 2D U-Net-based AIMOS method. Moreover, the conformity indices of the 3d_fullres model also compare favourably to the interobserver variability for all target organs, whereas the 2D models perform poorly in this regard. Importantly, the 3d_fullres model offers 98% reduction in contouring time.

Project description:Loss of adipose tissue in vertebrate wildlife species is indicative of decreased nutritional and health status and is linked to environmental stress and diseases. Body condition indices (BCI) are commonly used in ecological studies to estimate adipose tissue mass across wildlife populations. However, these indices have poor predictive power, which poses the need for quantitative methods for improved population assessments. Here, we calibrate bioelectrical impedance spectroscopy (BIS) as an alternative approach for assessing the nutritional status of vertebrate wildlife in ecological studies. BIS is a portable technology that can estimate body composition from measurements of body impedance and is widely used in humans. BIS is a predictive technique that requires calibration using a reference body composition method. Using sea turtles as model organisms, we propose a calibration protocol using computed tomography (CT) scans, with the prediction equation being: adipose tissue mass (kg) = body mass - (-0.03 [intercept] - 0.29 * length2/resistance at 50 kHz + 1.07 * body mass - 0.11 * time after capture). CT imaging allows for the quantification of body fat. However, processing the images manually is prohibitive due to the extensive time requirement. Using a form of artificial intelligence (AI), we trained a computer model to identify and quantify nonadipose tissue from the CT images, and adipose tissue was determined by the difference in body mass. This process enabled estimating adipose tissue mass from bioelectrical impedance measurements. The predictive performance of the model was built on 2/3 samples and tested against 1/3 samples. Prediction of adipose tissue percentage had greater accuracy when including impedance parameters (mean bias = 0.11%-0.61%) as predictor variables, compared with using body mass alone (mean bias = 6.35%). Our standardized BIS protocol improves on conventional body composition assessment methods (e.g., BCI) by quantifying adipose tissue mass. The protocol can be applied to other species for the validation of BIS and to provide robust information on the nutritional and health status of wildlife, which, in turn, can be used to inform conservation decisions at the management level.

Project description:PurposeTo automate skeletal muscle segmentation in a pediatric population using convolutional neural networks that identify and segment the L3 level at CT.Materials and methodsIn this retrospective study, two sets of U-Net-based models were developed to identify the L3 level in the sagittal plane and segment the skeletal muscle from the corresponding axial image. For model development, 370 patients (sampled uniformly across age group from 0 to 18 years and including both sexes) were selected between January 2009 and January 2019, and ground truth L3 location and skeletal muscle segmentation were manually defined. Twenty percent (74 of 370) of the examinations were reserved for testing the L3 locator and muscle segmentation, while the remaining were used for training. For the L3 locator models, maximum intensity projections (MIPs) from a fixed number of central sections of sagittal reformats (either 12 or 18 sections) were used as input with or without transfer learning using an L3 localizer trained on an external dataset (four models total). For the skeletal muscle segmentation models, two loss functions (weighted Dice similarity coefficient [DSC] and binary cross-entropy) were used on models trained with or without data augmentation (four models total). Outputs from each model were compared with ground truth, and the mean relative error and DSC from each of the models were compared with one another.ResultsL3 section detection trained with an 18-section MIP model with transfer learning had a mean error of 3.23 mm ± 2.61 standard deviation, which was within the reconstructed image thickness (3 or 5 mm). Skeletal muscle segmentation trained with the weighted DSC loss model without data augmentation had a mean DSC of 0.93 ± 0.03 and mean relative error of 0.04 ± 0.04.ConclusionConvolutional neural network models accurately identified the L3 level and segmented the skeletal muscle on pediatric CT scans.Supplemental material is available for this article.See also the commentary by Cadrin-Chênevert in this issue.© RSNA, 2021.

Project description:Lung cancer is the leading cause of cancer related deaths worldwide. The development of orthotopic mouse models of lung cancer, which recapitulates the disease more realistically compared to the widely used subcutaneous tumor models, is expected to critically aid the development of novel therapies to battle lung cancer or related comorbidities such as cachexia. However, follow-up of tumor take, tumor growth and detection of therapeutic effects is difficult, time consuming and requires a vast number of animals in orthotopic models. Here, we describe a solution for the fully automatic segmentation and quantification of orthotopic lung tumor volume and mass in whole-body mouse computed tomography (CT) scans. The goal is to drastically enhance the efficiency of the research process by replacing time-consuming manual procedures with fast, automated ones. A deep learning algorithm was trained on 60 unique manually delineated lung tumors and evaluated by four-fold cross validation. Quantitative performance metrics demonstrated high accuracy and robustness of the deep learning algorithm for automated tumor volume analyses (mean dice similarity coefficient of 0.80), and superior processing time (69 times faster) compared to manual segmentation. Moreover, manual delineations of the tumor volume by three independent annotators was sensitive to bias in human interpretation while the algorithm was less vulnerable to bias. In addition, we showed that besides longitudinal quantification of tumor development, the deep learning algorithm can also be used in parallel with the previously published method for muscle mass quantification and to optimize the experimental design reducing the number of animals needed in preclinical studies. In conclusion, we implemented a method for fast and highly accurate tumor quantification with minimal operator involvement in data analysis. This deep learning algorithm provides a helpful tool for the noninvasive detection and analysis of tumor take, tumor growth and therapeutic effects in mouse orthotopic lung cancer models.

Project description:Background We investigated the accuracy of quantifying epicardial adipose tissue volume (EATV) using low-dose cardiac scan (EATVcardiac scan) and evaluated its clinical utility in predicting coronary heart disease in patients with low or mild calcification. Methods In total, 204 patients with clinical symptoms of coronary heart disease and coronary artery calcium score (CACS) of <100 AU were enrolled in this retrospective study. After obtaining EATVcardiac scan and EATV measured using computed tomography angiography (EATVCTA), the agreement between the two measurements was evaluated using Pearson correlation coefficient and Bland-Altman analysis. Multivariate logistic regression was used to analyze the utility of EATV in predicting plaque and vulnerable plaque. Receiver operating characteristic curves were constructed. Results The mean EATVcardiac scan (101.51±41.57 cm3) and EATVCTA (104.57±41.34 cm3) of all patients were similar, and the two measurements were strongly correlated (r=0.9596, P<0.001). The difference between EATVcardiac scan and EATVCTA was −3.0549, with only 4.9% (10/204) of patients having values outside the 95% confidence interval (CI) range (−26.15 to 20.04; P for agreement =0.0003). Further, a significant agreement was observed between EATVcardiac scan and EATVCTA in 126 patients with plaques, with an estimated difference of −3.354, and 6.35% (8/126) of patients had values outside the 95% CI range (−31.37 to 24.66; P for agreement =0.0095). After adjustment for age and sex, EATVcardiac scan and EATVCTA were significantly associated with plaque (all P values <0.001), and the areas under the curve (AUCs) were 0.662 and 0.670 (P=0.4331), respectively. In contrast, EATVcardiac scan and EATVCTA were not associated with vulnerable plaque (P>0.05), with AUCs of 0.550 and 0.530, respectively (P=0.2157). Conclusions The study results indicate that EATVcardiac scan and EATVCTA are equivalent. In addition, both methods provide comparable values for predicting coronary arteriosclerosis in patients with low-to-mild calcification (CACS of <100 AU).

Project description:BackgroundDiagnosis of rib fractures plays an important role in identifying trauma severity. However, quickly and precisely identifying the rib fractures in a large number of CT images with increasing number of patients is a tough task, which is also subject to the qualification of radiologist. We aim at a clinically applicable automatic system for rib fracture detection and segmentation from CT scans.MethodsA total of 7,473 annotated traumatic rib fractures from 900 patients in a single center were enrolled into our dataset, named RibFrac Dataset, which were annotated with a human-in-the-loop labeling procedure. We developed a deep learning model, named FracNet, to detect and segment rib fractures. 720, 60 and 120 patients were randomly split as training cohort, tuning cohort and test cohort, respectively. Free-Response ROC (FROC) analysis was used to evaluate the sensitivity and false positives of the detection performance, and Intersection-over-Union (IoU) and Dice Coefficient (Dice) were used to evaluate the segmentation performance of predicted rib fractures. Observer studies, including independent human-only study and human-collaboration study, were used to benchmark the FracNet with human performance and evaluate its clinical applicability. A annotated subset of RibFrac Dataset, including 420 for training, 60 for tuning and 120 for test, as well as our code for model training and evaluation, was open to research community to facilitate both clinical and engineering research.FindingsOur method achieved a detection sensitivity of 92.9% with 5.27 false positives per scan and a segmentation Dice of 71.5%on the test cohort. Human experts achieved much lower false positives per scan, while underperforming the deep neural networks in terms of detection sensitivities with longer time in diagnosis. With human-computer collobration, human experts achieved higher detection sensitivities than human-only or computer-only diagnosis.InterpretationThe proposed FracNet provided increasing detection sensitivity of rib fractures with significantly decreased clinical time consumed, which established a clinically applicable method to assist the radiologist in clinical practice.FundingA full list of funding bodies that contributed to this study can be found in the Acknowledgements section. The funding sources played no role in the study design; collection, analysis, and interpretation of data; writing of the report; or decision to submit the article for publication .

Dataset Information

Deep learning segmentation and quantification method for assessing epicardial adipose tissue in CT calcium score scans.

Publications

Deep learning segmentation and quantification method for assessing epicardial adipose tissue in CT calcium score scans.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets