Dataset Information

3D Automatic Segmentation of Aortic Computed Tomography Angiography Combining Multi-View 2D Convolutional Neural Networks.

ABSTRACT:

Purpose

The quantitative analysis of contrast-enhanced Computed Tomography Angiography (CTA) is essential to assess aortic anatomy, identify pathologies, and perform preoperative planning in vascular surgery. To overcome the limitations given by manual and semi-automatic segmentation tools, we apply a deep learning-based pipeline to automatically segment the CTA scans of the aortic lumen, from the ascending aorta to the iliac arteries, accounting for 3D spatial coherence.

Methods

A first convolutional neural network (CNN) is used to coarsely segment and locate the aorta in the whole sub-sampled CTA volume, then three single-view CNNs are used to effectively segment the aortic lumen from axial, sagittal, and coronal planes under higher resolution. Finally, the predictions of the three orthogonal networks are integrated to obtain a segmentation with spatial coherence.

Results

The coarse segmentation performed to identify the aortic lumen achieved a Dice coefficient (DSC) of 0.92?±?0.01. Single-view axial, sagittal, and coronal CNNs provided a DSC of 0.92?±?0.02, 0.92?±?0.04, and 0.91?±?0.02, respectively. Multi-view integration provided a DSC of 0.93?±?0.02 and an average surface distance of 0.80?±?0.26 mm on a test set of 10 CTA scans. The generation of the ground truth dataset took about 150 h and the overall training process took 18 h. In prediction phase, the adopted pipeline takes around 25?±?1 s to get the final segmentation.

Conclusion

The achieved results show that the proposed pipeline can effectively localize and segment the aortic lumen in subjects with aneurysm.

SUBMITTER: Fantazzini A

PROVIDER: S-EPMC7511465 | biostudies-literature | 2020 Oct

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

3D Automatic Segmentation of Aortic Computed Tomography Angiography Combining Multi-View 2D Convolutional Neural Networks.

Fantazzini Alice A Esposito Mario M Finotello Alice A Auricchio Ferdinando F Pane Bianca B Basso Curzio C Spinella Giovanni G Conti Michele M

Cardiovascular engineering and technology 20200811 5

<h4>Purpose</h4>The quantitative analysis of contrast-enhanced Computed Tomography Angiography (CTA) is essential to assess aortic anatomy, identify pathologies, and perform preoperative planning in vascular surgery. To overcome the limitations given by manual and semi-automatic segmentation tools, we apply a deep learning-based pipeline to automatically segment the CTA scans of the aortic lumen, from the ascending aorta to the iliac arteries, accounting for 3D spatial coherence.<h4>Methods</h4> ...[more]

PMID: 32783134

Similar Datasets

Project description:Cardiac computed tomography angiography (CTA) is an emerging imaging modality for assessing coronary artery as well as various cardiovascular structures. Recently, deep learning (DL) methods have been successfully applied to many applications of medical image analysis including cardiac CTA structure segmentation. However, DL requires a large amounts of data and high-quality labels for training which can be burdensome to obtain due to its labor-intensive nature. In this study, we aim to develop a fully automatic artificial intelligence (AI) system, named DeepHeartCT, for accurate and rapid cardiac CTA segmentation based on DL. The proposed system was trained using a large clinical dataset with computer-generated labels to segment various cardiovascular structures including left and right ventricles (LV, RV), left and right atria (LA, RA), and LV myocardium (LVM). This new system was trained directly using high-quality computer labels generated from our previously developed multi-atlas based AI system. In addition, a reverse ranking strategy was proposed to assess the segmentation quality in the absence of manual reference labels. This strategy allowed the new framework to assemble optimal computer-generated labels from a large dataset for effective training of a deep convolutional neural network (CNN). A large clinical cardiac CTA studies (n = 1,064) were used to train and validate our framework. The trained model was then tested on another independent dataset with manual labels (n = 60). The Dice score, Hausdorff distance and mean surface distance were used to quantify the segmentation accuracy. The proposed DeepHeartCT framework yields a high median Dice score of 0.90 [interquartile range (IQR), 0.90-0.91], a low median Hausdorff distance of 7 mm (IQR, 4-15 mm) and a low mean surface distance of 0.80 mm (IQR, 0.57-1.29 mm) across all segmented structures. An additional experiment was conducted to evaluate the proposed DL-based AI framework trained with a small vs. large dataset. The results show our framework also performed well when trained on a small optimal training dataset (n = 110) with a significantly reduced training time. These results demonstrated that the proposed DeepHeartCT framework provides accurate and rapid cardiac CTA segmentation that can be readily generalized for handling large-scale medical imaging applications.

Project description:BackgroundPulmonary segments are valuable because they can provide more precise localization and intricate details of lung cancer than lung lobes. With advances in precision therapy, there is an increasing demand for the identification and visualization of pulmonary segments in computed tomography (CT) images to aid in the precise treatment of lung cancer. This study aimed to integrate multiple deep-learning models to accurately segment pulmonary segments in CT images using a bronchial tree (BT)-based approach.MethodsThe proposed segmentation method for pulmonary segments using the BT-based approach comprised the following five essential steps: (I) segmentation of the lung using a U-Net (R231) (public access) model; (II) segmentation of the lobes using a V-Net (self-developed) model; (III) segmentation of the airway using a combination of a differential geometric approach method and a BronchiNet (public access) model; (IV) labeling of the BT branches based on anatomical position; and (V) segmentation of the pulmonary segments based on the distance of each voxel to the labeled BT branches. This five-step process was applied to 14 high-resolution breath-hold CT images and compared against manual segmentations for evaluation.ResultsFor the lung segmentation, the lung mask had a mean dice similarity coefficient (DSC) of 0.98±0.03. For the lobe segmentation, the V-Net model had a mean DSC of 0.94±0.06. For the airway segmentation, the average total length of the segmented airway trees per image scan was 1,902.8±502.1 mm, and the average number of the maximum airway tree generations was 8.5±1.3. For the segmentation of the pulmonary segments, the proposed method had a DSC of 0.73±0.11 and a mean surface distance of 6.1±2.9 mm.ConclusionsThis study demonstrated the feasibility of combining multiple deep-learning models for the auxiliary segmentation of pulmonary segments on CT images using a BT-based approach. The results highlighted the potential of the BT-based method for the semi-automatic segmentation of the pulmonary segment.

Project description:OBJECTIVE:To compare assessment of collaterals by single-phase computed tomography (CT) angiography (CTA) and CT perfusion-derived 3-phase CTA, multiphase CTA and temporal maximum-intensity projection (tMIP) images to digital subtraction angiography (DSA), and relate collateral assessments to clinical outcome in patients with acute ischemic stroke. METHODS:Consecutive acute ischemic stroke patients who underwent CT perfusion, CTA, and DSA before thrombectomy with occlusion of the internal carotid artery, the M1 or the M2 segments were included. Two observers assessed all CT images and one separate observer assessed DSA (reference standard) with static and dynamic (modified American Society of Interventional and Therapeutic Neuroradiology) collateral grading methods. Interobserver agreement and concordance were quantified with Cohen-weighted ? and concordance correlation coefficient, respectively. Imaging assessments were related to clinical outcome (modified Rankin Scale, ? 2). RESULTS:Interobserver agreement (n = 101) was 0.46 (tMIP), 0.58 (3-phase CTA), 0.67 (multiphase CTA), and 0.69 (single-phase CTA) for static assessments and 0.52 (3-phase CTA) and 0.54 (multiphase CTA) for dynamic assessments. Concordance correlation coefficient (n = 80) was 0.08 (3-phase CTA), 0.09 (single-phase CTA), and 0.23 (multiphase CTA) for static assessments and 0.10 (3-phase CTA) and 0.27 (multiphase CTA) for dynamic assessments. Higher static collateral scores on multiphase CTA (odds ratio [OR], 1.7; 95% confidence interval [CI], 1.1-2.7) and tMIP images (OR, 2.0; 95% CI, 1.1-3.4) were associated with modified Rankin Scale of 2 or less as were higher modified American Society of Interventional and Therapeutic Neuroradiology scores on 3-phase CTA (OR, 1.5; 95% CI, 1.1-2.2) and multiphase CTA (OR, 1.7; 95% CI, 1.1-2.6). CONCLUSIONS:Concordance between assessments on CT and DSA was poor. Collateral status evaluated on 3-phase CTA and multiphase CTA, but not on DSA, was associated with clinical outcome.

Dataset Information

3D Automatic Segmentation of Aortic Computed Tomography Angiography Combining Multi-View 2D Convolutional Neural Networks.

Purpose

Methods

Results

Conclusion

Publications

3D Automatic Segmentation of Aortic Computed Tomography Angiography Combining Multi-View 2D Convolutional Neural Networks.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets