Automatic Coronary Calcium Scoring in Cardiac CT Angiography Using Convolutional Neural Networks

  title={Automatic Coronary Calcium Scoring in Cardiac CT Angiography Using Convolutional Neural Networks},
  author={Jelmer M. Wolterink and Tim Leiner and Max A. Viergever and Ivana I{\vs}gum},
The amount of coronary artery calcification CAC is a strong and independent predictor of cardiovascular events. [] Key Method The study included CCTA scans of 50 patients equally distributed over five cardiovascular risk categories. CAC in CCTA was identified in two stages. In the first stage, potential CAC voxels were identified using a convolutional neural network CNN.

Direct Automatic Coronary Calcium Scoring in Cardiac and Chest CT

A computationally efficient method that employs two convolutional neural networks that performs registration to align the fields of view of input CTs and direct regression of the calcium score, thereby circumventing time-consuming intermediate CAC segmentation is proposed.

An evaluation of automatic coronary artery calcium scoring methods with cardiac CT using the orCaScore framework.

An evaluation of five (semi)automatic methods within this framework shows that automatic per patient CVD risk categorization is feasible and CAC lesions at ambiguous locations such as the coronary ostia remain challenging, but their detection had limited impact on CVDrisk determination.

Detection and classification of coronary artery calcifications in low dose thoracic CT using deep learning

Deep learning is investigated for the detection of CACs and assessment of their severity on low-dose thoracic screening CTs (LDCT), demonstrating potential for deep learning use in LDCT screening programs.

Automatic Calcium Scoring in Low-Dose Chest CT Using Deep Neural Networks With Dilated Convolutions

The presented method enables reliable automatic cardiovascular risk assessment in all low-dose chest CT scans acquired for lung cancer screening and is evaluated on a set of 1744 CT scans from the National Lung Screening Trial.

Automatic segmentation of the left ventricle in cardiac CT angiography using convolutional neural networks

The results demonstrate that automatic segmentation of the LV in CCTA scans using voxel classification with convolutional neural networks is feasible.

Automated Agatston score computation in non-ECG gated CT scans using deep learning

A convolutional neural network can regress the Agatston score from the image of the heart directly, without a prior segmentation of Coronary Artery Calcifications (CACs).

Automatic Calcium Scoring in Cardiac and Chest CT Using DenseRAUnet

This work proposes a novel network called DenseRAUnet, which takes advantage of Dense U-net, ResNet and atrous convolutions to segment coronary calcium pixels on both types of CT scans and proves the robustness and generalizability of the model.

Prediction of Coronary Artery Calcium Score Using Machine Learning in a Healthy Population

Xgboost ML algorithm was found to be a more reliable predictor of CACS in healthy participants compared to the BLR algorithm, suggesting that ML algorithms may be useful for predicting CACs with only laboratory data inhealthy participants.

An algorithm for fully automatic detection of calcium in chest CT imaging

The proposed framework can reliably detect calcification using CT data and has a precision of 95.1% and a recall of 89.0% in classifying calcium candidates found based on thresholding.

Growing a Random Forest with Fuzzy Spatial Features for Fully Automatic Artery-Specific Coronary Calcium Scoring

An atlas-based feature approach in combination with a random forest (RF) classifier is used to incorporate fuzzy spatial knowledge from offline data in an automatic CAC labeling system with state-of-the-art accuracy and processing time.



Automatic Coronary Calcium Scoring in Non-Contrast-Enhanced ECG-Triggered Cardiac CT With Ambiguity Detection

A system that automatically quantifies total patient and per coronary artery CAC in non-contrast-enhanced, ECG-triggered cardiac CT and identifies candidate calcifications that cannot be automatically labeled with high certainty and optionally presents these to an expert for review.

Vessel specific coronary artery calcium scoring: an automatic system.

Quantifying coronary artery calcification from a contrast-enhanced cardiac computed tomography angiography study.

Quantification of CAC from a single contrast-enhanced CCTA scan is feasible and correlates well with Standard-CAC, and larger, multicentre studies are needed to validate the universal applicability of Cac quantified using CCTa.

Automatic detection and quantification of the Agatston coronary artery calcium score on contrast computed tomography angiography

Fully automatic detection of Agatston Cac score on contrast CTA is feasible and showed high correlation with non-contrast CT CAC score, which could imply a radiation dose reduction and time saving by omitting the non-Contrast scan.

Automatic detection and quantification of coronary calcium on 3D CT angiography data

A novel approach to the fully automatic segmentation and quantification of calcified lesions in coronary computed tomography angiograms that includes a robust threshold determination algorithm based on a histogram calculated from an automatically generated vessel tree is presented.

Fully automatic model-based calcium segmentation and scoring in coronary CT angiography

High diagnostic performance, combined with the benefits of the fully automatic solution, suggests that the proposed technique can be used to eliminate the need in a separate CS CT scan as part of the cCTA examination, thus reducing the radiation exposure and simplifying the procedure.

A method for coronary artery calcium scoring using contrast-enhanced computed tomography.

Deriving coronary artery calcium scores from CT coronary angiography: a proposed algorithm for evaluating stable chest pain

If incorporated into stable chest pain guidelines the need for further functional testing or invasive angiography could be determined from CTCA alone, supporting a change to the current guidelines.

Localizing Calcifications in Cardiac CT Data Sets Using a New Vessel Segmentation Approach

This work presents a method for localizing calcifications by employing a newly developed vessel segmentation approach and an approach for automatically detecting calcified regions that combines diameter information and gray value analysis.

Assessment of Agatston coronary artery calcium score using contrast-enhanced CT coronary angiography.

The AgatSTON calcium score derived from CTA images shows good correlation with unenhanced CT calcium score and is highly reproducible, however, higher Agatston scores are systematically underestimated when derived fromCTA images.