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

@article{Lessmann2018AutomaticCS,
  title={Automatic Calcium Scoring in Low-Dose Chest CT Using Deep Neural Networks With Dilated Convolutions},
  author={Nikolas Lessmann and Bram van Ginneken and Majd Zreik and Pim A de Jong and Bob D. de Vos and Max A. Viergever and Ivana I{\vs}gum},
  journal={IEEE Transactions on Medical Imaging},
  year={2018},
  volume={37},
  pages={615-625}
}
Heavy smokers undergoing screening with low-dose chest CT are affected by cardiovascular disease as much as by lung cancer. Low-dose chest CT scans acquired in screening enable quantification of atherosclerotic calcifications and thus enable identification of subjects at increased cardiovascular risk. This paper presents a method for automatic detection of coronary artery, thoracic aorta, and cardiac valve calcifications in low-dose chest CT using two consecutive convolutional neural networks… Expand
Automatic coronary artery calcium scoring from unenhanced-ECG-gated CT using deep learning.
TLDR
The deep learning-based method proposed here to compute automatically the CAC score from unenhanced-ECG-gated cardiac CT is fast, robust and yields accuracy similar to those of other artificial intelligence methods, which could improve workflow efficiency, eliminating the time spent on manually selecting coronary calcifications to compute the Agatston score. Expand
Impact of automatically detected motion artifacts on coronary calcium scoring in chest computed tomography
TLDR
The proposed method enables identification of scans affected by severe cardiac motion, where CAC quantification may not be reproducible, and reproducibility of CAC scores in scan pairs is higher in scans containing mostly CACs not affected bysevere cardiac motion. Expand
Direct Automatic Coronary Calcium Scoring in Cardiac and Chest CT
TLDR
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. Expand
Coronary Calcium Detection using 3D Attention Identical Dual Deep Network Based on Weakly Supervised Learning
TLDR
3D attention mechanisms were integrated into the AID-Net to provide complementary information for classification tasks and the 3D Gradient-weighted Class Activation Mapping was also proposed at the testing stage to interpret the behaviors of the deep neural network. Expand
Automatic Calcium Scoring in Cardiac and Chest CT Using DenseRAUnet
TLDR
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. Expand
Automated coronary calcium scoring using deep learning with multicenter external validation
TLDR
Two deep learning models that automate CAC scoring demonstrating advantages in automated scoring for both dedicated gated coronary CT exams and routine non-gated chest CTs performed for other reasons to allow opportunistic screening are presented. Expand
Automatic quantification of calcifications in the coronary arteries and thoracic aorta on radiotherapy planning CT scans of Western and Asian breast cancer patients.
TLDR
Deep learning software is a reliable method to automatically measure calcifications in coronary arteries and thoracic aorta on radiotherapy breast CT scans and its reproducibility compared to manual scoring is assessed. Expand
Coronary calcium scoring with partial volume correction in anthropomorphic thorax phantom and screening chest CT images
TLDR
Compared with clinical calcium scoring, proposed quantification provides a better estimate of the true calcium volume in phantoms and better agreement in calcium scores between different subject scan reconstructions. Expand
Motion-corrected coronary calcium scores by a convolutional neural network: a robotic simulating study
TLDR
A deep CNN architecture trained by CT images of motion artifacts showed the ability to correct coronary calcium scores from blurred images and to improve the sensitivity from 65 to 85% for the detection of calcifications. Expand
Knowledge-Based Analysis for Mortality Prediction From CT Images
TLDR
The results of this study confirm that radiologist defined features can complement CNNs in performance improvement and demonstrate that KAMP-Net can achieve a superior performance when compared to other methods. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 52 REFERENCES
Deep convolutional neural networks for automatic coronary calcium scoring in a screening study with low-dose chest CT
TLDR
The proposed system can perform automatic coronary artery calcium scoring to identify subjects undergoing low-dose chest CT screening who are at risk of cardiovascular events with high accuracy. Expand
Automated coronary artery calcification detection on low-dose chest CT images
TLDR
The automatic algorithm segments the heart region based on other pre-segmented organs to provide a coronary region mask to detect and measure CAC from low-dose non-contrast, non-ECG-gated chest CT scans and computed the Agatston score, mass score and volume score. Expand
Automated aortic calcium scoring on low-dose chest computed tomography.
TLDR
Automatic calcium scoring in the aorta appears feasible with good correlation between manual and automatic scoring in low-dose noncontrast-enhanced chest CT scans. Expand
Automatic Coronary Calcium Scoring in Cardiac CT Angiography Using Convolutional Neural Networks
TLDR
The results show that CAC can be automatically identified and quantified in CCTA using the proposed method, which might obviate the need for a dedicated non-contrast-enhanced CT scan for CAC scoring, which is regularly acquired prior to a C CTA scan, and thus reduce the CT radiation dose received by patients. Expand
Automatic Coronary Calcium Scoring in Low-Dose Chest Computed Tomography
TLDR
Calcium scoring can be performed automatically in low-dose, noncontrast enhanced, non-ECG-synchronized chest CT in screening of heavy smokers to identify subjects who might benefit from preventive treatment. Expand
Automatic coronary artery calcium scoring in cardiac CT angiography using paired convolutional neural networks
TLDR
CAC can be accurately automatically identified and quantified in CCTA using the proposed pattern recognition method, which might obviate the need to acquire a dedicated CSCT scan for CAC scoring, and thus reduce the CT radiation dose received by patients. Expand
Detection of coronary calcifications from computed tomography scans for automated risk assessment of coronary artery disease.
TLDR
A fully automated method for coronary calcification detection from non-contrast-enhanced, ECG-gated multi-slice computed tomography (CT) data is presented and the best performance was obtained employing a two-stage classification system with a k-nearest neighbor (k-NN) classifier and a feature selection scheme. Expand
Ordinal scoring of coronary artery calcifications on low-dose CT scans of the chest is predictive of death from cardiovascular disease.
TLDR
Visual assessment of CAC on low-dose CT scans provides clinically relevant quantitative information as to cardiovascular death in a cohort of smokers aged 40-85 years. Expand
Automated aortic calcification detection in low-dose chest CT images
TLDR
A fully automated computer algorithm is developed to segment and measure aortic calcification in low-dose noncontrast, non-ECG gated, chest CT scans and detected and measured in terms of the Agatston score, mass score, and volume score. Expand
A fully automated multi-modal computer aided diagnosis approach to coronary calcium scoring of MSCT images
TLDR
The results presented here are intended to show the feasibility and requirement for an automated scoring method to reduce the subjectivity and reproducibility error inherent with manual clinical calcium scoring. Expand
...
1
2
3
4
5
...