Learning physical properties in complex visual scenes: An intelligent machine for perceiving blood flow dynamics from static CT angiography imaging

Gao, Zhifan; Wang, Xin; Sun, Shanhui; Wu, Dan; Bai, Junjie; Yin, Youbing; Liu, Xin; Zhang, Heye; Albuquerque, Victor Hugo C. de

doi:10.1016/j.neunet.2019.11.017

Cited by 81 publications

(51 citation statements)

References 69 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With the growing attention on machine learning, the medical application of this technology has become a new focus [17]. Machine learning is an interdisciplinary subject, which involves probability theory, statistics, approximation theory, convex analysis, algorithm complexity theory, and other disciplines [18][19][20][21][22]. It is flexible, expandable, and automatic, which makes it adaptable for risk stratification, diagnosis, and predictions, but currently, we cannot find any machine learning algorithm being applied to predict the occurrence of LVR.…”

Section: Introductionmentioning

confidence: 99%

A Comparison of Three-Dimensional Speckle Tracking Echocardiography Parameters in Predicting Left Ventricular Remodeling

Zhong

Liu

et al. 2020

Journal of Healthcare Engineering

View full text Add to dashboard Cite

Three-dimensional speckle tracking echocardiography (3D STE) is an emerging noninvasive method for predicting left ventricular remodeling (LVR) after acute myocardial infarction (AMI). Previous studies analyzed the predictive value of 3D STE with traditional models. However, no models that contain comprehensive risk factors were assessed, and there are limited data on the comparison of different 3D STE parameters. In this study, we sought to build a machine learning model for predicting LVR in AMI patients after effective percutaneous coronary intervention (PCI) that contains the majority of the clinical risk factors and compare 3D STE parameters values for LVR prediction. We enrolled 135 first-onset AMI patients (120 males, mean age 54 ± 9 years). All patients went through a 3D STE and a traditional transthoracic echocardiography 24 hours after reperfusion. A second echocardiography was repeated at the three-month follow-up to detect LVR (defined as a 20 percent increase in left ventricular end-diastolic volume). Six models were constructed using 15 risk factors. A receiver operator characteristic curve and four performance measurements were used as evaluation methods. Feature importance was used to compare 3D STE parameters. 26 patients (19.3%) had LVR. Our evaluation showed that RF can best predict LVR with the best AUC of 0.96. 3D GLS was the most valuable 3D STE parameters, followed by GCS, global area strain, and global radial strain (feature importance 0.146, 0.089, 0.087, and 0.069, respectively). To sum up, RF models can accurately predict the LVR after AMI, and 3D GLS was the best 3D STE parameters in predicting the LVR.

show abstract

Section: Introductionmentioning

confidence: 99%

A Comparison of Three-Dimensional Speckle Tracking Echocardiography Parameters in Predicting Left Ventricular Remodeling

Zhong

Liu

et al. 2020

Journal of Healthcare Engineering

View full text Add to dashboard Cite

show abstract

“…Such as coronary computed tomography angiography (CTA) based approaches including transluminal attenuation gradient (TAG), CT vasodilator induced stress myocardial perfusion imaging, and fractional flow reserve CT (FFR CT ) 19 as well as the use of artificial intelligence. 20 Techniques such as FFR CT have shown improved diagnostic accuracies of calcifications, traditionally listed as unequivocal by other techniques. [21][22][23] Likewise, articles published in The Lancet and Neural Networks have shown comparable results of artificial intelligence when interpreting fractional flow reserve (FFR) directly through CT angiography images or artificial intelligence interpretation detecting electrocardiographic presentation of atrial fibrillation on a standard 12 lead ECG.…”

Section: Clinical Skillsmentioning

confidence: 99%

“…[21][22][23] Likewise, articles published in The Lancet and Neural Networks have shown comparable results of artificial intelligence when interpreting fractional flow reserve (FFR) directly through CT angiography images or artificial intelligence interpretation detecting electrocardiographic presentation of atrial fibrillation on a standard 12 lead ECG. 20,24…”

Section: Clinical Skillsmentioning

confidence: 99%

<p>Cardiology Fellow Diagnostic Accuracy and Data Interpretation Outcomes: A Review of the Current Literature</p>

Zhitny

Iftekhar

Alexander

et al. 2020

VHRM

View full text Add to dashboard Cite

Background: Cardiology fellows, in particular, are in a unique position to mold the new cardiovascular workforce, especially in terms of risk prevention. There is a growing need for the cardiovascular workforce. In the United States, one person dies every forty-two seconds due to a cardiovascular adverse event. Methods: A PRISMA systematic review included comprehensive search of the MED-LINE database (PubMed) from 1927 to 2020-the oldest to newest available literature on the subject available through PubMed. Results: Fifty-seven cardiology fellows together interpreted a total of 1719 EKGs with a correct rate of 52%. Sixty-four fellows completed a total of 1363 echocardiography interpretations with an accuracy rate of nearly 75%. Conclusion: Based on the studies discussed, it is evident that a cardiology fellow, particularly in their early years of training, may be limited due to a lack of experience. With continued EKG and echocardiogram interpretation, as well as other clinical skills practice, fellows can improve their diagnostic accuracy and procedural efficiency.

show abstract

“…To increase the conception rate of artificial insemination, a computer-aided method to determine the suitability (i.e., motility) of a sperm sample for artificial insemination based on the microscope footage is required. Recently, artificial intelligence (AI)-based methods, such as convolutional neural networks (CNNs) and deep learning combined with computer vision methods, were adopted for multiple biomedical imaging applications, such as disease classification [9,10], edge detection [11], image segmentation [12], knowledge inference [13], image reconstruction [14], shape recognition [15], and others [16].…”

Section: Introductionmentioning

confidence: 99%

Deep Learning Based Evaluation of Spermatozoid Motility for Artificial Insemination

Valiuškaitė

Raudonis

Maskeliūnas

et al. 2020

Sensors

View full text Add to dashboard Cite

We propose a deep learning method based on the Region Based Convolutional Neural Networks (R-CNN) architecture for the evaluation of sperm head motility in human semen videos. The neural network performs the segmentation of sperm heads, while the proposed central coordinate tracking algorithm allows us to calculate the movement speed of sperm heads. We have achieved 91.77% (95% CI, 91.11–92.43%) accuracy of sperm head detection on the VISEM (A Multimodal Video Dataset of Human Spermatozoa) sperm sample video dataset. The mean absolute error (MAE) of sperm head vitality prediction was 2.92 (95% CI, 2.46–3.37), while the Pearson correlation between actual and predicted sperm head vitality was 0.969. The results of the experiments presented below will show the applicability of the proposed method to be used in automated artificial insemination workflow.

show abstract

Learning physical properties in complex visual scenes: An intelligent machine for perceiving blood flow dynamics from static CT angiography imaging

Cited by 81 publications

References 69 publications

A Comparison of Three-Dimensional Speckle Tracking Echocardiography Parameters in Predicting Left Ventricular Remodeling

A Comparison of Three-Dimensional Speckle Tracking Echocardiography Parameters in Predicting Left Ventricular Remodeling

<p>Cardiology Fellow Diagnostic Accuracy and Data Interpretation Outcomes: A Review of the Current Literature</p>

Deep Learning Based Evaluation of Spermatozoid Motility for Artificial Insemination

Contact Info

Product

Resources

About