Fetal Congenital Heart Disease Echocardiogram Screening Based on DGACNN: Adversarial One-Class Classification Combined with Video Transfer Learning

Gong, Yuxin; Zhang, Yingying; Zhu, Haogang; Lv, Jing; Cheng, Qian; Zhang, Hongjia; He, Yihua; Wang, Shuliang

doi:10.1109/tmi.2019.2946059

Cited by 61 publications

(41 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Framework reaches a P rec = 0.93 and Rec = 0.93. In [71], a one-class classification network is proposed to classify patients with CHD and healthy subjects. An improved GAN is used for data augmentation.…”

Section: A Heartmentioning

confidence: 99%

A Review on Deep-Learning Algorithms for Fetal Ultrasound-Image Analysis

Fiorentino¹,

Villani²,

Cosmo³

et al. 2022

Preprint

View full text Add to dashboard Cite

Deep-learning (DL) algorithms are becoming the standard for processing ultrasound (US) fetal images. Despite the large number of survey papers already present in this field, most of them are focusing on a broader area of medicalimage analysis or not covering all fetal US DL applications. This paper surveys the most recent work in the field, with a total of 145 research papers published after 2017. Each paper is analyzed and commented from both the methodology and application perspective. We categorized the papers in (i) fetal standard-plane detection, (ii) anatomical-structure analysis and (iii) biometry parameter estimation. For each category, main limitations and open issues are presented. Summary tables are included to facilitate the comparison among the different approaches. Publicly-available datasets and performance metrics commonly used to assess algorithm performance are summarized, too. This paper ends with a critical summary of the current state of the art on DL algorithms for fetal US image analysis and a discussion on current challenges that have to be tackled by researchers working in the field to translate the research methodology into the actual clinical practice.

show abstract

Section: A Heartmentioning

confidence: 99%

A Review on Deep-Learning Algorithms for Fetal Ultrasound-Image Analysis

Fiorentino¹,

Villani²,

Cosmo³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…where n is the sample size, y k and t k are the actual objective and predicted values of the sample, respectively. The gradient descent method is used to minimize the loss function, and then the partial derivatives are calculated by Equation (15) to gradually update the adaptive parameters w and b.…”

Section: Backpropagation Of Parameter Updatesmentioning

confidence: 99%

“…In 2014, Goodfellow and Pouget-Abadie designed a new data enhancement method called a generative adversarial network (GAN), which can supplement the sample space with insufficient data by performing a model synthesis on a limited number of types of samples [13]. GANs are widely used for their outstanding application prospects, including signal processing, pattern recognition, and national security [14][15][16]. Meanwhile, due to GAN's excellent data expansion capability, many models with different structures have been derived [17,18].…”

Section: Introductionmentioning

confidence: 99%

A Novel Intelligent Fault Diagnosis Method for Rolling Bearings Based on Wasserstein Generative Adversarial Network and Convolutional Neural Network under Unbalanced Dataset

Tang

Gao

Wang

et al. 2021

Sensors

View full text Add to dashboard Cite

Rolling bearings are widely used in industrial manufacturing, and ensuring their stable and effective fault detection is a core requirement in the manufacturing process. However, it is a great challenge to achieve a highly accurate rolling bearing fault diagnosis because of the severe imbalance and distribution differences in fault data due to weak early fault features and interference from environmental noise. An intelligent fault diagnosis strategy for rolling bearings based on grayscale image transformation, a generative adversative network, and a convolutional neural network was proposed to solve this problem. First, the original vibration signal is converted into a grayscale image. Then more training samples are generated using GANs to solve severe imbalance and distribution differences in fault data. Finally, the rolling bearing condition detection and fault identification are carried out by using SECNN. The availability of the method is substantiated by experiments on datasets with different data imbalance ratios. In addition, the superiority of this diagnosis strategy is verified by comparing it with other mainstream intelligent diagnosis techniques. The experimental result demonstrates that this strategy can reach more than 99.6% recognition accuracy even under substantial environmental noise interference or changing working conditions and has good stability in the presence of a severe imbalance in fault data.

show abstract

“…Early screening of congenital heart disease is particularly important [1]. Traditional screening methods cannot fully meet the needs of large-scale screening because of cost, medical resources, detection rate and timeliness [2][3][4][5]. ECG is an early routine examination item, which is easy to obtain.…”

Section: Introductionmentioning

confidence: 99%

Recognition of Child Congenital Heart Disease Using Cardiac Cycle Segment of Electrocardiogram

Du¹,

Huang²,

Huang³

et al. 2021

Computer Methods in Medicine and Health Care

View full text Add to dashboard Cite

The results of previous studies showed that ECG could detect CHD in children with a detection rate of 76.43%. Although this result is better than the traditional CHD screening method, the sensitivity still needs to be improved if it is to be popularized clinically. Based on the previous ECG recording data, this study selects the more representative cardiac cycle segments to identify CHD, in order to achieve better screening effect. Firstly, better cardiac cycle segment data were extracted from ECG records of each patient. The final data set contains 72626 patients and each patient has a 9-lead ECG segment with duration of about one second. Then we trained a RoR network to identify the underlying patients with CHD using 62626 samples in the dataset. When tested on an independent set of 10000 patients, the network model yielded values for the sensitivity, specificity, and accuracy of 0.93, 86.3%, 85.7%, and 85.7% respectively. It can be seen that extracting more effective cardiac cycle fragments can significantly improve the sensitivity of CHD screening on the basis of ensuring better specificity, so as to find more potential patients with congenital heart disease.

show abstract

Fetal Congenital Heart Disease Echocardiogram Screening Based on DGACNN: Adversarial One-Class Classification Combined with Video Transfer Learning

Cited by 61 publications

References 25 publications

A Review on Deep-Learning Algorithms for Fetal Ultrasound-Image Analysis

A Review on Deep-Learning Algorithms for Fetal Ultrasound-Image Analysis

A Novel Intelligent Fault Diagnosis Method for Rolling Bearings Based on Wasserstein Generative Adversarial Network and Convolutional Neural Network under Unbalanced Dataset

Recognition of Child Congenital Heart Disease Using Cardiac Cycle Segment of Electrocardiogram

Contact Info

Product

Resources

About