A data generation pipeline for cardiac vessel segmentation and motion artifact grading

Sushmit, Asif Shahriyar; Xu, Yongshun; Mariani, Olivia; Lyu, Qing; Liu, Ying; Cao, Ximiao; Wiedeman, Christopher; Ma, Hongfeng; Maltz, Jonathan S.; Yu, Hengyong; Wang, Ge

doi:10.1117/12.2642869

Cited by 1 publication

(1 citation statement)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…More recently, Generative Adversarial Networks (GAN) based approaches are being used in place of SMOTE for heart disease diagnosis, because of its ability to produce synthetic data to tackle classimbalance concerns [32]. Different types of modalities are also employed to diagnose heart disease instead of only ECG features which include clinical features and image modality such as detection of heart disease by performing segmentation of coronary arteries [33,34]. Cardia Magnetic imaging resonance is also utilized to detect abnormalities in coronary arteries of the heart [35].…”

Section: Figure 1: Samples Of Ecg Signals From Mitdb and Ptb Database...mentioning

confidence: 99%

A Smart Heart Disease Diagnostic System Using Deep Vanilla LSTM

Bukhari,

Yasmin,

Naz

et al. 2023

CMC

View full text Add to dashboard Cite

Effective smart healthcare frameworks contain novel and emerging solutions for remote disease diagnostics, which aid in the prevention of several diseases including heart-related abnormalities. In this context, regular monitoring of cardiac patients through smart healthcare systems based on Electrocardiogram (ECG) signals has the potential to save many lives. In existing studies, several heart disease diagnostic systems are proposed by employing different state-of-the-art methods, however, improving such methods is always an intriguing area of research. Hence, in this research, a smart healthcare system is proposed for the diagnosis of heart disease using ECG signals. The proposed framework extracts both linear and time-series information on the ECG signals and fuses them into a single framework concurrently. The linear characteristics of ECG signals are extracted by convolution layers followed by Gaussian Error Linear Units (GeLu) and time series characteristics of ECG beats are extracted by Vanilla Long Short-Term Memory Networks (LSTM). Following on, the feature reduction of linear information is done with the help of ID Generalized Gated Pooling (GGP). In addition, data misbalancing issues are also addressed with the help of the Synthetic Minority Oversampling Technique (SMOTE). The performance assessment of the proposed model is done over the two publicly available datasets named MIT-BIH arrhythmia database (MITDB) and PTB Diagnostic ECG database (PTBDB). The proposed framework achieves an average accuracy performance of 99.14% along with a 95% recall value.

show abstract