PA²Net: Period-Aware Attention Network for Robust Fetal ECG Detection

Wang, Xu; He, Zhaoshui; Lin, Zhijie; Han, Yang; Liu, Taiheng; Lu, Jun; Xie, Shengli

doi:10.1109/tim.2022.3189742

Cited by 12 publications

(3 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We achieve this by leveraging the periodic activation function, i.e., sine function, in MLP to form a sinusoidal representation network (SIREN), which can potentially extract complex frequency information from EEG. In the recent years, there has been growing interest in utilizing periodic activation function in neural network for decoding neural and physiological signals 12,[18][19][20] . Our experiments further highlight the potential of periodic activation function in learning the representation of neural data by showing that the SIREN block effectively facilitates the prediction performance of CNN and aids in achieving higher accuracy compared with the previous state-of-the-art models.…”

Section: Discussionmentioning

confidence: 99%

Leveraging sinusoidal representation networks to predict fMRI signals from EEG

Li,

Lou,

et al. 2024

Medical Imaging 2024: Image Processing

View full text Add to dashboard Cite

In modern neuroscience, functional magnetic resonance imaging (fMRI) has been a crucial and irreplaceable tool that provides a non-invasive window into the dynamics of whole-brain activity. Nevertheless, fMRI is limited by hemodynamic blurring as well as high cost, immobility, and incompatibility with metal implants. Electroencephalography (EEG) is complementary to fMRI and can directly record the cortical electrical activity at high temporal resolution, but has more limited spatial resolution and is unable to recover information about deep subcortical brain structures. The ability to obtain fMRI information from EEG would enable cost-effective, naturalistic imaging across a wider set of brain regions. Further, beyond augmenting the capabilities of EEG, cross-modality models would facilitate the interpretation of fMRI signals. However, as both EEG and fMRI are high-dimensional and prone to noise and artifacts, it is currently challenging to model fMRI from EEG. Indeed, although correlations between these two modalities have been widely investigated, few studies have successfully used EEG to directly reconstruct fMRI time series. To address this challenge, we propose a novel architecture that can predict fMRI signals directly from multi-channel EEG without explicit feature engineering. Our model achieves this by implementing a Sinusoidal Representation Network (SIREN) to learn frequency information in brain dynamics from EEG, which serves as the input to a subsequent encoder-decoder to effectively reconstruct the fMRI signal in a specific brain region. We evaluate our model using a simultaneous EEG-fMRI dataset with 8 subjects and investigate its potential for predicting subcortical fMRI signals. The present results reveal that our model outperforms a recent stateof-the-art model and indicate the potential of leveraging periodic activation functions in deep neural networks to model functional neuroimaging data.

show abstract

Section: Discussionmentioning

confidence: 99%

Leveraging sinusoidal representation networks to predict fMRI signals from EEG

Li,

Lou,

et al. 2024

Medical Imaging 2024: Image Processing

View full text Add to dashboard Cite

show abstract

“…DAMs may adaptively locate pertinent lesion locations to retrieve discriminative imaging characteristics of COVID-19 [21]. For foetal ECG (FECG) detection, a period-aware attention network (PA2Net) is presented in [22], in which an FECG period-aware attention unit (FPAM) is created to decrease noise interference by modelling the periods and properties of signals. In [23], a brandnew 2D motion-compensated rebuilding technique for coronary arteries is suggested.…”

Section: Introductionmentioning

confidence: 99%

Artificial intelligence based approach for categorization of COVID-19 ECG images in presence of other cardiovascular disorders

Chaitanya

Sharma

Rahul

et al. 2023

Biomed. Phys. Eng. Express

View full text Add to dashboard Cite

Coronavirus disease (COVID-19) is a class of SARS-CoV-2 virus which is initially identified in the later half of the year 2019 and then evolved as a pandemic. If it is not identified in the early stage then the infection and mortality rates increase with time. A timely and reliable approach for COVID-19 identification has become important in order to prevent the disease from spreading rapidly. In recent times, many methods have been suggested for the detection of COVID-19 disease have various flaws, to increase diagnosis performance, fresh investigations are required. In this article, automatically diagnosing COVID-19 using ECG images and deep learning approaches like as Visual Geometry Group (VGG) and AlexNet architectures have been proposed. The proposed method is able to classify between COVID-19, myocardial infarction, normal sinus rhythm, and other abnormal heart beats using Lead-II ECG image only. The efficacy of the technique proposed is validated by using a publicly available ECG image database. We have achieved an accuracy of 77.42% using Alexnet model and 75% accuracy with the help of VGG19 model.

show abstract

“…Since the deep learning-based network has shown excellent results on the computer visions, such as image classification [14]- [16], object detection [17], [18], and semantic segmentation [19]- [21], it is also applied in defects detection on the magnetic tile [22]- [24]. For example, Liang et al propose a loop-shaped fusion convolutional neural network to detect small defects from magnetic tiles [25].…”

Section: Introductionmentioning

confidence: 99%

MVRA-UNet: Multi-View Residual Attention U-Net for Precise Defect Segmentation on Magnetic Tile Surface

Luo,

Cui,

Liao

2023

IEEE Access

View full text Add to dashboard Cite

PA²Net: Period-Aware Attention Network for Robust Fetal ECG Detection

Cited by 12 publications

References 43 publications

Leveraging sinusoidal representation networks to predict fMRI signals from EEG

Leveraging sinusoidal representation networks to predict fMRI signals from EEG

Artificial intelligence based approach for categorization of COVID-19 ECG images in presence of other cardiovascular disorders

MVRA-UNet: Multi-View Residual Attention U-Net for Precise Defect Segmentation on Magnetic Tile Surface

Contact Info

Product

Resources

About