Pretrained Transformers for Seizure Detection

Panchavati, Saarang; Dussen, Samuel Vander; Semwal, Hemal; Ahmed, Ali; Li, Haoran; Arnold, Corey; Speier, William

doi:10.1109/icassp49357.2023.10095660

Cited by 5 publications

(3 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…ChronoNet incorporates multiple 1D convolution layers followed by deep Gated Recurrent Unit (GRU) layers, taking raw time-series EEG data and learning to identify patterns in brain activity. Transformer and CNN [ 60 ]: Recognizing the limitation of conventional EEG systems and the need for timely and accurate diagnosis, the authors adopted a transformer-based deep neural network approach. This model incorporated a mixed Transformer and CNN architecture, which was trained and pre-trained on several datasets, including the Temple University Hospital Seizure Corpus [ 61 ].…”

Section: Methodsmentioning

confidence: 99%

“…Transformer and CNN [ 60 ]: Recognizing the limitation of conventional EEG systems and the need for timely and accurate diagnosis, the authors adopted a transformer-based deep neural network approach. This model incorporated a mixed Transformer and CNN architecture, which was trained and pre-trained on several datasets, including the Temple University Hospital Seizure Corpus [ 61 ].…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

SeizFt: Interpretable Machine Learning for Seizure Detection Using Wearables

Al-Hussaini

Mitchell

2023

Bioengineering

View full text Add to dashboard Cite

This work presents SeizFt—a novel seizure detection framework that utilizes machine learning to automatically detect seizures using wearable SensorDot EEG data. Inspired by interpretable sleep staging, our novel approach employs a unique combination of data augmentation, meaningful feature extraction, and an ensemble of decision trees to improve resilience to variations in EEG and to increase the capacity to generalize to unseen data. Fourier Transform (FT) Surrogates were utilized to increase sample size and improve the class balance between labeled non-seizure and seizure epochs. To enhance model stability and accuracy, SeizFt utilizes an ensemble of decision trees through the CatBoost classifier to classify each second of EEG recording as seizure or non-seizure. The SeizIt1 dataset was used for training, and the SeizIt2 dataset for validation and testing. Model performance for seizure detection was evaluated using two primary metrics: sensitivity using the any-overlap method (OVLP) and False Alarm (FA) rate using epoch-based scoring (EPOCH). Notably, SeizFt placed first among an array of state-of-the-art seizure detection algorithms as part of the Seizure Detection Grand Challenge at the 2023 International Conference on Acoustics, Speech, and Signal Processing (ICASSP). SeizFt outperformed state-of-the-art black-box models in accurate seizure detection and minimized false alarms, obtaining a total score of 40.15, combining OVLP and EPOCH across two tasks and representing an improvement of ~30% from the next best approach. The interpretability of SeizFt is a key advantage, as it fosters trust and accountability among healthcare professionals. The most predictive seizure detection features extracted from SeizFt were: delta wave, interquartile range, standard deviation, total absolute power, theta wave, the ratio of delta to theta, binned entropy, Hjorth complexity, delta + theta, and Higuchi fractal dimension. In conclusion, the successful application of SeizFt to wearable SensorDot data suggests its potential for real-time, continuous monitoring to improve personalized medicine for epilepsy.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

SeizFt: Interpretable Machine Learning for Seizure Detection Using Wearables

Al-Hussaini

Mitchell

2023

Bioengineering

View full text Add to dashboard Cite

show abstract

“…These models were chosen for their simplicity of training and predicting, as well as their incorporation of neural networks. 35 , 36 Logistic regression statistically evaluates the relationship between dependent and independent variables, rendering it promising for multi‐frequency EIS applications. 37 , 38 It often serves as a baseline to validate more advanced models.…”

Section: Methodsmentioning

confidence: 99%

Machine learning‐directed electrical impedance tomography to predict metabolically vulnerable plaques

Chen,

Wang,

Wang

et al. 2023

Bioengineering & Transla Med

Self Cite

View full text Add to dashboard Cite

The characterization of atherosclerotic plaques to predict their vulnerability to rupture remains a diagnostic challenge. Despite existing imaging modalities, none have proven their abilities to identify metabolically active oxidized low‐density lipoprotein (oxLDL), a marker of plaque vulnerability. To this end, we developed a machine learning‐directed electrochemical impedance spectroscopy (EIS) platform to analyze oxLDL‐rich plaques, with immunohistology serving as the ground truth. We fabricated the EIS sensor by affixing a six‐point microelectrode configuration onto a silicone balloon catheter and electroplating the surface with platinum black (PtB) to improve the charge transfer efficiency at the electrochemical interface. To demonstrate clinical translation, we deployed the EIS sensor to the coronary arteries of an explanted human heart from a patient undergoing heart transplant and interrogated the atherosclerotic lesions to reconstruct the 3D EIS profiles of oxLDL‐rich atherosclerotic plaques in both right coronary and left descending coronary arteries. To establish effective generalization of our methods, we repeated the reconstruction and training process on the common carotid arteries of an unembalmed human cadaver specimen. Our findings indicated that our DenseNet model achieves the most reliable predictions for metabolically vulnerable plaque, yielding an accuracy of 92.59% after 100 epochs of training.

show abstract

Deep Learning in EEG-Based BCIs: A Comprehensive Review of Transformer Models, Advantages, Challenges, and Applications

Abibullaev,

Keutayeva,

Zollanvari

2023

IEEE Access

View full text Add to dashboard Cite

Brain-computer interfaces (BCIs) have undergone significant advancements in recent years. The integration of deep learning techniques, specifically transformers, has shown promising development in research and application domains. Transformers, which were originally designed for natural language processing, have now made notable inroads into BCIs, offering a unique self-attention mechanism that adeptly handles the temporal dynamics of brain signals. This comprehensive survey delves into the application of transformers in BCIs, providing readers with a lucid understanding of their foundational principles, inherent advantages, potential challenges, and diverse applications. In addition to discussing the benefits of transformers, we also address their limitations, such as computational overhead, interpretability concerns, and the data-intensive nature of these models, providing a well-rounded analysis. Furthermore, the paper sheds light on the myriad of BCI applications that have benefited from the incorporation of transformers. These applications span from motor imagery decoding, emotion recognition, and sleep stage analysis to novel ventures such as speech reconstruction. This review serves as a holistic guide for researchers and practitioners, offering a panoramic view of the transformative potential of transformers in the BCI landscape. With the inclusion of examples and references, readers will gain a deeper understanding of the topic and its significance in the field.

show abstract

Pretrained Transformers for Seizure Detection

Cited by 5 publications

References 8 publications

SeizFt: Interpretable Machine Learning for Seizure Detection Using Wearables

SeizFt: Interpretable Machine Learning for Seizure Detection Using Wearables

Machine learning‐directed electrical impedance tomography to predict metabolically vulnerable plaques

Deep Learning in EEG-Based BCIs: A Comprehensive Review of Transformer Models, Advantages, Challenges, and Applications

Contact Info

Product

Resources

About