Alternative Diagnosis of Epilepsy in Children Without Epileptiform Discharges Using Deep Convolutional Neural Networks

Lin, Lung‐Chang; Ouyang, Chen‐Sen; Wu, Ray; Yang, Rei‐Cheng; Chiang, Ching‐Tai

doi:10.1142/s0129065718500600

Cited by 39 publications

(43 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The reference electrode, namely Cz, was placed on the midline sagittal plane of the skull. To ensure unbiased comparisons, artifacts caused by eye and muscle movements were manually removed by an experienced neurologist after visual examination in the preprocessing step (Lin et al, 2019 ). For each participant, a 300 s artifact-free EEG signal was extracted for analysis.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Increased Temporal Lobe Beta Activity in Boys With Attention-Deficit Hyperactivity Disorder by LORETA Analysis

Chiang

Ouyang

Yang

et al. 2020

Front. Behav. Neurosci.

Self Cite

View full text Add to dashboard Cite

Aim: Attention-deficit hyperactivity disorder (ADHD) is a common childhood neuropsychiatric disorder that affects 6.1 million US children. The mechanism of ADHD is currently unclear. Differences in ADHD presentations between boys and girls are well-established. In the present study, we used quantitative electroencephalography (EEG) to investigate the brain area and EEG bands of boys with ADHD. Methods: This study enrolled 40 boys with ADHD and 40 age-matched controls without ADHD. Low-resolution electromagnetic tomography (LORETA) and instantaneous frequency were used to analyze EEG data to reveal the mechanisms underlying ADHD in boys. Results: We found that the instantaneous frequencies in the T3 and T4 EEG channels in boys with ADHD were significantly higher than those in the controls. The beta band showed significant difference in current density between the ADHD and control groups. In the entire brain area, the bilateral inferior and middle temporal gyrus exhibited the most significant difference between the ADHD and control groups in the EEG beta band. Connectivity analysis revealed an increase in connectivity between the left middle frontal gyrus and fusiform gyrus of the temporal lobe in boys with ADHD. Conclusions: LORETA is a promising tool for analyzing EEG signals and can be used to investigate the mechanism of ADHD. Our results reveal that the inferior temporal gyrus, middle temporal gyrus, and fusiform gyrus of the temporal lobe are potentially involved in the pathogenesis of ADHD in boys. In comparison with other imaging methods, such as magnetic resonance imaging, EEG is easy to perform, fast, and low cost. Our study presents a new approach for investigating the pathogenesis of ADHD in boys.

show abstract

Section: Methodsmentioning

confidence: 99%

“…The recordings of photic and hyperventilation segments were excluded. Subsequently, EEG signals were normalized as z scores with zero mean and a standard deviation (SD) of 1 (Lin et al, 2019 ).…”

Section: Methodsmentioning

confidence: 99%

Increased Temporal Lobe Beta Activity in Boys With Attention-Deficit Hyperactivity Disorder by LORETA Analysis

Chiang

Ouyang

Yang

et al. 2020

Front. Behav. Neurosci.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Subsequently, EEG signals were normalized as z scores with zero means and SDs of 1. 22 A detailed calculation of instantaneous frequency is given in the Supplemental Appendix (available online).…”

Section: Methodsmentioning

confidence: 99%

“…To enable unbiased comparison, artifacts caused by eye movements and muscle activities were removed manually after visual examination in the preprocessing step. 22 For each participant, 300-second EEGs were extracted for analysis. Subsequently, EEG signals were normalized as z scores with zero means and SDs of 1.…”

Section: Instantaneous Frequencymentioning

confidence: 99%

Delay Maturation in Occipital Lobe in Girls With Inattention Subtype of Attention-Deficit Hyperactivity Disorder

et al. 2020

Self Cite

View full text Add to dashboard Cite

Attention-deficit hyperactivity disorder (ADHD) is a common childhood neuropsychiatric disorder. Differences in the presentations of ADHD between boys and girls have been well established. Three subtypes of ADHD exist. In addition to sex difference, different mechanisms may underlie different subtypes. The present study enrolled 30 girls with the inattentive subtype of ADHD and 30 age-matched controls. Low-resolution electromagnetic tomography (LORETA) and instantaneous frequency were used to analyze electroencephalography (EEG) for investigating the brain area and EEG bands involved in girls with inattentive ADHD. We found that the instantaneous frequencies in all EEG channels in girls with ADHD were lower than those in controls. Alpha 2 was the only EEG band that showed significant difference in current density between the ADHD and control groups ( P = .0014). In the entire brain area, the posterior cingulate cortex, cingulate gyrus, and precuneus demonstrated the most significant difference between the ADHD and control groups. Our results suggest that brain maturation delay in the posterior areas might result in the inattention subtype of ADHD. In addition, posterior cingulate cortex, cingulate gyrus, and precuneus may play a critical role in the pathogenesis of ADHD. Our study provides a new approach method and possible mechanism of girls with inattentive subtype ADHD.

show abstract

“…In [137], a novel imaging tool was presented, where DCNN tract classification method was used to analyze the pre-surgical condition of children with focal epilepsy. [138] mainly distinguished nonepileptic paroxysmal events from epilepsy. In [139], a novel hybrid method using the adaptive Haar wavelet-based binary grasshopper optimization algorithm and DNN was proposed to detect epilepsy with high accuracy.…”

Section: ) Dl-based Approaches In Epilepsy Diagnosismentioning

confidence: 99%

Machine Learning and Deep Learning Approaches for Brain Disease Diagnosis: Principles and Recent Advances

et al. 2021

View full text Add to dashboard Cite

Brain is the controlling center of our body. With the advent of time, newer and newer brain diseases are being discovered. Thus, because of the variability of brain diseases, existing diagnosis or detection systems are becoming challenging and are still an open problem for research. Detection of brain diseases at an early stage can make a huge difference in attempting to cure it. In recent years, the use of artificial intelligence (AI) is surging through all spheres of science, and no doubt, it is revolutionizing the field of neurology. Application of AI in medical science has made brain disease prediction and detection more accurate and precise. In this study, we present a review on recent machine learning and deep learning approaches in detecting four brain diseases such as Alzheimer's disease (AD), brain tumor, epilepsy, and Parkinson's disease. 147 recent articles on four brain diseases are reviewed considering diverse machine learning and deep learning approaches, modalities, datasets etc. Twenty-two datasets are discussed which are used most frequently in the reviewed articles as a primary source of brain disease data. Moreover, a brief overview of different feature extraction techniques that are used in diagnosing brain diseases is provided. Finally, key findings from the reviewed articles are summarized and a number of major issues related to machine learning/deep learning-based brain disease diagnostic approaches are discussed. Through this study, we aim at finding the most accurate technique for detecting different brain diseases which can be employed for future betterment. INDEX TERMS Alzheimer's disease, brain tumor, deep learning, epilepsy, Parkinson's disease, machine learning NOMENCLATURE The most commonly used abbreviations in this survey are summarized in Table 1.

show abstract

Alternative Diagnosis of Epilepsy in Children Without Epileptiform Discharges Using Deep Convolutional Neural Networks

Cited by 39 publications

References 32 publications

Increased Temporal Lobe Beta Activity in Boys With Attention-Deficit Hyperactivity Disorder by LORETA Analysis

Increased Temporal Lobe Beta Activity in Boys With Attention-Deficit Hyperactivity Disorder by LORETA Analysis

Delay Maturation in Occipital Lobe in Girls With Inattention Subtype of Attention-Deficit Hyperactivity Disorder

Machine Learning and Deep Learning Approaches for Brain Disease Diagnosis: Principles and Recent Advances

Contact Info

Product

Resources

About