Neurological disease diagnosis is nowadays one of the biggest challenges for clinics, due to the nervous system complexity and the diseases overlapping symptoms. With almost 700 neurological diseases already identified, Alzheimer's and Parkinson's diseases, cerebrovascular diseases, multiple sclerosis, neuroinfectious and neuromuscular diseases are the most well-known. Imaging methods, such as magnetic resonance imaging (MRI), functional near-infrared spectroscopy (fNIRS), CSF biomarkers, electroencephalographic signals (EEG), magnetoencephalographic signals (MEG), Positron emission tomography (PET) images, Single-photon emission computed tomography images and also genetic tests, neurophysiological tests, among others, provide useful information for neurological disease diagnosis.
As neurological diseases have low ratios of diagnosis accuracy, greater research efforts should be devoted to gathering discriminative pathologic measures. One of the possibilities for offering a more correct and accurate diagnosis of nervous system diseases is to search pathological information on biosignals, e.g., EEG, MEG, MRI, fNIRS, and speech, among others, taking advance of biosignals' capacity to gather brain responses continuously over time. Statistical and machine-learning methods can help in modeling cognitive load associated with the pathological activity. Thus, this research topic will focus on new advances and technologies based on artificial intelligence systems (machine learning and deep learning) for nervous system disease diagnosis by means of biosignals.
Topics may include but are not limited to Biosignals and tools for detecting nervous system diseases by:
• classical machine learning (e.g., trees, support-vector-machines & k-neighbors)
• deep learning approaches (e.g., Convolution Neuronal Networks, Long-short-term Networks & autoencoders)
• Signals: EEG, EMG, ECG, MEG, fNIRS, Speech, and Evoked Potential analysis.
Keywords:
Machine learning, Deep Learning, Neurological diseases
Important Note:
All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.
Neurological disease diagnosis is nowadays one of the biggest challenges for clinics, due to the nervous system complexity and the diseases overlapping symptoms. With almost 700 neurological diseases already identified, Alzheimer's and Parkinson's diseases, cerebrovascular diseases, multiple sclerosis, neuroinfectious and neuromuscular diseases are the most well-known. Imaging methods, such as magnetic resonance imaging (MRI), functional near-infrared spectroscopy (fNIRS), CSF biomarkers, electroencephalographic signals (EEG), magnetoencephalographic signals (MEG), Positron emission tomography (PET) images, Single-photon emission computed tomography images and also genetic tests, neurophysiological tests, among others, provide useful information for neurological disease diagnosis.
As neurological diseases have low ratios of diagnosis accuracy, greater research efforts should be devoted to gathering discriminative pathologic measures. One of the possibilities for offering a more correct and accurate diagnosis of nervous system diseases is to search pathological information on biosignals, e.g., EEG, MEG, MRI, fNIRS, and speech, among others, taking advance of biosignals' capacity to gather brain responses continuously over time. Statistical and machine-learning methods can help in modeling cognitive load associated with the pathological activity. Thus, this research topic will focus on new advances and technologies based on artificial intelligence systems (machine learning and deep learning) for nervous system disease diagnosis by means of biosignals.
Topics may include but are not limited to Biosignals and tools for detecting nervous system diseases by:
• classical machine learning (e.g., trees, support-vector-machines & k-neighbors)
• deep learning approaches (e.g., Convolution Neuronal Networks, Long-short-term Networks & autoencoders)
• Signals: EEG, EMG, ECG, MEG, fNIRS, Speech, and Evoked Potential analysis.
Keywords:
Machine learning, Deep Learning, Neurological diseases
Important Note:
All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.