Editorial: Intelligent Recognition and Detection in Neuroimaging

Yu-Dong Zhang, German Castellanos-Dominguez, Yuankai Huo, Juan Manuel Gorriz, Roohallah Alizadehsani
2022 Frontiers in Neuroscience  
Editorial on the Research Topic Intelligent Recognition and Detection in Neuroimaging Neuroimaging scan uses various techniques to either directly or indirectly image the nervous system's structure, function, or pharmacology. Those scans are being used more and more to help detect and diagnose many medical disorders and illnesses. Currently, brain scans for mental disorders are in research studies to learn more about the disorders. Many neuroimaging methods are used in hospitals and research
more » ... titutes, such as computed tomography, event-related optical imaging, magnetic resonance imaging (MRI), functional MRI, positron emission tomography, single-photon emission computed tomography, magnetoencephalography, etc. Brain scans alone are commonly used to diagnose neurological and psychiatric diseases, such as Meningioma, glioma, Herpes encephalitis, Huntington's disease, Pick's disease, Alzheimer's disease, Multiple sclerosis, and cerebral palsy toxoplasmosis, Sarcoma, Subdural hematoma, etc. Intelligent recognition and detection use the latest pattern recognition (PR) methods to recognize and detect suspicious areas of neuroimaging scan images. Also, we can realize the analysis, enhancement, reconstruction, segmentation, and classification of those neuroimaging scan images. Those PR methods include support vector machine, deep learning, transfer learning, convolutional neural network, graph neural network, attention neural network, explainable AI, trustworthy AI, etc. This intelligent recognition and detection are still an ongoing developing field. Hence, we expect our topic can intrigue more fascinating works in this area. This topic was online, calling for papers from April/2021. It received more than 40 submissions from over 30 different countries. After strict peer reviews, only eight papers are accepted and published. All the papers are research articles. VOICE DATA Voice data is a meaningful way to help diagnose diseases. Ali et al. investigated Parkinson's disease (PD). Multimodal voice data are put into two channels, i.e., the Smart Phone (SP) and Acoustic Cardioid (AC). Four types of data modalities are collected through each channel, namely sustained phonation (P), speech (S), voiced (V), and unvoiced (U) modality. The contributions of this paper are two-fold. First, it explores optimal data modality and features with better PD information. Second, it proposes a MultiModal Data-Driven Ensemble (MMDD-Ensemble) approach for PD detection. Experimental results show that their proposed multimodal approach yields 96% accuracy, 100% sensitivity, 88.88% specificity, 0.914 MCC, and 0.986 AUC. Their results Publisher's Note: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article, or claim that may be made by its manufacturer, is not guaranteed or endorsed by the publisher.
doi:10.3389/fnins.2022.943180 pmid:35864991 pmcid:PMC9294631 fatcat:s2lvsnw5jvexvcnjmm43ewdwnq