Introduction - ISIP



IntroductionThe electroencephalogram (EEG) is an excellent tool for probing neural function, both in clinical and research environments, due to its low cost, non-invasive nature, and pervasiveness. In the clinic, the EEG is the standard test for diagnosing and characterizing epilepsy and stroke, as well as a host of other trauma and pathology related conditions ADDIN CSL_CITATION { "citationItems" : [ { "id" : "ITEM-1", "itemData" : { "author" : [ { "dropping-particle" : "", "family" : "Tatum", "given" : "William", "non-dropping-particle" : "", "parse-names" : false, "suffix" : "" }, { "dropping-particle" : "", "family" : "Husain", "given" : "Aatif", "non-dropping-particle" : "", "parse-names" : false, "suffix" : "" }, { "dropping-particle" : "", "family" : "Benbadis", "given" : "Selim", "non-dropping-particle" : "", "parse-names" : false, "suffix" : "" }, { "dropping-particle" : "", "family" : "Kaplan", "given" : "Peter", "non-dropping-particle" : "", "parse-names" : false, "suffix" : "" } ], "id" : "ITEM-1", "issued" : { "date-parts" : [ [ "2007" ] ] }, "publisher" : "Demos Medical Publishing", "publisher-place" : "New York, NY", "title" : "Handbook of EEG Interpretation", "type" : "book" }, "uris" : [ "" ] }, { "id" : "ITEM-2", "itemData" : { "author" : [ { "dropping-particle" : "", "family" : "Yamada", "given" : "T", "non-dropping-particle" : "", "parse-names" : false, "suffix" : "" }, { "dropping-particle" : "", "family" : "Meng", "given" : "E", "non-dropping-particle" : "", "parse-names" : false, "suffix" : "" } ], "id" : "ITEM-2", "issued" : { "date-parts" : [ [ "2009" ] ] }, "publisher" : "Lippincott Williams & Wilkins", "publisher-place" : "Philadelphia, PA", "title" : "Practical Guide for Clinical Neurophysiologic Testing: EEG", "type" : "book" }, "uris" : [ "" ] } ], "mendeley" : { "formattedCitation" : "(Tatum et al. 2007; Yamada and Meng 2009)", "plainTextFormattedCitation" : "(Tatum et al. 2007; Yamada and Meng 2009)", "previouslyFormattedCitation" : "(Tatum, Husain, Benbadis, & Kaplan, 2007; Yamada & Meng, 2009)" }, "properties" : { "noteIndex" : 0 }, "schema" : "" }(Tatum et al. 2007; Yamada and Meng 2009). In research laboratories, EEG is used to study neural responses to external stimuli, motor planning and execution, and brain-computer interfaces ADDIN CSL_CITATION { "citationItems" : [ { "id" : "ITEM-1", "itemData" : { "DOI" : "10.1371/journal.pone.0055344", "ISSN" : "1932-6203", "PMID" : "23405137", "abstract" : "Brain-computer interface (BCI) technology aims to help individuals with disability to control assistive devices and reanimate paralyzed limbs. Our study investigated the feasibility of an electrocorticography (ECoG)-based BCI system in an individual with tetraplegia caused by C4 level spinal cord injury. ECoG signals were recorded with a high-density 32-electrode grid over the hand and arm area of the left sensorimotor cortex. The participant was able to voluntarily activate his sensorimotor cortex using attempted movements, with distinct cortical activity patterns for different segments of the upper limb. Using only brain activity, the participant achieved robust control of 3D cursor movement. The ECoG grid was explanted 28 days post-implantation with no adverse effect. This study demonstrates that ECoG signals recorded from the sensorimotor cortex can be used for real-time device control in paralyzed individuals.", "author" : [ { "dropping-particle" : "", "family" : "Wang", "given" : "Wei", "non-dropping-particle" : "", "parse-names" : false, "suffix" : "" }, { "dropping-particle" : "", "family" : "Collinger", "given" : "Jennifer L", "non-dropping-particle" : "", "parse-names" : false, "suffix" : "" }, { "dropping-particle" : "", "family" : "Degenhart", "given" : "Alan D", "non-dropping-particle" : "", "parse-names" : false, "suffix" : "" }, { "dropping-particle" : "", "family" : "Tyler-Kabara", "given" : "Elizabeth C", "non-dropping-particle" : "", "parse-names" : false, "suffix" : "" }, { "dropping-particle" : "", "family" : "Schwartz", "given" : "Andrew B", "non-dropping-particle" : "", "parse-names" : false, "suffix" : "" }, { "dropping-particle" : "", "family" : "Moran", "given" : "Daniel W", "non-dropping-particle" : "", "parse-names" : false, "suffix" : "" }, { "dropping-particle" : "", "family" : "Weber", "given" : "Douglas J", "non-dropping-particle" : "", "parse-names" : false, "suffix" : "" }, { "dropping-particle" : "", "family" : "Wodlinger", "given" : "Brian", "non-dropping-particle" : "", "parse-names" : false, "suffix" : "" }, { "dropping-particle" : "", "family" : "Vinjamuri", "given" : "Ramana K", "non-dropping-particle" : "", "parse-names" : false, "suffix" : "" }, { "dropping-particle" : "", "family" : "Ashmore", "given" : "Robin C", "non-dropping-particle" : "", "parse-names" : false, "suffix" : "" }, { "dropping-particle" : "", "family" : "Kelly", "given" : "John W", "non-dropping-particle" : "", "parse-names" : false, "suffix" : "" }, { "dropping-particle" : "", "family" : "Boninger", "given" : "Michael L", "non-dropping-particle" : "", "parse-names" : false, "suffix" : "" } ], "container-title" : "PloS one", "id" : "ITEM-1", "issue" : "2", "issued" : { "date-parts" : [ [ "2013", "1" ] ] }, "page" : "e55344", "title" : "An electrocorticographic brain interface in an individual with tetraplegia.", "type" : "article-journal", "volume" : "8" }, "uris" : [ "" ] }, { "id" : "ITEM-2", "itemData" : { "author" : [ { "dropping-particle" : "", "family" : "Lebedev", "given" : "M", "non-dropping-particle" : "", "parse-names" : false, "suffix" : "" }, { "dropping-particle" : "", "family" : "Nicolelis", "given" : "M", "non-dropping-particle" : "", "parse-names" : false, "suffix" : "" } ], "container-title" : "Trends in Neurosciences", "id" : "ITEM-2", "issue" : "9", "issued" : { "date-parts" : [ [ "2006" ] ] }, "page" : "536-546", "title" : "Brain\u2013machine interfaces: past, present and future", "type" : "article-journal", "volume" : "29" }, "uris" : [ "" ] } ], "mendeley" : { "formattedCitation" : "(Wang et al. 2013; Lebedev and Nicolelis 2006)", "plainTextFormattedCitation" : "(Wang et al. 2013; Lebedev and Nicolelis 2006)", "previouslyFormattedCitation" : "(Lebedev & Nicolelis, 2006; Wang et al., 2013)" }, "properties" : { "noteIndex" : 0 }, "schema" : "" }(Wang et al. 2013; Lebedev and Nicolelis 2006). While human interpretation is still the gold standard for EEG analysis in the clinic, a host of software tools exist to facilitate the process or to make predictive analyses such as seizure prediction.Recently, a confluence of events has underscored the need for robust EEG tools. First, there has been a renewed push via the White House BRAIN initiative to understand neural function and disease ADDIN CSL_CITATION { "citationItems" : [ { "id" : "ITEM-1", "itemData" : { "DOI" : "10.1021/nn401796f", "ISSN" : "1936-086X", "PMID" : "23607423", "author" : [ { "dropping-particle" : "", "family" : "Weiss", "given" : "Paul S", "non-dropping-particle" : "", "parse-names" : false, "suffix" : "" } ], "container-title" : "ACS nano", "id" : "ITEM-1", "issue" : "4", "issued" : { "date-parts" : [ [ "2013", "4", "23" ] ] }, "page" : "2873-4", "publisher" : "American Chemical Society", "title" : "President Obama announces the BRAIN Initiative.", "type" : "article-journal", "volume" : "7" }, "uris" : [ "" ] } ], "mendeley" : { "formattedCitation" : "(Weiss 2013)", "plainTextFormattedCitation" : "(Weiss 2013)", "previouslyFormattedCitation" : "(Weiss, 2013)" }, "properties" : { "noteIndex" : 0 }, "schema" : "" }(Weiss 2013). Secondly, there is an increased awareness on brain injury owing to both the influx of injured warfighters and numerous high-profile athletes found to have chronic brain damage ADDIN CSL_CITATION { "citationItems" : [ { "id" : "ITEM-1", "itemData" : { "ISSN" : "0022-3069", "PMID" : "19535999", "abstract" : "Since the 1920s, it has been known that the repetitive brain trauma associated with boxing may produce a progressive neurological deterioration, originally termed dementia pugilistica, and more recently, chronic traumatic encephalopathy (CTE). We review 48 cases of neuropathologically verified CTE recorded in the literature and document the detailed findings of CTE in 3 profession althletes, 1 football player and 2 boxers. Clinically, CTE is associated with memory disturbances, behavioral and personality changes, parkinsonism, and speech and gait abnormalities. Neuropathologically, CTE is characterized by atrophy of the cerebral hemispheres, medial temporal lobe, thalamus, mammillary bodies, and brainstem, with ventricular dilatation and a fenestrated cavum septum pellucidum. Microscopically, there are extensive tau-immunoreactive neurofibrillary tangles, astrocytic tangles, and spindle-shaped and threadlike neurites throughout the brain. The neurofibrillary degeneration of CTE is distinguished from other tauopathies by preferential involvement of the superficial cortical layers, irregular patchy distribution in the frontal and temporal cortices, propensity for sulcal depths, prominent perivascular, periventricular, and subpial distribution, and marked accumulation of tau-immunoreactive astrocytes. Deposition of beta-amyloid, most commonly as diffuse plaques, occurs in fewer than half the cases. Chronic traumatic encephalopathy is a neuropathologically distinct slowly progressive tauopathy with a clear environmental etiology.", "author" : [ { "dropping-particle" : "", "family" : "McKee", "given" : "Ann C", "non-dropping-particle" : "", "parse-names" : false, "suffix" : "" }, { "dropping-particle" : "", "family" : "Cantu", "given" : "Robert C", "non-dropping-particle" : "", "parse-names" : false, "suffix" : "" }, { "dropping-particle" : "", "family" : "Nowinski", "given" : "Christopher J", "non-dropping-particle" : "", "parse-names" : false, "suffix" : "" }, { "dropping-particle" : "", "family" : "Hedley-Whyte", "given" : "E Tessa", "non-dropping-particle" : "", "parse-names" : false, "suffix" : "" }, { "dropping-particle" : "", "family" : "Gavett", "given" : "Brandon E", "non-dropping-particle" : "", "parse-names" : false, "suffix" : "" }, { "dropping-particle" : "", "family" : "Budson", "given" : "Andrew E", "non-dropping-particle" : "", "parse-names" : false, "suffix" : "" }, { "dropping-particle" : "", "family" : "Santini", "given" : "Veronica E", "non-dropping-particle" : "", "parse-names" : false, "suffix" : "" }, { "dropping-particle" : "", "family" : "Lee", "given" : "Hyo-Soon", "non-dropping-particle" : "", "parse-names" : false, "suffix" : "" }, { "dropping-particle" : "", "family" : "Kubilus", "given" : "Caroline A", "non-dropping-particle" : "", "parse-names" : false, "suffix" : "" }, { "dropping-particle" : "", "family" : "Stern", "given" : "Robert A", "non-dropping-particle" : "", "parse-names" : false, "suffix" : "" } ], "container-title" : "Journal of neuropathology and experimental neurology", "id" : "ITEM-1", "issue" : "7", "issued" : { "date-parts" : [ [ "2009", "7" ] ] }, "page" : "709-35", "title" : "Chronic traumatic encephalopathy in athletes: progressive tauopathy after repetitive head injury.", "type" : "article-journal", "volume" : "68" }, "uris" : [ "" ] }, { "id" : "ITEM-2", "itemData" : { "ISSN" : "1934-1563", "PMID" : "22035690", "abstract" : "Chronic traumatic encephalopathy (CTE) has been linked to participation in contact sports such as boxing and American football. CTE results in a progressive decline of memory and cognition, as well as depression, suicidal behavior, poor impulse control, aggressiveness, parkinsonism, and, eventually, dementia. In some individuals, it is associated with motor neuron disease, referred to as chronic traumatic encephalomyelopathy, which appears clinically similar to amyotrophic lateral sclerosis. Results of neuropathologic research has shown that CTE may be more common in former contact sports athletes than previously believed. It is believed that repetitive brain trauma, with or possibly without symptomatic concussion, is responsible for neurodegenerative changes highlighted by accumulations of hyperphosphorylated tau and TDP-43 proteins. Given the millions of youth, high school, collegiate, and professional athletes participating in contact sports that involve repetitive brain trauma, as well as military personnel exposed to repeated brain trauma from blast and other injuries in the military, CTE represents an important public health issue. Focused and intensive study of the risk factors and in vivo diagnosis of CTE will potentially allow for methods to prevent and treat these diseases. Research also will provide policy makers with the scientific knowledge to make appropriate guidelines regarding the prevention and treatment of brain trauma in all levels of athletic involvement as well as the military theater.", "author" : [ { "dropping-particle" : "", "family" : "Stern", "given" : "Robert A", "non-dropping-particle" : "", "parse-names" : false, "suffix" : "" }, { "dropping-particle" : "", "family" : "Riley", "given" : "David O", "non-dropping-particle" : "", "parse-names" : false, "suffix" : "" }, { "dropping-particle" : "", "family" : "Daneshvar", "given" : "Daniel H", "non-dropping-particle" : "", "parse-names" : false, "suffix" : "" }, { "dropping-particle" : "", "family" : "Nowinski", "given" : "Christopher J", "non-dropping-particle" : "", "parse-names" : false, "suffix" : "" }, { "dropping-particle" : "", "family" : "Cantu", "given" : "Robert C", "non-dropping-particle" : "", "parse-names" : false, "suffix" : "" }, { "dropping-particle" : "", "family" : "McKee", "given" : "Ann C", "non-dropping-particle" : "", "parse-names" : false, "suffix" : "" } ], "container-title" : "PM & R : the journal of injury, function, and rehabilitation", "id" : "ITEM-2", "issue" : "10 Suppl 2", "issued" : { "date-parts" : [ [ "2011", "10" ] ] }, "page" : "S460-7", "publisher" : "Elsevier Inc.", "title" : "Long-term consequences of repetitive brain trauma: chronic traumatic encephalopathy.", "type" : "article-journal", "volume" : "3" }, "uris" : [ "" ] } ], "mendeley" : { "formattedCitation" : "(McKee et al. 2009; Stern et al. 2011)", "plainTextFormattedCitation" : "(McKee et al. 2009; Stern et al. 2011)", "previouslyFormattedCitation" : "(McKee et al., 2009; Stern et al., 2011)" }, "properties" : { "noteIndex" : 0 }, "schema" : "" }(McKee et al. 2009; Stern et al. 2011). And thirdly, a wave of consumer grade scalp sensors has entered the market, allowing end users to monitor sleep, arousal, and mood ADDIN CSL_CITATION { "citationItems" : [ { "id" : "ITEM-1", "itemData" : { "author" : [ { "dropping-particle" : "", "family" : "Liao", "given" : "By Lun-de", "non-dropping-particle" : "", "parse-names" : false, "suffix" : "" }, { "dropping-particle" : "", "family" : "Lin", "given" : "Chin-teng", "non-dropping-particle" : "", "parse-names" : false, "suffix" : "" }, { "dropping-particle" : "", "family" : "McDowell", "given" : "Kaleb", "non-dropping-particle" : "", "parse-names" : false, "suffix" : "" }, { "dropping-particle" : "", "family" : "Wickenden", "given" : "Alma E", "non-dropping-particle" : "", "parse-names" : false, "suffix" : "" }, { "dropping-particle" : "", "family" : "Gramann", "given" : "Klaus", "non-dropping-particle" : "", "parse-names" : false, "suffix" : "" }, { "dropping-particle" : "", "family" : "Jung", "given" : "Tzyy-ping", "non-dropping-particle" : "", "parse-names" : false, "suffix" : "" }, { "dropping-particle" : "", "family" : "Ko", "given" : "Li-Wei", "non-dropping-particle" : "", "parse-names" : false, "suffix" : "" }, { "dropping-particle" : "", "family" : "Chang", "given" : "Jyh-Yeong", "non-dropping-particle" : "", "parse-names" : false, "suffix" : "" } ], "container-title" : "Proceedings of the IEEE", "id" : "ITEM-1", "issued" : { "date-parts" : [ [ "2012" ] ] }, "page" : "1553-1566", "title" : "Biosensor Technologies for Augmented Brain \u2013 Computer Interfaces in the Next Decades", "type" : "article-journal", "volume" : "100" }, "uris" : [ "" ] } ], "mendeley" : { "formattedCitation" : "(Liao et al. 2012)", "plainTextFormattedCitation" : "(Liao et al. 2012)", "previouslyFormattedCitation" : "(Liao et al., 2012)" }, "properties" : { "noteIndex" : 0 }, "schema" : "" }(Liao et al. 2012).In all these applications, there is a need for robust signal processing tools to analyze the EEG data. Historically, EEG signal processing tools have been devised using either ad hoc heuristic methods, or by training pattern recognition engines on small data sets ADDIN CSL_CITATION { "citationItems" : [ { "id" : "ITEM-1", "itemData" : { "DOI" : "10.1016/0013-4694(82)90038-4", "ISSN" : "00134694", "abstract" : "During prolonged EEG monitoring of epileptic patients, the continuous EEG tracing may be replaced by a selective recording of ictal and interictal epileptic activity. We have described previously methods for the EEG recording of seizures with overt clinical manifestations and for the automatic detection of spikes. This paper describes a method for the automatic detection of seizures in the EEG, independently of the presence of clinical signs; it is based on the decomposition of the EEG into elementary waves and the detection of paroxysmal bursts of rhythmic activity having a frequency between 3 and 20 c/sec. Simple procedures are used to measure the amplitude of waves relative to the background, their duration and rhythmicity. The evaluation of the method on 24 surface recordings (average duration 12.4 h) and 44 recordings from intracerebral electrodes (average duration 18.7 h) indicated that it was capable of recognizing numerous types of seizures. False detections due to non-epileptiform rhythmic EEG bursts and to artefacts were quite frequent but were not a serious problem because they did not unduly lengthen the EEG tracing and they could be easily identified by the electroencephalographer. The program can perform on-line and simultaneously the automatic recognition of spikes and of seizures in 16 channels. Au cours de sessions prolong\u00e9es d'enregistrement EEG chez les malades \u00e9pileptiques, il est possible de remplacer le trac\u00e9 EEG continu par un enregistrement s\u00e9lectif de l'activit\u00e9 \u00e9pileptique critique et intercritique. Nous avions d\u00e9crit auparavant des m\u00e9thodes d'enregistrement de crises avec manifestations cliniques apparentes et de reconnaissance automatique des pointes. Le pr\u00e9sent article d\u00e9crit une m\u00e9thode de d\u00e9tection automatique des crises, qu'elles aient ou non des manifestations cliniques. Elle est fond\u00e9e sur la d\u00e9composition de l'EEG en ondes \u00e9l\u00e9mentaires et la d\u00e9tection de bouff\u00e9es paroxystiques et rythmiques ayant une fr\u00e9quence de 3 \u00e0 20 c/sec. Des calculs simples sont utilis\u00e9s pour mesurer l'amplitude des ondes relativement \u00e0 l'activit\u00e9 de fond, leur dur\u00e9e et leur rythmicit\u00e9. Cette m\u00e9thode a \u00e9t\u00e9 \u00e9valu\u00e9e \u00e0 l'aide de 24 EEG de surface (dur\u00e9e moyenne 12,4 h) et 44 EEG d'\u00e9lectrodes intrac\u00e9r\u00e9brales (dur\u00e9e moyenne 18,7 h); les r\u00e9sultats montrent que de nombreux types de crises ont pu \u00eatre d\u00e9tect\u00e9s. Il y eut aussi d'assez nombreuses fausses d\u00e9tections dues \u00e0 des bouff\u00e9es EEG rythmiques mais non \u00e9pileptiques et \u00e0 des art\u00e9facts; ce probl\u00e8me n'e\u2026", "author" : [ { "dropping-particle" : "", "family" : "Gotman", "given" : "J", "non-dropping-particle" : "", "parse-names" : false, "suffix" : "" } ], "container-title" : "Electroencephalography and Clinical Neurophysiology", "id" : "ITEM-1", "issue" : "5", "issued" : { "date-parts" : [ [ "1982", "11" ] ] }, "page" : "530-540", "title" : "Automatic recognition of epileptic seizures in the EEG", "type" : "article-journal", "volume" : "54" }, "uris" : [ "" ] } ], "mendeley" : { "formattedCitation" : "(Gotman 1982)", "plainTextFormattedCitation" : "(Gotman 1982)", "previouslyFormattedCitation" : "(Gotman, 1982)" }, "properties" : { "noteIndex" : 0 }, "schema" : "" }(Gotman 1982). These methods have yielded limited results, owing mostly to the fact that brain signals (and EEG in particular) are characterized by great variability, which can only be properly interpreted by building statistical models using massive amounts of data ADDIN CSL_CITATION { "citationItems" : [ { "id" : "ITEM-1", "itemData" : { "DOI" : "10.1186/1687-6180-2014-183", "ISSN" : "1687-6180", "author" : [ { "dropping-particle" : "", "family" : "Alotaiby", "given" : "Turkey N", "non-dropping-particle" : "", "parse-names" : false, "suffix" : "" }, { "dropping-particle" : "", "family" : "Alshebeili", "given" : "Saleh A", "non-dropping-particle" : "", "parse-names" : false, "suffix" : "" }, { "dropping-particle" : "", "family" : "Alshawi", "given" : "Tariq", "non-dropping-particle" : "", "parse-names" : false, "suffix" : "" }, { "dropping-particle" : "", "family" : "Ahmad", "given" : "Ishtiaq", "non-dropping-particle" : "", "parse-names" : false, "suffix" : "" }, { "dropping-particle" : "", "family" : "Abd El-Samie", "given" : "Fathi E", "non-dropping-particle" : "", "parse-names" : false, "suffix" : "" } ], "container-title" : "EURASIP Journal on Advances in Signal Processing", "id" : "ITEM-1", "issue" : "1", "issued" : { "date-parts" : [ [ "2014" ] ] }, "page" : "183", "title" : "EEG seizure detection and prediction algorithms: a survey", "type" : "article-journal", "volume" : "2014" }, "uris" : [ "" ] }, { "id" : "ITEM-2", "itemData" : { "DOI" : "10.1016/j.yebeh.2014.06.023", "ISSN" : "1525-5069", "PMID" : "25174001", "abstract" : "Nearly one-third of patients with epilepsy continue to have seizures despite optimal medication management. Systems employed to detect seizures may have the potential to improve outcomes in these patients by allowing more tailored therapies and might, additionally, have a role in accident and SUDEP prevention. Automated seizure detection and prediction require algorithms which employ feature computation and subsequent classification. Over the last few decades, methods have been developed to detect seizures utilizing scalp and intracranial EEG, electrocardiography, accelerometry and motion sensors, electrodermal activity, and audio/video captures. To date, it is unclear which combination of detection technologies yields the best results, and approaches may ultimately need to be individualized. This review presents an overview of seizure detection and related prediction methods and discusses their potential uses in closed-loop warning systems in epilepsy.", "author" : [ { "dropping-particle" : "", "family" : "Ramgopal", "given" : "Sriram", "non-dropping-particle" : "", "parse-names" : false, "suffix" : "" }, { "dropping-particle" : "", "family" : "Thome-Souza", "given" : "Sigride", "non-dropping-particle" : "", "parse-names" : false, "suffix" : "" }, { "dropping-particle" : "", "family" : "Jackson", "given" : "Michele", "non-dropping-particle" : "", "parse-names" : false, "suffix" : "" }, { "dropping-particle" : "", "family" : "Kadish", "given" : "Navah Ester", "non-dropping-particle" : "", "parse-names" : false, "suffix" : "" }, { "dropping-particle" : "", "family" : "S\u00e1nchez Fern\u00e1ndez", "given" : "Iv\u00e1n", "non-dropping-particle" : "", "parse-names" : false, "suffix" : "" }, { "dropping-particle" : "", "family" : "Klehm", "given" : "Jacquelyn", "non-dropping-particle" : "", "parse-names" : false, "suffix" : "" }, { "dropping-particle" : "", "family" : "Bosl", "given" : "William", "non-dropping-particle" : "", "parse-names" : false, "suffix" : "" }, { "dropping-particle" : "", "family" : "Reinsberger", "given" : "Claus", "non-dropping-particle" : "", "parse-names" : false, "suffix" : "" }, { "dropping-particle" : "", "family" : "Schachter", "given" : "Steven", "non-dropping-particle" : "", "parse-names" : false, "suffix" : "" }, { "dropping-particle" : "", "family" : "Loddenkemper", "given" : "Tobias", "non-dropping-particle" : "", "parse-names" : false, "suffix" : "" } ], "container-title" : "Epilepsy & behavior : E&B", "id" : "ITEM-2", "issued" : { "date-parts" : [ [ "2014", "8" ] ] }, "page" : "291-307", "title" : "Seizure detection, seizure prediction, and closed-loop warning systems in epilepsy.", "type" : "article-journal", "volume" : "37" }, "uris" : [ "" ] } ], "mendeley" : { "formattedCitation" : "(Alotaiby et al. 2014; Ramgopal et al. 2014)", "plainTextFormattedCitation" : "(Alotaiby et al. 2014; Ramgopal et al. 2014)", "previouslyFormattedCitation" : "(Alotaiby, Alshebeili, Alshawi, Ahmad, & Abd El-Samie, 2014; Ramgopal et al., 2014)" }, "properties" : { "noteIndex" : 0 }, "schema" : "" }(Alotaiby et al. 2014; Ramgopal et al. 2014). Unfortunately, despite EEG being perhaps the most pervasive modality for acquiring brain signals, there is a severe lack of data in the public domain. For example, the “EEG Motor Movement/Imagery Dataset” () contains approximately 1500 recordings of one or two minutes duration apiece from 109 subjects ADDIN CSL_CITATION { "citationItems" : [ { "id" : "ITEM-1", "itemData" : { "ISSN" : "0009-7322", "author" : [ { "dropping-particle" : "", "family" : "Goldberger", "given" : "Ary L", "non-dropping-particle" : "", "parse-names" : false, "suffix" : "" }, { "dropping-particle" : "", "family" : "Amaral", "given" : "Luis A N", "non-dropping-particle" : "", "parse-names" : false, "suffix" : "" }, { "dropping-particle" : "", "family" : "Glass", "given" : "Leon", "non-dropping-particle" : "", "parse-names" : false, "suffix" : "" }, { "dropping-particle" : "", "family" : "Hausdorff", "given" : "Jeffrey M", "non-dropping-particle" : "", "parse-names" : false, "suffix" : "" }, { "dropping-particle" : "", "family" : "Ivanov", "given" : "Plamen Ch", "non-dropping-particle" : "", "parse-names" : false, "suffix" : "" }, { "dropping-particle" : "", "family" : "Mark", "given" : "Roger G", "non-dropping-particle" : "", "parse-names" : false, "suffix" : "" }, { "dropping-particle" : "", "family" : "Mietus", "given" : "Joseph E", "non-dropping-particle" : "", "parse-names" : false, "suffix" : "" }, { "dropping-particle" : "", "family" : "Moody", "given" : "George B", "non-dropping-particle" : "", "parse-names" : false, "suffix" : "" }, { "dropping-particle" : "", "family" : "Peng", "given" : "Chung-Kang", "non-dropping-particle" : "", "parse-names" : false, "suffix" : "" }, { "dropping-particle" : "", "family" : "Stanley", "given" : "H Eugene", "non-dropping-particle" : "", "parse-names" : false, "suffix" : "" } ], "container-title" : "Circulation", "id" : "ITEM-1", "issue" : "23", "issued" : { "date-parts" : [ [ "2000" ] ] }, "page" : "e215--e220", "publisher" : "Lippincott Williams & Wilkins", "title" : "Physiobank, physiotoolkit, and physionet components of a new research resource for complex physiologic signals", "type" : "article-journal", "volume" : "101" }, "uris" : [ "" ] }, { "id" : "ITEM-2", "itemData" : { "DOI" : "10.1109/TBME.2004.827072", "ISSN" : "0018-9294", "PMID" : "15188875", "abstract" : "Many laboratories have begun to develop brain-computer interface (BCI) systems that provide communication and control capabilities to people with severe motor disabilities. Further progress and realization of practical applications depends on systematic evaluations and comparisons of different brain signals, recording methods, processing algorithms, output formats, and operating protocols. However, the typical BCI system is designed specifically for one particular BCI method and is, therefore, not suited to the systematic studies that are essential for continued progress. In response to this problem, we have developed a documented general-purpose BCI research and development platform called BCI2000. BCI2000 can incorporate alone or in combination any brain signals, signal processing methods, output devices, and operating protocols. This report is intended to describe to investigators, biomedical engineers, and computer scientists the concepts that the BC12000 system is based upon and gives examples of successful BCI implementations using this system. To date, we have used BCI2000 to create BCI systems for a variety of brain signals, processing methods, and applications. The data show that these systems function well in online operation and that BCI2000 satisfies the stringent real-time requirements of BCI systems. By substantially reducing labor and cost, BCI2000 facilitates the implementation of different BCI systems and other psychophysiological experiments. It is available with full documentation and free of charge for research or educational purposes and is currently being used in a variety of studies by many research groups.", "author" : [ { "dropping-particle" : "", "family" : "Schalk", "given" : "Gerwin", "non-dropping-particle" : "", "parse-names" : false, "suffix" : "" }, { "dropping-particle" : "", "family" : "McFarland", "given" : "Dennis J", "non-dropping-particle" : "", "parse-names" : false, "suffix" : "" }, { "dropping-particle" : "", "family" : "Hinterberger", "given" : "Thilo", "non-dropping-particle" : "", "parse-names" : false, "suffix" : "" }, { "dropping-particle" : "", "family" : "Birbaumer", "given" : "Niels", "non-dropping-particle" : "", "parse-names" : false, "suffix" : "" }, { "dropping-particle" : "", "family" : "Wolpaw", "given" : "Jonathan R", "non-dropping-particle" : "", "parse-names" : false, "suffix" : "" } ], "container-title" : "IEEE transactions on bio-medical engineering", "id" : "ITEM-2", "issue" : "6", "issued" : { "date-parts" : [ [ "2004", "6" ] ] }, "page" : "1034-43", "title" : "BCI2000: a general-purpose brain-computer interface (BCI) system.", "type" : "article-journal", "volume" : "51" }, "uris" : [ "" ] } ], "mendeley" : { "formattedCitation" : "(Goldberger et al. 2000; Schalk et al. 2004)", "plainTextFormattedCitation" : "(Goldberger et al. 2000; Schalk et al. 2004)", "previouslyFormattedCitation" : "(Goldberger et al., 2000; Schalk, McFarland, Hinterberger, Birbaumer, & Wolpaw, 2004)" }, "properties" : { "noteIndex" : 0 }, "schema" : "" }(Goldberger et al. 2000; Schalk et al. 2004). The CHB-MIT database contains data from 22 subjects, mostly pediatric ADDIN CSL_CITATION { "citationItems" : [ { "id" : "ITEM-1", "itemData" : { "author" : [ { "dropping-particle" : "", "family" : "Shoeb", "given" : "Ali", "non-dropping-particle" : "", "parse-names" : false, "suffix" : "" } ], "id" : "ITEM-1", "issued" : { "date-parts" : [ [ "2009" ] ] }, "publisher" : "MIT", "title" : "Application of Machine Learning to Epileptic Seizure Onset Detection and Treatment", "type" : "thesis" }, "uris" : [ "" ] } ], "mendeley" : { "formattedCitation" : "(Shoeb 2009)", "plainTextFormattedCitation" : "(Shoeb 2009)", "previouslyFormattedCitation" : "(Shoeb, 2009)" }, "properties" : { "noteIndex" : 0 }, "schema" : "" }(Shoeb 2009). A database from Karunya University contains 175 16-channel EEGs of duration 10 seconds ADDIN CSL_CITATION { "citationItems" : [ { "id" : "ITEM-1", "itemData" : { "DOI" : "10.1177/1550059413500960", "ISSN" : "1550-0594", "PMID" : "24357675", "abstract" : "This article presents an online accessible electroencephalogram (EEG) database, where the EEG recordings comprise abnormal patterns such as spikes, poly spikes, slow waves, and sharp waves to help diagnose related disorders. The data, as of now, are a collection of EEGs from a diagnostic center in Coimbatore, Tamil Nadu, India, and the data samples pertain to an age-group ranging from 1 to 107 years. Eventually, the EEG data concerning other disorders as well as those from other institutions will be included. The present database provides information under the following categories: major classification of the disorder, patient's record, digitized EEG, and specific diagnosis; in addition, a search facility is incorporated into the database. The mode of access by the domain experts, application developers, and researchers, along with a few classical applications are explained in this article. With the advance of clinical neuroscience, this database will be helpful in developing software for applications such as diagnosis and treatment.", "author" : [ { "dropping-particle" : "", "family" : "Selvaraj", "given" : "Thomas George", "non-dropping-particle" : "", "parse-names" : false, "suffix" : "" }, { "dropping-particle" : "", "family" : "Ramasamy", "given" : "Balakrishnan", "non-dropping-particle" : "", "parse-names" : false, "suffix" : "" }, { "dropping-particle" : "", "family" : "Jeyaraj", "given" : "Stanly Johnson", "non-dropping-particle" : "", "parse-names" : false, "suffix" : "" }, { "dropping-particle" : "", "family" : "Suviseshamuthu", "given" : "Easter Selvan", "non-dropping-particle" : "", "parse-names" : false, "suffix" : "" } ], "container-title" : "Clinical EEG and neuroscience", "id" : "ITEM-1", "issue" : "4", "issued" : { "date-parts" : [ [ "2014", "3", "28" ] ] }, "page" : "304-309", "title" : "EEG Database of Seizure Disorders for Experts and Application Developers.", "type" : "article-journal", "volume" : "45" }, "uris" : [ "" ] } ], "mendeley" : { "formattedCitation" : "(Selvaraj et al. 2014)", "plainTextFormattedCitation" : "(Selvaraj et al. 2014)", "previouslyFormattedCitation" : "(Selvaraj, Ramasamy, Jeyaraj, & Suviseshamuthu, 2014)" }, "properties" : { "noteIndex" : 0 }, "schema" : "" }(Selvaraj et al. 2014). One of the most extensive databases for supporting epilepsy research is the European Epilepsy Database (), which contains 250 datasets from 30 unique patients, but sells for €3,000. Other databases, such as , contain a wealth of data from more invasive modalities such as electrocorticogram, but little or no EEG. This lack of publically available data is ironic considering that hundreds of thousands of EEGs are administered annually in clinical settings around the world. Relatively little of this data is publicly available to the research community in a form that is useful to machine learning research. Massive amounts of EEG data would allow the use of state-of-the-art machine learning algorithms to discover new diagnostics and validate clinical practice. Furthermore, it is desirable that such data be collected in clinical settings, as opposed to tightly controlled research environments, since ‘clinical-grade’ data is inherently more variable with respect to parameters such as electrode location, clinical environment, equipment and noise. Capturing this variability is critical to the development of robust, high performance technology that has real-world impact.In this work, we describe a new corpus, the TUH-EEG Corpus, which is an ongoing data collection effort that has recently released 14 years of clinical EEG data collected at Temple University Hospital. The records have been curated, organized, and paired with textual clinician reports that describe the patients and scans. The corpus is publicly available from the Neural Engineering Data Consortium ().MethodsClinical EEG data were collected from archival records at Temple University Hospital (TUH). All work was performed in accordance with the Declaration of Helsinki and with the full approval of the Temple University IRB. All personnel in contact with privileged patient information were fully trained on patient privacy and were certified by the Temple IRB.Archival EEG signal data were recovered from CD-ROMs. Files were converted from their native proprietary file format (Nicolet’s NicVue) to an open format EDF standard. Data was then rigorously de-identified to conform to the HIPAA Privacy Rule by eliminating 18 potential identifiers including patient names and dates of birth. Patient medical record numbers were replaced with randomized database identifiers, with a key to that mapping being saved to a secure off-line location. Importantly, our process captured instances in which the same patient received multiple EEGs over time and assigned database IDs accordingly. Data de-identification was performed by combining automated custom-designed software tools with manual editing and proofreading. All storage and manipulation of source files was conducted on dedicated non-network connected computers that were physically located within the TUH Department of Neurology.We also manually paired each retrieved EEG with its corresponding clinician report. These reports are generated by the neurologist after analyzing the EEG scan and are the official hospital summary of the clinical impression. These reports are comprised of unstructured text that describes the patient, relevant history, medications, and clinical impression. Reports were mined from the hospital’s central electronic medical records archives and typically consisted of image scans of printed reports. Various levels of image processing were employed to improve the image quality before applying optical character recognition (OCR) to convert the images into text. A combination of software and manual editing was used to scrub protected health information (PHI) from the reports and to correct errors in OCR transcription. Only sessions with both an EEG and a corresponding clinician report were included in the final corpus.The corpus was defined with a hierarchical Unix-style filetree structure. The top folder, edf, contains 109 numbered folders, each of which contain numbered folders for up to 100 patients. Each of these patient folders contains sub-folders that correspond to individual recording sessions. Those folder names reflect the session number and date of recording. Finally, each session folder includes one or more EEG (.edf) data files as well as the clinician report in .txt format. Figure 1 summarizes the corpus file structure and gives examples of text and signal data.ResultsThe completed corpus comprises 16,986 sessions from 10,874 unique subjects. Each of these sessions contains at least one EDF file (more in the case of long term monitoring sessions that were broken into multiple files) and one physician report. Corpus metrics are summarized in Figure 2. Subjects were 51% female and ranged in age from less than one year to over 90 (average 51.6, stdev 55.9; see Figure 2 bottom left). The average number of sessions per patient was 1.56, although as many as 37 EEGs were recorded for a single patient over an eight-month period (Figure 2 top left). The number of sessions per year varies from approximately 1,000-2,500 (with the exception of years 2000-2002, and 2005, in which limited numbers of complete reports were found in the various electronic medical record archives; see Figure 2 top right).There was a substantial degree of variability with respect to the number of channels included in the corpus (see Figure 2 bottom right). EDF files typically contained both EEG-specific channels as well as supplementary channels such as detected bursts, EKG, EMG, and photic stimuli. The most common number of EEG-only channels per EDF file was 31, although there were cases with as few as 20. A majority of the EEG data was sampled at 250Hz (87%) with the remaining data being sampled at 256Hz (8.3%), 400Hz (3.8%), and 512Hz (1%).An initial analysis of the physician reports reveals a wide range of medications and medical conditions. Unsurprisingly, the most common listed medications were anti-convulsants such as Keppra and Dilantin, as well as blood thinners such as Lovenox and heparin. Approximately 87% of the reports included the text string ‘epilep’, and about 12% included ‘stroke’. Only 48 total reports included the string ‘concus’.The TUH-EEG corpus v0.6.0 has been released and is freely available online at . Users must register with a valid email address. The uncompressed EDF files and reports together comprise 572?GB. For convenience, the website stores all data from each patient as individual gzip files with a median filesize of 4.1?MB; all 10,874 gzips together comprise 330GB. Users wanting to access the entire database are encouraged to physically mail a USB hard drive to the authors in order to avoid the downloading process.DiscussionThis work presents the world’s largest publically available corpus of clinical EEG data, representing a grand total of 29.1 years (total duration summed over all EEG channels) of EEG data. In addition to its size, this corpus features a wide variation of patient ages, diagnoses, medications, channel counts, and sampling rates. Furthermore, the corpus continues to be expanded at a rate of approximately 2,500 new sessions per year.Biomedicine is entering a new age of data-driven discovery driven by ubiquitous computing power, inexpensive data storage, the machine learning revolution, and high speed internet connections. Access to massive quantities of properly curated data is now the critical bottleneck to advancement in many areas of biomedical research. Ironically, doctors and clinicians generate enormous quantities of data every day, but that information is almost exclusively sequestered in secure archives where it cannot be used for research by the biomedical research community. The quantity, quality, and variability of such data represent a significant unrealized potential, which is doubly unfortunate considering that the cost of generating that data has already been borne. Although there has been some advancement with respect to publishing databases of patient metadata, curated signal databases are much less commonly available, especially in quantities that would be sufficient to train most contemporary machine learning engines.In this work, we have endeavored to achieve two goals. The first is to create a corpus of clinical EEG signals and their corresponding physician reports. The second is to establish best practices for the curation and publication of clinical signal data, which is an inherently different entity than discrete metadata. The EEG corpus we present here is the first of its kind, both in terms of volume and heterogeneity, both of which are critical factors for training machine learning engines. Typically, “research-grade” data is created by tightly controlling as many external factors as possible. In contrast, “clinical-grade” data is inherently heterogeneous with respect to those same external factors. Whereas certain classes of research questions can only be answered using well-controlled data, others benefit from variability. For example, an epilepsy detection algorithm that is trained using 31 specific EEG channels may not be effective if one or more of those channels are not connected, or if the electrodes are improperly located or affixed to the scalp. Algorithms that must be sufficiently robust to function under a plurality of conditions must be trained with data that is sufficiently heterogeneous.Our work has shown that, although clinical signal data is ubiquitous and inherently valuable to the research community, it requires substantial manipulation before it can be released as an adequately curated data corpus. This effort is non-trivial, both in terms of time and cost. Our team’s activities ranged from the mundane (e.g. manually copying archival hospital data from over 1,500 CD-ROMs) to more technical challenges (e.g, developing software for detecting data entry errors in the clinical records). Physician reports had to be located through one of five different EMR portals, often manually. A battery of tests was created to validate that each record was complete, unique, error-free, and completely free of privileged patient information. A rigorous accounting system was created to track and organize the tens of thousands of files and their status. The cost to develop the TUH EEG Corpus has been relatively low, totaling less than $100K in direct charges. As medical record technology improves, the cost of this collection can be reduced even further. On the balance, these types of large-scale collections are a worthwhile investment, since costs are minor relative to the cost of acquiring the data or conducting research on the data. In general, the authors expect that a dedicated community-wide data facility would be best suited to curate data of the magnitude and complexity described here because there are significant on-going costs associated with such an activity.An example of these on-going costs is annotation of the data – a critical issue for machine learning research. In most semi-supervised machine learning applications, one of the first steps is to annotate the data, a process in which important elements of the signal are marked as such. This can be performed either manually by a human domain expert, or automatically with a bootstrap-style algorithm. In addition to the EEG data itself, we are releasing a collection of annotations which may be downloaded separately if they are of interest to the user. The annotations contain the start and stop time and an event label and are specific to each channel. Six classes of events are included: (1)?spike and/or sharp waves (SPSW), (2)?periodic lateralized epileptiform discharges (PLED), and (3) generalized periodic epileptiform discharges (GPED). SPSW events are epileptiform transients that are typically observed in patients with epilepsy. PLED events are indicative of EEG abnormalities and often manifest themselves with repetitive spike or sharp wave discharges that can be focal or lateralized over one hemisphere. These signals display quasi-periodic behavior. GPED events are similar to PLEDs, and manifest themselves as periodic short-interval diffuse discharges, periodic long-interval diffuse discharges and suppression-burst patterns according to the interval between the discharges. Triphasic waves, which manifest themselves as diffuse and bilaterally synchronous spikes with bifrontal predominance, typically at a rate of 1-2 Hz, are also included in this class.Three events are used to model background noise: (1) artifacts (ARTF) are recorded electrical activity that is not of cerebral origin, such as those due to the equipment, patient behavior or the environment; (2) eye movement (EYEM) are common events that can often be confused with a spike; (3) background (BCKG) is used for all other signals.These six classes (three signal classes and three noise classes) were arrived at through several iterations of a study conducted with Temple University Hospital neurologists. Automatic labeling of these events allows a neurologist to rapidly search long-term EEG recordings for anomalous behavior. However, there are many more annotations that need to be developed for this data. For example, we are currently developing technology to automatically annotate seizures. There are many other events of interest that need annotation (e.g. sleep states). We expect to be continually enhancing the value of the TUH EEG Corpus.BibliographyADDIN Mendeley Bibliography CSL_BIBLIOGRAPHY Alotaiby, Turkey N, Saleh A Alshebeili, Tariq Alshawi, Ishtiaq Ahmad, and Fathi E Abd El-Samie. 2014. “EEG Seizure Detection and Prediction Algorithms: A Survey.” EURASIP Journal on Advances in Signal Processing 2014 (1): 183. doi:10.1186/1687-6180-2014-183.Goldberger, Ary L, Luis A N Amaral, Leon Glass, Jeffrey M Hausdorff, Plamen Ch Ivanov, Roger G Mark, Joseph E Mietus, George B Moody, Chung-Kang Peng, and H Eugene Stanley. 2000. “Physiobank, Physiotoolkit, and Physionet Components of a New Research Resource for Complex Physiologic Signals.” Circulation 101 (23): e215–e220.Gotman, J. 1982. “Automatic Recognition of Epileptic Seizures in the EEG.” Electroencephalography and Clinical Neurophysiology 54 (5) (November): 530–540. doi:10.1016/0013-4694(82)90038-4.Lebedev, M, and M Nicolelis. 2006. “Brain–machine Interfaces: Past, Present and Future.” Trends in Neurosciences 29 (9): 536–546.Liao, By Lun-de, Chin-teng Lin, Kaleb McDowell, Alma E Wickenden, Klaus Gramann, Tzyy-ping Jung, Li-Wei Ko, and Jyh-Yeong Chang. 2012. “Biosensor Technologies for Augmented Brain – Computer Interfaces in the Next Decades.” Proceedings of the IEEE 100: 1553–1566.McKee, Ann C, Robert C Cantu, Christopher J Nowinski, E Tessa Hedley-Whyte, Brandon E Gavett, Andrew E Budson, Veronica E Santini, Hyo-Soon Lee, Caroline A Kubilus, and Robert A Stern. 2009. “Chronic Traumatic Encephalopathy in Athletes: Progressive Tauopathy after Repetitive Head Injury.” Journal of Neuropathology and Experimental Neurology 68 (7) (July): 709–35.Ramgopal, Sriram, Sigride Thome-Souza, Michele Jackson, Navah Ester Kadish, Iván Sánchez Fernández, Jacquelyn Klehm, William Bosl, Claus Reinsberger, Steven Schachter, and Tobias Loddenkemper. 2014. “Seizure Detection, Seizure Prediction, and Closed-Loop Warning Systems in Epilepsy.” Epilepsy & Behavior?: E&B 37 (August): 291–307. doi:10.1016/j.yebeh.2014.06.023.Schalk, Gerwin, Dennis J McFarland, Thilo Hinterberger, Niels Birbaumer, and Jonathan R Wolpaw. 2004. “BCI2000: A General-Purpose Brain-Computer Interface (BCI) System.” IEEE Transactions on Bio-Medical Engineering 51 (6) (June): 1034–43. doi:10.1109/TBME.2004.827072.Selvaraj, Thomas George, Balakrishnan Ramasamy, Stanly Johnson Jeyaraj, and Easter Selvan Suviseshamuthu. 2014. “EEG Database of Seizure Disorders for Experts and Application Developers.” Clinical EEG and Neuroscience 45 (4) (March 28): 304–309. doi:10.1177/1550059413500960.Shoeb, Ali. 2009. “Application of Machine Learning to Epileptic Seizure Onset Detection and Treatment.” MIT.Stern, Robert A, David O Riley, Daniel H Daneshvar, Christopher J Nowinski, Robert C Cantu, and Ann C McKee. 2011. “Long-Term Consequences of Repetitive Brain Trauma: Chronic Traumatic Encephalopathy.” PM & R?: The Journal of Injury, Function, and Rehabilitation 3 (10 Suppl 2) (October): S460–7.Tatum, William, Aatif Husain, Selim Benbadis, and Peter Kaplan. 2007. Handbook of EEG Interpretation. New York, NY: Demos Medical Publishing.Wang, Wei, Jennifer L Collinger, Alan D Degenhart, Elizabeth C Tyler-Kabara, Andrew B Schwartz, Daniel W Moran, Douglas J Weber, et al. 2013. “An Electrocorticographic Brain Interface in an Individual with Tetraplegia.” PloS One 8 (2) (January): e55344. doi:10.1371/journal.pone.0055344.Weiss, Paul S. 2013. “President Obama Announces the BRAIN Initiative.” ACS Nano 7 (4) (April 23): 2873–4. doi:10.1021/nn401796f.Yamada, T, and E Meng. 2009. Practical Guide for Clinical Neurophysiologic Testing: EEG. Philadelphia, PA: Lippincott Williams & Wilkins.Figure 1: Directory and file structure of the TUH-EEG database. Data is organized by patient (orange) and then by session (yellow). Each session contains one or more signal (edf) and physican report (txt) files. To accommodate filesystem management issues, patients are grouped into sets of about 100 (blue).Figure 1: Directory and file structure of the TUH-EEG database. Data is organized by patient (orange) and then by session (yellow). Each session contains one or more signal (edf) and physican report (txt) files. To accommodate filesystem management issues, patients are grouped into sets of about 100 (blue).Figure 2: Metrics describing the TUH-EEG corpus. [top left] histogram showing number of sessions per patient; [top right] histogram showing number of sessions recorded per calendar year; [bottom left] histogram of patient ages; [bottom right] histogram showing number of EEG-only channels (purple) and total channels (green).Figure 2: Metrics describing the TUH-EEG corpus. [top left] histogram showing number of sessions per patient; [top right] histogram showing number of sessions recorded per calendar year; [bottom left] histogram of patient ages; [bottom right] histogram showing number of EEG-only channels (purple) and total channels (green). ................
................

In order to avoid copyright disputes, this page is only a partial summary.

Google Online Preview   Download