Recurrent Neural Network-based Acute Concussion Classifier using Raw Resting State EEG Data

ABSTRACTConcussion is a global health concern. Despite its high prevalence, a sound understanding of the mechanisms underlying this type of diffuse brain injury remains elusive. It is, however, well established that concussions cause significant functional deficits; that children and youths are disproportionately affected and have longer recovery time than adults; and recovering individuals are more prone to suffer additional concussions, with each successive injury increasing the risk of long term neurological and mental health complications. Currently, concussion management faces two significant challenges: there are no objective, clinically accepted, brain-based approaches for determining (i) whether an athlete has suffered a concussion, and (ii) when the athlete has recovered. Diagnosis is based on clinical testing and self-reporting of symptoms and their severity. Self-reporting is highly subjective and symptoms only indirectly reflect the underlying brain injury. Here, we introduce a deep learning Long Short Term Memory (LSTM)-based recurrent neural network that is able to distinguish between healthy and acute post-concussed adolescent athletes using only a short (i.e. 90 seconds long) sample of resting state EEG data as input. The athletes were neither required to perform a specific task nor subjected to a stimulus during data collection, and the acquired EEG data was neither filtered, cleaned of artefacts, nor subjected to explicit feature extraction. The LSTM network was trained and tested on data from 27 male, adolescent athletes with sports related concussion, bench marked against 35 healthy, adolescent athletes. During rigorous testing, the classifier consistently identified concussions with an accuracy of >90% and its ensemble-median Area Under the Curve (AUC) corresponds to 0.971. This is the first instance of a high-performing classifier that relies only on easy-to-acquire resting state EEG data. It represents a key step towards the development of an easy-to-use, brain-based, automatic classification of concussion at an individual level.

Download Full-text

Recurrent neural network-based acute concussion classifier using raw resting state EEG data

Scientific Reports ◽

10.1038/s41598-021-91614-4 ◽

2021 ◽

Vol 11 (1) ◽

Author(s):

Karun Thanjavur ◽

Arif Babul ◽

Brandon Foran ◽

Maya Bielecki ◽

Adam Gilchrist ◽

...

Keyword(s):

Neural Network ◽

Recurrent Neural Network ◽

Resting State ◽

Short Term Memory ◽

Characteristic Curve ◽

Health Concern ◽

Adolescent Athletes ◽

Individual Level ◽

Diffuse Brain Injury ◽

Eeg Data

AbstractConcussion is a global health concern. Despite its high prevalence, a sound understanding of the mechanisms underlying this type of diffuse brain injury remains elusive. It is, however, well established that concussions cause significant functional deficits; that children and youths are disproportionately affected and have longer recovery time than adults; and that individuals suffering from a concussion are more prone to experience additional concussions, with each successive injury increasing the risk of long term neurological and mental health complications. Currently, the most significant challenge in concussion management is the lack of objective, clinically- accepted, brain-based approaches for determining whether an athlete has suffered a concussion. Here, we report on our efforts to address this challenge. Specifically, we introduce a deep learning long short-term memory (LSTM)-based recurrent neural network that is able to distinguish between non-concussed and acute post-concussed adolescent athletes using only short (i.e. 90 s long) samples of resting state EEG data as input. The athletes were neither required to perform a specific task nor expected to respond to a stimulus during data collection. The acquired EEG data were neither filtered, cleaned of artefacts, nor subjected to explicit feature extraction. The LSTM network was trained and validated using data from 27 male, adolescent athletes with sports related concussion, benchmarked against 35 non-concussed adolescent athletes. During rigorous testing, the classifier consistently identified concussions with an accuracy of > 90% and achieved an ensemble median Area Under the Receiver Operating Characteristic Curve (ROC/AUC) equal to 0.971. This is the first instance of a high-performing classifier that relies only on easy-to-acquire resting state, raw EEG data. Our concussion classifier represents a promising first step towards the development of an easy-to-use, objective, brain-based, automatic classification of concussion at an individual level.

Download Full-text

Deep Learning Recurrent Neural Network for Concussion Classification in Adolescents Using Raw Electroencephalography Signals: Toward a Minimal Number of Sensors

Frontiers in Human Neuroscience ◽

10.3389/fnhum.2021.734501 ◽

2021 ◽

Vol 15 ◽

Author(s):

Karun Thanjavur ◽

Dionissios T. Hristopulos ◽

Arif Babul ◽

Kwang Moo Yi ◽

Naznin Virji-Babul

Keyword(s):

Neural Network ◽

Neural Networks ◽

Deep Learning ◽

Recurrent Neural Network ◽

Resting State ◽

Short Term Memory ◽

State Data ◽

Eeg Data ◽

Clinical Environments ◽

Lstm Network

Artificial neural networks (ANNs) are showing increasing promise as decision support tools in medicine and particularly in neuroscience and neuroimaging. Recently, there has been increasing work on using neural networks to classify individuals with concussion using electroencephalography (EEG) data. However, to date the need for research grade equipment has limited the applications to clinical environments. We recently developed a deep learning long short-term memory (LSTM) based recurrent neural network to classify concussion using raw, resting state data using 64 EEG channels and achieved high accuracy in classifying concussion. Here, we report on our efforts to develop a clinically practical system using a minimal subset of EEG sensors. EEG data from 23 athletes who had suffered a sport-related concussion and 35 non-concussed, control athletes were used for this study. We tested and ranked each of the original 64 channels based on its contribution toward the concussion classification performed by the original LSTM network. The top scoring channels were used to train and test a network with the same architecture as the previously trained network. We found that with only six of the top scoring channels the classifier identified concussions with an accuracy of 94%. These results show that it is possible to classify concussion using raw, resting state data from a small number of EEG sensors, constituting a first step toward developing portable, easy to use EEG systems that can be used in a clinical setting.

Download Full-text

Prediction of IDH genotype in gliomas with dynamic susceptibility contrast perfusion MR imaging using an explainable recurrent neural network

Neuro-Oncology ◽

10.1093/neuonc/noz095 ◽

2019 ◽

Vol 21 (9) ◽

pp. 1197-1209 ◽

Cited By ~ 15

Author(s):

Kyu Sung Choi ◽

Seung Hong Choi ◽

Bumseok Jeong

Keyword(s):

Neural Network ◽

Recurrent Neural Network ◽

Signal Intensity ◽

Short Term Memory ◽

Area Under The Curve ◽

Perfusion Mri ◽

Dynamic Susceptibility ◽

Dynamic Susceptibility Contrast ◽

Operating Characteristics ◽

Susceptibility Contrast

Abstract Background The aim of this study was to predict isocitrate dehydrogenase (IDH) genotypes of gliomas using an interpretable deep learning application for dynamic susceptibility contrast (DSC) perfusion MRI. Methods Four hundred sixty-three patients with gliomas who underwent preoperative MRI were enrolled in the study. All the patients had immunohistopathologic diagnoses of either IDH-wildtype or IDH-mutant gliomas. Tumor subregions were segmented using a convolutional neural network followed by manual correction. DSC perfusion MRI was performed to obtain T2* susceptibility signal intensity-time curves from each subregion of the tumors: enhancing tumor, non-enhancing tumor, peritumoral edema, and whole tumor. These, with arterial input functions, were fed into a neural network as multidimensional inputs. A convolutional long short-term memory model with an attention mechanism was developed to predict IDH genotypes. Receiver operating characteristics analysis was performed to evaluate the model. Results The IDH genotype predictions had an accuracy, sensitivity, and specificity of 92.8%, 92.6%, and 93.1%, respectively, in the validation set (area under the curve [AUC], 0.98; 95% confidence interval [CI], 0.969–0.991) and 91.7%, 92.1%, and 91.5%, respectively, in the test set (AUC, 0.95; 95% CI, 0.898–0.982). In temporal feature analysis, T2* susceptibility signal intensity-time curves obtained from DSC perfusion MRI with attention weights demonstrated high attention on the combination of the end of the pre-contrast baseline, up/downslopes of signal drops, and/or post-bolus plateaus for the curves used to predict IDH genotype. Conclusions We developed an explainable recurrent neural network model based on DSC perfusion MRI to predict IDH genotypes in gliomas.

Download Full-text

Disturbance learning controller design for unmanned surface vehicle using LSTM technique of recurrent neural network

Journal of Intelligent & Fuzzy Systems ◽

10.3233/jifs-189622 ◽

2021 ◽

pp. 1-11

Author(s):

Sang-Ki Jeong ◽

Dea-Hyeong Ji ◽

Ji-Youn Oh ◽

Jung-Min Seo ◽

Hyeung-Sik Choi

Keyword(s):

Neural Network ◽

Control System ◽

Flow Velocity ◽

Recurrent Neural Network ◽

Pid Controller ◽

Short Term Memory ◽

Ocean Currents ◽

Ocean Current ◽

Movement Speed ◽

Marine Research

In this study, to effectively control small unmanned surface vehicles (USVs) for marine research, characteristics of ocean current were learned using the long short-term memory (LSTM) model algorithm of a recurrent neural network (RNN), and ocean currents were predicted. Using the results, a study on the control of USVs was conducted. A control system model of a small USV equipped with two rear thrusters and a front thruster arranged horizontally was designed. The system was also designed to determine the output of the controller by predicting the speed of the following currents and utilizing this data as a system disturbance by learning data from ocean currents using the LSTM algorithm of a RNN. To measure ocean currents on the sea when a small USV moves, the speed and direction of the ship’s movement were measured using speed, azimuth, and location (latitude and longitude) data from GPS. In addition, the movement speed of the fluid with flow velocity is measured using the installed flow velocity measurement sensor. Additionally, a control system was designed to control the movement of the USV using an artificial neural network-PID (ANN-PID) controller [12]. The ANN-PID controller can manage disturbances by adjusting the control gain. Based on these studies, the control results were analyzed, and the control algorithm was verified through a simulation of the applied control system [8, 9].

Download Full-text