?
Deep Learning for Non-Invasive Cortical Potential Imaging
Cold Spring Harbor Laboratory
,
2020.
Razorenova A., Yavich N., Malovichko M., Fedorov M., Fedorov M., Dylov D.
Electroencephalography (EEG) is a well-established non-invasive technique to measure the brain activity, albeit with a limited spatial resolution. Variations in electric conductivity between different tissues distort the electric fields generated by cortical sources, resulting in smeared potential measurements on the scalp. One needs to solve an ill-posed inverse problem to recover the original neural activity. In this article, we present a generic method of recovering the cortical potentials from the EEG measurement by introducing a new inverse-problem solver based on deep Convolutional Neural Networks (CNN) in paired (U-Net) and unpaired (DualGAN) configurations. The solvers were trained on synthetic EEG-ECoG pairs that were generated using a head conductivity model computed using the Finite Element Method (FEM). These solvers are the first of their kind, that provide robust translation of EEG data to the cortex surface using deep learning. Providing a fast and accurate interpretation of the tracked EEG signal, our approach promises a boost to the spatial resolution of the future EEG devices.
Priority areas:
IT and mathematics
Language:
English
Publication based on the results of:
Ossadtchi A., Altukhov D., Jerbi K., Neuroimage 2018 Vol. 183 P. 950-971
Increasing evidence suggests that neuronal communication is a defining property of functionally specialized brain networks and that it is implemented through synchronization between population activities of distinct brain areas. The detection of long-range coupling in electroencephalography (EEG) and magnetoencephalography (MEG) data using conventional metrics (such as coherence or phase-locking value) is by definition contaminated by ...
Added: November 30, 2018
Razorenova A., Yavich N., Malovichko M. et al., , in : Machine Learning in Clinical Neuroimaging and Radiogenomics in Neuro-oncology. Third International Workshop, MLCN 2020, and Second International Workshop, RNO-AI 2020. Lecture Notes in Computer Science. Vol. 12449: Machine Learning in Clinical Neuroimaging and Radiogenomics in Neuro-oncology.: Springer, 2020. Ch. 5. P. 45-55.
Electroencephalography (EEG) is a well-established non-invasive technique to measure the brain activity, albeit with a limited spatial resolution. Variations in electric conductivity between different tissues distort the electric fields generated by cortical sources, resulting in smeared potential measurements on the scalp. One needs to solve an ill-posed inverse problem to recover the original neural activity. In this article, ...
Added: December 10, 2020
Терновой С. К., Веселова Т. Н., Борисенко В. В. et al., Russian Electronic Journal of Radiology 2020 Т. 10 № 2 С. 71-77
Гидродинамический расчет кровотока в коронарной артерии поз-волил получить оценку ФРК с отклонением от инвазивно измеренных значений ФРК равным или меньшим 7%.
Продемонстрирован научный и клинический потенциал предложенной ранее методологии неинвазивного определения ФРК по результатам КТА для оценки функциональной значимости пограничных стенозов в коронарных артериях. ...
Added: December 4, 2020
Fedorov A., Nikolskaia K., Ivanov S. et al., Journal of Big Data 2019 Vol. 6 Article 73
This study addresses the problem of traffic flow estimation based on the data from a video surveillance camera. Target problem here is formulated as counting and classifying vehicles by their driving direction. This subject area is in early development, and the focus of this work is only one of the busiest crossroads in city Chelyabinsk, ...
Added: December 5, 2020
Savchenko A., Belova N. S., Expert Systems with Applications 2018 Vol. 108 P. 170-182
The paper deals with unconstrained face recognition task for the small sample size problem based on computation of distances between high-dimensional off-the-shelf features extracted by deep convolution neural network. We present the novel statistical recognition method, which maximizes the likelihood (joint probabilistic density) of the distances to all reference images from the gallery set. This ...
Added: May 17, 2018
Switzerland : Springer, 2019
The series “Advances in Intelligent Systems and Computing” contains publications on theory, applications, and design methods of Intelligent Systems and Intelligent Computing. Virtually all disciplines such as engineering, natural sciences, computer and information science, ICT, economics, business, e-commerce, environment, healthcare, life science are covered. The list of topics spans all the areas of modern intelligent ...
Added: January 9, 2019
Генов П. Г., Тимербаев В. Х., Гринь А. А. et al., Нейрохирургия 2017 № 1 С. 45-53
Objective: to determine the influence of perioperative analgesia methods on the incidence of « failed back surgery syndrome» after intervertebral discal hernia removal. Material and methods: This prospective study was conducted from 2010 till 2013 and included 129 patients who underwent lumbar discectomy regarding intervertebral discal hernia. Patients of group GA+R (n=20) were operated on ...
Added: October 2, 2018
NY : IEEE, 2016
This paper aims to tackle the problem of brain network classification with machine learning algorithms using spectra of networks’ matrices. Two approaches are discussed: first, linear and tree-based models are trained on the vectors of sorted eigenvalues of the adjacency matrix, the Laplacian matrix and the normalized Laplacian; next, SVM classifier is trained with kernels ...
Added: December 9, 2016
Chepovskiy A., Терновой С. К., Веселова Т. Н. et al., Russian Electronic Journal of Radiology 2019 Т. 9 № 3 С. 58-64
Purpose: Determination of transluminal attenuation gradient (TAG) in intact cor onary arteries ...
Added: October 7, 2019
Savchenko A., Information Sciences 2021 Vol. 560 P. 370-385
A novel image recognition algorithm based on sequential three-way decisions is introduced to speed up the inference in a convolutional neural network. In contrast to the majority of existing studies, our approach does not require a special procedure to train a neural network, and thus it can be used with arbitrary architectures including pre-trained convolutional ...
Added: February 25, 2021
Веселова Т. Н., Омаров Ю. А., Шахнович Р. М. et al., Russian Electronic Journal of Radiology 2020 Т. 10 № 3 С. 150-155
В сообщении представлены клинические случаи использования
стресс-ПКТ миокарда и ФРККТА в диагностике ишемической болезни сердца. Приведенные клинические примеры продемонстрировали эффек-тивное использование ПКТ миокарда и ФРККТА в оценке гемодинамической значимо-сти стенозов в коронарных артериях. ...
Added: December 4, 2020
Гаврилова А. Е., Нагаева Е. В., Rebrova O. et al., Проблемы эндокринологии 2017 Т. 63 № 5 С. 282-290
Background. Predicting the efficacy of rGH therapy in patients with GH deficiency, based on the final achieved height (FAH) criterion, is an important tool for the clinician. It enables a personalized approach to the treatment of patients with GH deficiency: to recommend careful adherence to the regimen and dosage of the drug, evaluate the efficacy ...
Added: October 2, 2018
Switzerland : Springer, 2020
This book comprises high-quality, refereed research papers presented at the 2019 International Symposium on Computer Science, Digital Economy and Intelligent Systems (CSDEIS2019): The symposium, held in Moscow, Russia, on 4–6 October 2019, was organized jointly by Moscow State Technical University and the International Research Association of Modern Education and Computer Science. The book discusses the ...
Added: March 15, 2020
Yasnitsky L., Мартынов А. И., Терапия 2020 Т. 6 № 3(37) С. 149-154
Despite the success of modern medicine, the important ethical problem of communication between doctor and patient still remains open. The matter of it is the fact that doctors often prescribe treatment courses for patients and observe: «will it help» or «will not help». If «does not help», they prescribe other drugs, etc. Physicists and engineers ...
Added: November 28, 2020
Стукалова О. В., Серова Н. С., Chepovskiy A. et al., Russian Electronic Journal of Radiology 2021 Т. 11 № 2 С. 32-45
В статье представлен обзор современной отечественной и зарубежной литературы, по-священной различным подходам к созданию моделей сердца, от первых очень простых компьютерных симуляций электрофизиологии до современных, основанных на магнитно-резонансной
томографии с контрастированием, с отражением не только анатомии, но и структуры миокар-да. Также в данном обзоре обсуждается вопрос практического применения данных технологий
для повышения эффективности сердечной ресинхронизирующей терапии, аблации ...
Added: August 8, 2021
Зимина Е. Ю., Статистика и Экономика 2018 Т. 15 № 2 С. 30-37
The article includes the observation of the cluster analysis of medical
data on the example of the cardiac data. One of the main effective
and commonly used Data Mining methods that applied to the large
amounts of information (for example, mathematical economics) are
clustering methods: the search for signs of similarity between objects
in the study of the subject area ...
Added: May 29, 2018
Tyuryumina E., Neznanov A., The Breast 2019 Vol. 44 P. 88-89
Previously, the mathematical models (CoMPaS and CoM-III) of primary tumor (PT) growth and secondary distant metastases (sdMTS) growth of breast cancer (BC) considering TNM classification have been presented (Tyuryumina E., Neznanov A.; 2017, 2018). Goal: To detect the earliest diagnostics period of visible sdMTS via CoMPaS and CoM-III. ...
Added: March 30, 2019
Rebrova O., Российская ринология 2018 Т. 26 № 1 С. 65-68
Description of the statistical analysis of the data contained in original articles. Typical mistakes ...
Added: October 2, 2018
Sokolova A., Savchenko A., Optical Memory and Neural Networks (Information Optics) 2020 Vol. 29 No. 1 P. 19-29
The goal of the study is to increase the computation efficiency of the face recognition that uses feature vectors to describe facial images on photos and videos. These high-dimensional feature vectors are nowadays produced by convolutional neural networks. The methods to aggregate the features generated for each video frame are used to process the video ...
Added: October 25, 2019
Savchenko A., Information Sciences 2019 Vol. 489 P. 18-36
The paper addresses the issue of insufficient speed of image recognition methods if the number of classes is rather large. We propose the novel algorithm based on sequential three-way decisions and a formal description of granular computing. Each image is associated with principal component scores of the high-dimensional features extracted by deep convolution neural network. ...
Added: March 20, 2019
Vorontsova D. V., Zubov A. I., Isaeva M. V. et al., Computer Research and Modeling 2023
Using data analysis and indirect application of neural networks in our work, we identified patterns of brain electrical activity that characterize COVID−19. We were interested in frequency, temporal, and spatial domain patterns of electrical activity in people who have undergone COVID−19.
We found a predominance of α−rhythm patterns in the left hemisphere in healthy people compared ...
Added: April 26, 2023
Isaev E., Pervukhin D., Tarasov P. et al., Математическая биология и биоинформатика 2019 Т. 14 № 2 С. 420-429
It is necessary not only to develop information and communication infrastructures and algorithms for distributed and cloud processing of data coming from all kinds of sensors and sensors, but also to design new materials that enable the production of safe, effective and accessible to the general public test systems when creating digital health saving systems ...
Added: August 6, 2019
Savchenko A., Дёмочкин К. В., Savchenko L., Optical Memory and Neural Networks (Information Optics) 2020 Vol. 29 No. 4 P. 297-304
In this paper, we analyze effective methods of multi-label classification of image sets in development of visual recommender systems. We propose a two-step algorithm, which at the first step performs fine-tuning of a convolutional neural network for extraction of visual features. At the second stage, the algorithm concatenates the obtained feature vectors of each image ...
Added: October 25, 2019
Ossadtchi A., Okorokova L., Татьяна Ш. et al., Scientific Reports 2017
Although the first experiments on alpha-neurofeedback date back nearly six decades ago, when Joseph Kamiya reported successful operant conditioning of alpha-rhythm in humans, the effectiveness of this paradigm in various experimental and clinical settings is still a matter of debate. Here, we investigated the changes in EEG patterns during a continuously administered neurofeedback of P4 ...
Added: June 8, 2017