Artificial Intelligence (AI) in Neuroscience

A special issue of Applied Sciences (ISSN 2076-3417). This special issue belongs to the section "Applied Biosciences and Bioengineering".

Deadline for manuscript submissions: closed (30 September 2023) | Viewed by 21354

Special Issue Editors

1. Baltic Center for Artificial Intelligence and Neurotechnology, Immanuel Kant Baltic Federal University, Kaliningrad 236041, Russia
2. Neurosciences Research Institute of Samara State Medical University, Samara 443079, Russia
3. Neuroscience and Cognitive Technology Laboratory, Innopolis University, Kazan 420500, Russia
Interests: neuroscience; nonlinear dynamics; wavelets; intelligent systems; synchronization; biomedical signal processing; neuronal networks
Special Issues, Collections and Topics in MDPI journals
Center for Biomedical Technology, Technical University of Madrid, Campus Montegancedo, Pozuelo de Alarcón, 28223 Madrid, Spain
Interests: complex systems; bioinformatics; mathematical and computational biology; optics and photonics; biological physics; cognitive neuroscience
Special Issues, Collections and Topics in MDPI journals
1. Neuroscience and Cognitive Technology Laboratory, Innopolis University, 420500 Innopolis, Russia
2. Institute of Biology and Biomedicine, Lobachevsky State University of Nizhny Novgorod, 603950 Nizhny Novgorod, Russia
Interests: computational neuroscience; spiking neuron networks; neurointerfaces; neurocontrol; biomorphic robotics; nonlinear dynamics
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

Artificial intelligence (AI) is a state-of-the-art computational tool employed to analyze big data in fundamental and applied science. Recently, it has gained popularity in neuroscience due to its ability to recognize hidden patterns and nonlinear relations in large amounts of nonstationary and ambiguous neuroimaging data. Researchers and engineers are increasingly using machine learning approaches to gain new insights into brain behavior and for neurotechnology applications, including neural interfaces and memristive systems. AI-based methods are of particular importance in the medical diagnosis of neurological diseases, where machine learning is a powerful tool for the early detection of biomarkers of various neurological disorders. In the latter case, the methods and approaches of explainable artificial intelligence (XAI), which is extremely important for modern digital medicine, are beginning to play a significant role. The rapid development of AI technologies suggests that the ambitious goal formulated can be achieved by applying AI concepts.

This Special Issue aims to attract high-quality research studies and reviews from scholars, professors, researchers and engineers that advance the application of state-of-the-art artificial intelligence concepts in neuroscience and neurological disease diagnostic systems. Potential topics will include, but are not limited to:

  • Explainable AI (XAI) and deep learning in neuroscience;
  • Neuroimaging data processing;
  • In vitro diagnostics with AI application;
  • Brain images analysis and diagnostics;
  • Neurological signals processing;
  • Reservoir computing;
  • AI-based methods for the diagnostics and analysis of brain functional networks;
  • Applications of memristive devices and systems;
  • Dynamics of spiking neuronal networks;
  • AI-based intelligence systems for brain–computer interfaces;
  • Data analytics and mining for neurological disease diagnostics.

Prof. Dr. Alexander E. Hramov
Prof. Dr. Alexander N. Pisarchik
Prof. Dr. Victor B. Kazantsev
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Applied Sciences is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • machine learning
  • explainable artificial intelligence (XAI)
  • data analytics and mining in neuroscience
  • EEG/MEG/fMRI/MRI/fNIRS data processing
  • AI for brain–computer interfaces
  • AI applications in neurological disease diagnostics
  • memristive intelligence systems
  • dynamics of spiking neuronal networks

Published Papers (15 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Research

Jump to: Review

20 pages, 6294 KiB  
Article
Neuromorphic Analog Machine Vision Enabled by Nanoelectronic Memristive Devices
by Sergey Shchanikov, Ilya Bordanov, Alexey Kucherik, Evgeny Gryaznov and Alexey Mikhaylov
Appl. Sci. 2023, 13(24), 13309; https://doi.org/10.3390/app132413309 - 16 Dec 2023
Viewed by 928
Abstract
Arrays of memristive devices coupled with photosensors can be used for capturing and processing visual information, thereby realizing the concept of “in-sensor computing”. This is a promising concept associated with the development of compact and low-power machine vision devices, which is crucial important [...] Read more.
Arrays of memristive devices coupled with photosensors can be used for capturing and processing visual information, thereby realizing the concept of “in-sensor computing”. This is a promising concept associated with the development of compact and low-power machine vision devices, which is crucial important for bionic prostheses of eyes, on-board image recognition systems for unmanned vehicles, computer vision in robotics, etc. This concept can be applied for the creation of a memristor based neuromorphic analog machine vision systems, and here, we propose a new architecture for these systems in which captured visual data are fed to a spiking artificial neural network (SNN) based on memristive devices without analog-to-digital and digital-to-analog conversions. Such an approach opens up the opportunities of creating more compact, energy-efficient visual processing units for wearable, on-board, and embedded electronics for such areas as robotics, the Internet of Things, and neuroprosthetics, as well as other practical applications in the field of artificial intelligence. Full article
(This article belongs to the Special Issue Artificial Intelligence (AI) in Neuroscience)
Show Figures

Figure 1

9 pages, 885 KiB  
Article
Artificial Neural Networks for a Semantic Map of Variables in a Music Listening-Based Study
by Alfredo Raglio, Enzo Grossi and Luca Manzoni
Appl. Sci. 2023, 13(21), 11811; https://doi.org/10.3390/app132111811 - 29 Oct 2023
Viewed by 568
Abstract
Music listening is widely used in therapeutic music-based interventions across various clinical contexts. However, relating the diverse and overlapping musical elements to their potential effects is a complex task. Furthermore, the considerable subjectivity of musical preferences and perceptual components of music, influenced by [...] Read more.
Music listening is widely used in therapeutic music-based interventions across various clinical contexts. However, relating the diverse and overlapping musical elements to their potential effects is a complex task. Furthermore, the considerable subjectivity of musical preferences and perceptual components of music, influenced by factors like cultural and musical background, personality structure of the user, and clinical aspects (in the case of diseases), adds to the difficulty. This paper analyzes data derived from a previous randomized controlled study involving a healthy population (n = 320). The study aimed to induce relaxation through music listening experiences using both conventional and algorithmic approaches. The main goal of the current research is to identify potential relationships among the variables investigated during the experiment. To achieve this, we employed the Auto Contractive Map (Auto-CM), a fourth-generation artificial neural network (ANN). This approach allows us to quantify the strength of association between each of the variables with respect to all others in the dataset. The main results highlighted that individuals who achieved a state of relaxation by listening to music composed by Melomics-Health were predominantly over 49 years old, female, and had a high level of education and musical training. Conversely, for conventional (self-selected) music, the relaxing effect was correlated with the male population, aged less than 50 years, with a high level of education and musical training. Future studies conducted in clinical settings could help identify “responder” populations based on different types of music listening approaches. Full article
(This article belongs to the Special Issue Artificial Intelligence (AI) in Neuroscience)
Show Figures

Figure 1

17 pages, 12220 KiB  
Article
Neural Encoding of Pavement Textures during Exoskeleton Control: A Pilot Study
by Júlia Ramos, Mafalda Aguiar and Miguel Pais-Vieira
Appl. Sci. 2023, 13(16), 9356; https://doi.org/10.3390/app13169356 - 17 Aug 2023
Viewed by 656
Abstract
This paper investigates the changes in sensory neural activity during exoskeleton control. Exoskeletons are becoming reliable tools for neurorehabilitation, as recent studies have shown that their use enhances neural plasticity. However, the specific neural correlates associated with exoskeleton control have not yet been [...] Read more.
This paper investigates the changes in sensory neural activity during exoskeleton control. Exoskeletons are becoming reliable tools for neurorehabilitation, as recent studies have shown that their use enhances neural plasticity. However, the specific neural correlates associated with exoskeleton control have not yet been described in detail. Therefore, in this pilot study, our aim was to investigate the effects of different pavement textures on the neural signals of participants (n = 5) while controlling a lower limb ExoAtlet®-powered exoskeleton. Subjects were instructed to walk on various types of pavements, including a flat surface, carpet, foam, and rubber circles, both with and without the exoskeleton. This setup resulted in eight different experimental conditions for classification (i.e., Exoskeleton/No Exoskeleton in one of four different pavements). Four-minute Electroencephalography (EEG) signals were recorded in each condition: (i) the power of the signals was compared for electrodes C3 and C4 across different conditions (Exoskeleton/No Exoskeleton on different pavements), and (ii) the signals were classified using four models: the linear support vector machine (L-SVM), the K-nearest neighbor algorithm (KNN), linear discriminant analysis (LDA), and the artificial neural network (ANN). the results of power analysis showed increases and decreases in power within the delta frequency bands in electrodes C3 and C4 across the various conditions. The results of comparison between classifiers revealed that LDA exhibited the highest performance with an accuracy of 85.71%. These findings support the notion that the sensory processing of pavement textures during exoskeleton control is associated with changes in the delta band of the C3 and C4 electrodes. From the results, it is concluded that the use of classifiers, such as LDA, allow for a better offline classification of different textures in EEG signals, with and without exoskeleton control, than the analysis of power in different frequency bands. Full article
(This article belongs to the Special Issue Artificial Intelligence (AI) in Neuroscience)
Show Figures

Figure 1

16 pages, 2642 KiB  
Article
Analysis of Mobile Device Dual Tasking on the Move: Normal Cognitive Decline of Aging as Ground Truth for Mild Cognitive Impairment
by Ramón Hervás, Alfonso Barragán, Luis Cabañero, Laura Villa and Tania Mondéjar
Appl. Sci. 2023, 13(16), 9204; https://doi.org/10.3390/app13169204 - 13 Aug 2023
Viewed by 662
Abstract
The widespread use of mobile phones in daily life makes them a fundamental tool for the study of human behavior. In particular, they can be used as a source of additional information to help to diagnose diseases. This work is based on contrasted [...] Read more.
The widespread use of mobile phones in daily life makes them a fundamental tool for the study of human behavior. In particular, they can be used as a source of additional information to help to diagnose diseases. This work is based on contrasted dual-tasking tests where cognitive performance is studied by performing tasks of high cognitive load while walking. In this case, we study significant differences in mobile device use among groups of people of different ages and examine whether they are more characteristic when the interaction takes place on the move. A study is conducted by monitoring the interaction with the mobile device for one consecutive week and analyzing the correlations between these interactions and the participants’ ages. Additionally, a user profiling model is designed to help to use this ground truth in future works focused on the early diagnosis of cognitive deficits. The results obtained contribute to preliminarily characterizing how age-related normotypical cognitive decline affects interactions with mobile devices. In addition, the pilot study generates a dataset with monitored events and interactions of 45 users that includes more than 4.5 million records. Full article
(This article belongs to the Special Issue Artificial Intelligence (AI) in Neuroscience)
Show Figures

Figure 1

30 pages, 3643 KiB  
Article
Implementation of Machine Learning and Deep Learning Techniques for the Detection of Epileptic Seizures Using Intracranial Electroencephalography
by Marcin Kołodziej, Andrzej Majkowski and Andrzej Rysz
Appl. Sci. 2023, 13(15), 8747; https://doi.org/10.3390/app13158747 - 28 Jul 2023
Cited by 3 | Viewed by 1218
Abstract
The diagnosis of epilepsy primarily relies on the visual and subjective assessment of the patient’s electroencephalographic (EEG) or intracranial electroencephalographic (iEEG) signals. Neurophysiologists, based on their experience, look for characteristic discharges such as spikes and multi-spikes. One of the main challenges in epilepsy [...] Read more.
The diagnosis of epilepsy primarily relies on the visual and subjective assessment of the patient’s electroencephalographic (EEG) or intracranial electroencephalographic (iEEG) signals. Neurophysiologists, based on their experience, look for characteristic discharges such as spikes and multi-spikes. One of the main challenges in epilepsy research is developing an automated system capable of detecting epileptic seizures with high sensitivity and precision. Moreover, there is an ongoing search for universal features in iEEG signals that can be easily interpreted by neurophysiologists. This article explores the possibilities, issues, and challenges associated with utilizing artificial intelligence for seizure detection using the publicly available iEEG database. The study presents standard approaches for analyzing iEEG signals, including chaos theory, energy in different frequency bands (alpha, beta, gamma, theta, and delta), wavelet transform, empirical mode decomposition, and machine learning techniques such as support vector machines. It also discusses modern deep learning algorithms such as convolutional neural networks (CNN) and long short-term memory (LSTM) networks. Our goal was to gather and comprehensively compare various artificial intelligence techniques, including both traditional machine learning methods and deep learning techniques, which are most commonly used in the field of seizure detection. Detection results were tested on a separate dataset, demonstrating classification accuracy, sensitivity, precision, and specificity of seizure detection. The best results for seizure detection were obtained with features related to iEEG signal energy (accuracy of 0.97, precision of 0.96, sensitivity of 0.99, and specificity of 0.96), as well as features related to chaos, Lyapunov exponents, and fractal dimension (accuracy, precision, sensitivity, and specificity all equal to 0.95). The application of CNN and LSTM networks yielded significantly better results (CNN: Accuracy of 0.99, precision of 0.98, sensitivity of 1, and specificity of 0.99; LSTM: Accuracy of 0.98, precision of 0.96, sensitivity of 1, and specificity of 0.99). Additionally, the use of the gradient-weighted class activation mapping algorithm identified iEEG signal fragments that played a significant role in seizure detection. Full article
(This article belongs to the Special Issue Artificial Intelligence (AI) in Neuroscience)
Show Figures

Figure 1

14 pages, 2710 KiB  
Article
Changes in the Power and Coupling of Infra-Slow Oscillations in the Signals of EEG Leads during Stress-Inducing Cognitive Tasks
by Mikhail D. Prokhorov, Ekaterina I. Borovkova, Aleksey N. Hramkov, Elizaveta S. Dubinkina, Vladimir I. Ponomarenko, Yurii M. Ishbulatov, Alexander V. Kurbako and Anatoly S. Karavaev
Appl. Sci. 2023, 13(14), 8390; https://doi.org/10.3390/app13148390 - 20 Jul 2023
Cited by 1 | Viewed by 755
Abstract
A change in the human psychophysiological state, caused by stress in particular, affects the processes of autonomic control, the activity of which is reflected in infra-slow oscillations of brain potentials with a frequency of less than 0.5 Hz. We studied the infra-slow oscillations [...] Read more.
A change in the human psychophysiological state, caused by stress in particular, affects the processes of autonomic control, the activity of which is reflected in infra-slow oscillations of brain potentials with a frequency of less than 0.5 Hz. We studied the infra-slow oscillations in scalp electroencephalogram (EEG) signals in the frequency ranges of 0.05–0.15 Hz and 0.15–0.50 Hz that are associated with the processes of sympathetic and parasympathetic control, respectively, in healthy subjects at rest and during stress-inducing cognitive tasks. The power spectra of EEG signals, the phase coherence coefficients, and indices of directional coupling between the infra-slow oscillations in the signals of different EEG leads were analyzed. We revealed that, compared with the state of rest, the stress state is characterized by a significant decrease in the power of infra-slow oscillations and changes in the structure of couplings between infra-slow oscillations in EEG leads. In particular, under stressful conditions, a decrease in both intrahemispheric and interhemispheric coupling between EEG leads occurred in the range of 0.05–0.15 Hz, while a decrease in intrahemispheric and an increase in interhemispheric couplings was observed in the range of 0.15–0.50 Hz. Full article
(This article belongs to the Special Issue Artificial Intelligence (AI) in Neuroscience)
Show Figures

Figure 1

16 pages, 856 KiB  
Article
Development and Validation of Machine-Learning Models to Support Clinical Diagnosis for Non-Epileptic Psychogenic Seizures
by Chiara Zucco, Barbara Calabrese, Rossana Mancuso, Miriam Sturniolo, Franco Pucci, Antonio Gambardella and Mario Cannataro
Appl. Sci. 2023, 13(12), 6924; https://doi.org/10.3390/app13126924 - 08 Jun 2023
Viewed by 872
Abstract
Electroencephalographic (EEG) signal processing and machine learning can support neurologists’ work in discriminating Psychogenic Non-Epileptic Seizure (PNES) from epilepsy. PNES represents a neurological disease often misdiagnosed. Although the symptoms of PNES patients can be similar to those exhibited by epileptic patients, EEG signals [...] Read more.
Electroencephalographic (EEG) signal processing and machine learning can support neurologists’ work in discriminating Psychogenic Non-Epileptic Seizure (PNES) from epilepsy. PNES represents a neurological disease often misdiagnosed. Although the symptoms of PNES patients can be similar to those exhibited by epileptic patients, EEG signals during a psychogenic seizure do not show ictal patterns such as in epilepsy. Therefore, PNES diagnosis requires long-term EEG video. Applying signal processing and machine-learning methodologies could help clinicians find helpful information in the clinical diagnosis of PNES by analyzing EEG signals registered in resting conditions and in a short time. These methodologies should prevent long EEG recording sessions and avoid inducing seizures in the subjects. The aim of our study is to develop and validate several machine-learning models on a larger dataset, consisting of 225 EEGs (75 healthy, 75 PNES, and 75 subjects with epilepsy). A deep analysis of our results shows that changes in the evaluation strategy led to changes in accuracy from 45% to 83.98% for a standard Light Gradient Boosting Machine (LGBM) classifier. Our findings suggest that it is necessary to operate a very rigorous control in terms of experimental data collection (patient selection, signal acquisition) and terms of validation strategies to obtain and reproducible results. Full article
(This article belongs to the Special Issue Artificial Intelligence (AI) in Neuroscience)
Show Figures

Figure 1

12 pages, 1671 KiB  
Article
Cross-Subject Classification of Effectiveness in Performing Cognitive Tasks Using Resting-State EEG
by Helen Steiner, Ilya Mikheev and Olga Martynova
Appl. Sci. 2023, 13(11), 6606; https://doi.org/10.3390/app13116606 - 29 May 2023
Cited by 1 | Viewed by 849
Abstract
A high level of mathematical education is often associated with high effectiveness in solving cognitive problems and professional success. It is known that cognitive processes are accompanied by specific bioelectric activity in the brain and success in mathematical education as a behavioral phenotype [...] Read more.
A high level of mathematical education is often associated with high effectiveness in solving cognitive problems and professional success. It is known that cognitive processes are accompanied by specific bioelectric activity in the brain and success in mathematical education as a behavioral phenotype is also reflected in EEG both during mental activity and at rest. This study tested the potential to distinguish volunteers with an advanced level of education in mathematics (AM) from individuals with a basic level of education in mathematics (BM) based on the frequency parameters of the resting-state electroencephalogram (EEG) recorded before the start of cognitive tasks. Further, the volunteers were divided into two groups, highly successful and moderately successful, according to their task-solving performance. The Light Gradient Boosting Machine learning algorithm was used for cross-subject classification based on the power spectral density of seven EEG frequency bands. It most accurately recognized and differentiated EEG of highly successful from highly successful BM subjects. The results indicate that success in solving tasks in combination with a high level of education in mathematics can be reflected in or predicted by the specific rhythmic activity of the brain at rest. Full article
(This article belongs to the Special Issue Artificial Intelligence (AI) in Neuroscience)
Show Figures

Figure 1

21 pages, 5317 KiB  
Article
Rediscovering Automatic Detection of Stuttering and Its Subclasses through Machine Learning—The Impact of Changing Deep Model Architecture and Amount of Data in the Training Set
by Piotr Filipowicz and Bozena Kostek
Appl. Sci. 2023, 13(10), 6192; https://doi.org/10.3390/app13106192 - 18 May 2023
Cited by 2 | Viewed by 1930
Abstract
This work deals with automatically detecting stuttering and its subclasses. An effective classification of stuttering along with its subclasses could find wide application in determining the severity of stuttering by speech therapists, preliminary patient diagnosis, and enabling communication with the previously mentioned voice [...] Read more.
This work deals with automatically detecting stuttering and its subclasses. An effective classification of stuttering along with its subclasses could find wide application in determining the severity of stuttering by speech therapists, preliminary patient diagnosis, and enabling communication with the previously mentioned voice assistants. The first part of this work provides an overview of examples of classical and deep learning methods used in automated stuttering classifications as well as databases and features used. Then, two classical algorithms (k-NN (k-nearest neighbor) and SVM (support vector machine) and several deep models (ConvLSTM; ResNetBiLstm; ResNet18; Wav2Vec2) are examined on the available stuttering dataset. The experiments investigate the influence of individual signal features such as Mel-Frequency Cepstral Coefficients (MFCCs), pitch-determining features in the signal, and various 2D speech representations on the classification results. The most successful algorithm, i.e., ResNet18, can classify speech disorders at the F1 measure of 0.93 for the general class. Additionally, deep learning shows superiority over a classical approach to stuttering disorder detection. However, due to insufficient data and the quality of the annotations, the results differ between stuttering subcategories. Observation of the impact of the number of dense layers, the amount of data in the training set, and the amount of data divided into the training and test sets on the effectiveness of stuttering event detection is provided for further use of this methodology. Full article
(This article belongs to the Special Issue Artificial Intelligence (AI) in Neuroscience)
Show Figures

Figure 1

15 pages, 418 KiB  
Article
Evaluation of Unsupervised Anomaly Detection Techniques in Labelling Epileptic Seizures on Human EEG
by Oleg E. Karpov, Matvey S. Khoymov, Vladimir A. Maksimenko, Vadim V. Grubov, Nikita Utyashev, Denis A. Andrikov, Semen A. Kurkin and Alexander E. Hramov
Appl. Sci. 2023, 13(9), 5655; https://doi.org/10.3390/app13095655 - 04 May 2023
Cited by 7 | Viewed by 1979
Abstract
Automated labelling of epileptic seizures on electroencephalograms is an essential interdisciplinary task of diagnostics. Traditional machine learning approaches operate in a supervised fashion requiring complex pre-processing procedures that are usually labour intensive and time-consuming. The biggest issue with the analysis of electroencephalograms is [...] Read more.
Automated labelling of epileptic seizures on electroencephalograms is an essential interdisciplinary task of diagnostics. Traditional machine learning approaches operate in a supervised fashion requiring complex pre-processing procedures that are usually labour intensive and time-consuming. The biggest issue with the analysis of electroencephalograms is the artefacts caused by head movements, eye blinks, and other non-physiological reasons. Similarly to epileptic seizures, artefacts produce rare high-amplitude spikes on electroencephalograms, complicating their separability. We suggest that artefacts and seizures are rare events; therefore, separating them from the rest data seriously reduces information for further processing. Based on the occasional nature of these events and their distinctive pattern, we propose using anomaly detection algorithms for their detection. These algorithms are unsupervised and require minimal pre-processing. In this work, we test the possibility of an anomaly (or outlier) detection algorithm to detect seizures. We compared the state-of-the-art outlier detection algorithms and showed how their performance varied depending on input data. Our results evidence that outlier detection methods can detect all seizures reaching 100% recall, while their precision barely exceeds 30%. However, the small number of seizures means that the algorithm outputs a set of few events that could be quickly classified by an expert. Thus, we believe that outlier detection algorithms could be used for the rapid analysis of electroencephalograms to save the time and effort of experts. Full article
(This article belongs to the Special Issue Artificial Intelligence (AI) in Neuroscience)
Show Figures

Figure 1

15 pages, 1939 KiB  
Article
MCI Conversion Prediction Using 3D Zernike Moments and the Improved Dynamic Particle Swarm Optimization Algorithm
by Pouya Bolourchi, Mohammadreza Gholami, Masoud Moradi, Iman Beheshti and Hasan Demirel
Appl. Sci. 2023, 13(7), 4489; https://doi.org/10.3390/app13074489 - 01 Apr 2023
Cited by 2 | Viewed by 1209
Abstract
Mild cognitive impairment (MCI) conversion prediction is a vital challenge in the area of Alzheimer’s disease (AD) as it could determine possible treatment pathways for AD patients. In this work, we presented a robust MCI conversion prediction framework based on the 3D-Zernike Moment [...] Read more.
Mild cognitive impairment (MCI) conversion prediction is a vital challenge in the area of Alzheimer’s disease (AD) as it could determine possible treatment pathways for AD patients. In this work, we presented a robust MCI conversion prediction framework based on the 3D-Zernike Moment (3D-ZM) method that generates statistical features (e.g., shape, texture, and symmetry information) from 3D-MRI scans and improved dynamic particle swarm optimization (IDPSO) that finds an informative sub-set of Zernike features for MCI conversion prediction. We quantified the efficiency of the proposed prediction framework on a large sample of MCI patients including 105 progressive-MCI (pMCI) and 121 stable-MCI (sMCI) at the baseline from the ADNI dataset. Using the proposed MCI conversion prediction framework, pMCI patients were distinguished from sMCI patients with an accuracy exceeding 75% (sensitivity, 83%, and specificity, 68%), which is well comparable with the state-of-the-art MCI conversion prediction approaches. Experimental results indicate that the 3D-ZM method can represent informative statistical patterns from 3D-MRI scans and IDPSO has a great capability to find meaningful statistical features for identifying MCI patients who are at risk of conversion to the AD stage. Full article
(This article belongs to the Special Issue Artificial Intelligence (AI) in Neuroscience)
Show Figures

Figure 1

15 pages, 660 KiB  
Article
Optimal Sensor Set for Decoding Motor Imagery from EEG
by Arnau Dillen, Fakhreddine Ghaffari, Olivier Romain, Bram Vanderborght, Uros Marusic, Sidney Grosprêtre, Ann Nowé, Romain Meeusen and Kevin De Pauw
Appl. Sci. 2023, 13(7), 4438; https://doi.org/10.3390/app13074438 - 31 Mar 2023
Viewed by 1943
Abstract
Brain–computer interfaces (BCIs) have the potential to enable individuals to interact with devices by detecting their intention from brain activity. A common approach to BCI is to decode movement intention from motor imagery (MI), the mental representation of an overt action. However, research-grade [...] Read more.
Brain–computer interfaces (BCIs) have the potential to enable individuals to interact with devices by detecting their intention from brain activity. A common approach to BCI is to decode movement intention from motor imagery (MI), the mental representation of an overt action. However, research-grade electroencephalogram (EEG) acquisition devices with a high number of sensors are typically necessary to achieve the spatial resolution required for reliable analysis. This entails high monetary and computational costs that make these approaches impractical for everyday use. This study investigates the trade-off between accuracy and complexity when decoding MI from fewer EEG sensors. Data were acquired from 15 healthy participants performing MI with a 64-channel research-grade EEG device. After performing a quality assessment by identifying visually evoked potentials, several decoding pipelines were trained on these data using different subsets of electrode locations. No significant differences (p = [0.18–0.91]) in the average decoding accuracy were found when using a reduced number of sensors. Therefore, decoding MI from a limited number of sensors is feasible. Hence, using commercial sensor devices for this purpose should be attainable, reducing both monetary and computational costs for BCI control. Full article
(This article belongs to the Special Issue Artificial Intelligence (AI) in Neuroscience)
Show Figures

Figure 1

10 pages, 891 KiB  
Article
Deep Learning-Based Radiomics for Prognostic Stratification of Low-Grade Gliomas Using a Multiple-Gene Signature
by Mert Karabacak, Burak B. Ozkara, Kaan Senparlak and Sotirios Bisdas
Appl. Sci. 2023, 13(6), 3873; https://doi.org/10.3390/app13063873 - 18 Mar 2023
Cited by 2 | Viewed by 1398
Abstract
Low-grade gliomas are a heterogeneous group of infiltrative neoplasms. Radiomics allows the characterization of phenotypes with high-throughput extraction of quantitative imaging features from radiologic images. Deep learning models, such as convolutional neural networks (CNNs), offer well-performing models and a simplified pipeline by automatic [...] Read more.
Low-grade gliomas are a heterogeneous group of infiltrative neoplasms. Radiomics allows the characterization of phenotypes with high-throughput extraction of quantitative imaging features from radiologic images. Deep learning models, such as convolutional neural networks (CNNs), offer well-performing models and a simplified pipeline by automatic feature learning. In our study, MRI data were retrospectively obtained from The Cancer Imaging Archive (TCIA), which contains MR images for a subset of the LGG patients in The Cancer Genome Atlas (TCGA). Corresponding molecular genetics and clinical information were obtained from TCGA. Three genes included in the genetic signatures were WEE1, CRTAC1, and SEMA4G. A CNN-based deep learning model was used to classify patients into low and high-risk groups, with the median gene signature risk score as the cut-off value. The data were randomly split into training and test sets, with 61 patients in the training set and 20 in the test set. In the test set, models using T1 and T2 weighted images had an area under the receiver operating characteristic curve of 73% and 79%, respectively. In conclusion, we developed a CNN-based model to predict non-invasively the risk stratification provided by the prognostic gene signature in LGGs. Numerous previously discovered gene signatures and novel genetic identifiers that will be developed in the future may be utilized with this method. Full article
(This article belongs to the Special Issue Artificial Intelligence (AI) in Neuroscience)
Show Figures

Figure 1

13 pages, 1953 KiB  
Article
Dissimilarity Corrective Generative Adversarial Network for Brain Image Segmentation
by Rukesh Prajapati and Goo-Rak Kwon
Appl. Sci. 2022, 12(24), 12944; https://doi.org/10.3390/app122412944 - 16 Dec 2022
Cited by 1 | Viewed by 1117
Abstract
More accurate diagnosis of brain disorders can be achieved by properly analyzing structural changes in the brain. For the quantification of change in brain structure, the segmentation task is crucial. Recently, generative adversarial networks (GAN) have been rapidly developed and used in many [...] Read more.
More accurate diagnosis of brain disorders can be achieved by properly analyzing structural changes in the brain. For the quantification of change in brain structure, the segmentation task is crucial. Recently, generative adversarial networks (GAN) have been rapidly developed and used in many fields. Segmentation of medical images with these networks will greatly improve performance. However, segmentation accuracy improvement is a challenging task. In this paper, we propose a novel corrective algorithm for updating the accuracy and a novel loss function based on dissimilarity. First, we update the generator using the typical dice similarity coefficient (DSC) as a loss function only. For the next update, we use the same image as input and obtain the output; this time, we calculate dissimilarity and update the generator again. In this way, false prediction, due to the first weight update, can be updated again to minimize the dissimilarity. Our proposed algorithm can correct the weights to minimize the error. The DSC scores obtained with the proposed algorithm and the loss function are higher, and clearly outperformed the model with only DSC as the loss function for the generator. Full article
(This article belongs to the Special Issue Artificial Intelligence (AI) in Neuroscience)
Show Figures

Figure 1

Review

Jump to: Research

27 pages, 364 KiB  
Review
An Overview of Open Source Deep Learning-Based Libraries for Neuroscience
by Louis Fabrice Tshimanga, Federico Del Pup, Maurizio Corbetta and Manfredo Atzori
Appl. Sci. 2023, 13(9), 5472; https://doi.org/10.3390/app13095472 - 27 Apr 2023
Cited by 2 | Viewed by 2314
Abstract
In recent years, deep learning has revolutionized machine learning and its applications, producing results comparable to human experts in several domains, including neuroscience. Each year, hundreds of scientific publications present applications of deep neural networks for biomedical data analysis. Due to the fast [...] Read more.
In recent years, deep learning has revolutionized machine learning and its applications, producing results comparable to human experts in several domains, including neuroscience. Each year, hundreds of scientific publications present applications of deep neural networks for biomedical data analysis. Due to the fast growth of the domain, it could be a complicated and extremely time-consuming task for worldwide researchers to have a clear perspective of the most recent and advanced software libraries. This work contributes to clarifying the current situation in the domain, outlining the most useful libraries that implement and facilitate deep learning applications for neuroscience, allowing scientists to identify the most suitable options for their research or clinical projects. This paper summarizes the main developments in deep learning and their relevance to neuroscience; it then reviews neuroinformatic toolboxes and libraries collected from the literature and from specific hubs of software projects oriented to neuroscience research. The selected tools are presented in tables detailing key features grouped by the domain of application (e.g., data type, neuroscience area, task), model engineering (e.g., programming language, model customization), and technological aspect (e.g., interface, code source). The results show that, among a high number of available software tools, several libraries stand out in terms of functionalities for neuroscience applications. The aggregation and discussion of this information can help the neuroscience community to develop their research projects more efficiently and quickly, both by means of readily available tools and by knowing which modules may be improved, connected, or added. Full article
(This article belongs to the Special Issue Artificial Intelligence (AI) in Neuroscience)
Back to TopTop