Research

Jump to: Review

23 pages, 3990 KiB

Open AccessArticle

The Active Segmentation Platform for Microscopic Image Classification and Segmentation

by Sumit K. Vohra and Dimiter Prodanov

Brain Sci. 2021, 11(12), 1645; https://doi.org/10.3390/brainsci11121645 - 14 Dec 2021

Cited by 4 | Viewed by 3768

Image segmentation still represents an active area of research since no universal solution can be identified. Traditional image segmentation algorithms are problem-specific and limited in scope. On the other hand, machine learning offers an alternative paradigm where predefined features are combined into different [...] Read more.

Image segmentation still represents an active area of research since no universal solution can be identified. Traditional image segmentation algorithms are problem-specific and limited in scope. On the other hand, machine learning offers an alternative paradigm where predefined features are combined into different classifiers, providing pixel-level classification and segmentation. However, machine learning only can not address the question as to which features are appropriate for a certain classification problem. The article presents an automated image segmentation and classification platform, called Active Segmentation, which is based on ImageJ. The platform integrates expert domain knowledge, providing partial ground truth, with geometrical feature extraction based on multi-scale signal processing combined with machine learning. The approach in image segmentation is exemplified on the ISBI 2012 image segmentation challenge data set. As a second application we demonstrate whole image classification functionality based on the same principles. The approach is exemplified using the HeLa and HEp-2 data sets. Obtained results indicate that feature space enrichment properly balanced with feature selection functionality can achieve performance comparable to deep learning approaches. In summary, differential geometry can substantially improve the outcome of machine learning since it can enrich the underlying feature space with new geometrical invariant objects. Full article

(This article belongs to the Special Issue Neuroinformatics and Signal Processing)

► Show Figures

Figure 1

16 pages, 2806 KiB

Open AccessArticle

FARCI: Fast and Robust Connectome Inference

by Saber Meamardoost, Mahasweta Bhattacharya, Eun Jung Hwang, Takaki Komiyama, Claudia Mewes, Linbing Wang, Ying Zhang and Rudiyanto Gunawan

Brain Sci. 2021, 11(12), 1556; https://doi.org/10.3390/brainsci11121556 - 24 Nov 2021

Cited by 2 | Viewed by 2169

Abstract

The inference of neuronal connectome from large-scale neuronal activity recordings, such as two-photon Calcium imaging, represents an active area of research in computational neuroscience. In this work, we developed FARCI (Fast and Robust Connectome Inference), a MATLAB package for neuronal connectome inference from [...] Read more.

The inference of neuronal connectome from large-scale neuronal activity recordings, such as two-photon Calcium imaging, represents an active area of research in computational neuroscience. In this work, we developed FARCI (Fast and Robust Connectome Inference), a MATLAB package for neuronal connectome inference from high-dimensional two-photon Calcium fluorescence data. We employed partial correlations as a measure of the functional association strength between pairs of neurons to reconstruct a neuronal connectome. We demonstrated using in silico datasets from the Neural Connectomics Challenge (NCC) and those generated using the state-of-the-art simulator of Neural Anatomy and Optimal Microscopy (NAOMi) that FARCI provides an accurate connectome and its performance is robust to network sizes, missing neurons, and noise levels. Moreover, FARCI is computationally efficient and highly scalable to large networks. In comparison with the best performing connectome inference algorithm in the NCC, Generalized Transfer Entropy (GTE), and Fluorescence Single Neuron and Network Analysis Package (FluoroSNNAP), FARCI produces more accurate networks over different network sizes, while providing significantly better computational speed and scaling. Full article

(This article belongs to the Special Issue Neuroinformatics and Signal Processing)

► Show Figures

Figure 1

13 pages, 39277 KiB

Open AccessArticle

Extensions of Granger Causality Calculations on Brain Networks for Efficient and Accurate Seizure Focus Identification via iEEGs

by Victor B. Yang and Joseph R. Madsen

Brain Sci. 2021, 11(9), 1167; https://doi.org/10.3390/brainsci11091167 - 01 Sep 2021

Cited by 3 | Viewed by 2208

Abstract

Current epilepsy surgery planning protocol determines the seizure onset zone (SOZ) through resource-intensive, invasive monitoring of ictal events. Recently, we have reported that Granger Causality (GC) maps produced from analysis of interictal iEEG recordings have potential in revealing SOZ. In this study, we [...] Read more.

Current epilepsy surgery planning protocol determines the seizure onset zone (SOZ) through resource-intensive, invasive monitoring of ictal events. Recently, we have reported that Granger Causality (GC) maps produced from analysis of interictal iEEG recordings have potential in revealing SOZ. In this study, we investigate GC maps’ network connectivity patterns to determine possible clinical correlation with patients’ SOZ and resection zone (RZ). While building understanding of interictal network topography and its relationship to the RZ/SOZ, we identify algorithmic tools with potential applications in epilepsy surgery planning. These graph algorithms are retrospectively tested on data from 25 patients and compared to the neurologist-determined SOZ and surgical RZ, viewed as sources of truth. Centrality algorithms yielded statistically significant RZ rank order sums for 16 of 24 patients with RZ data, representing an improvement from prior algorithms. While SOZ results remained largely the same, this study validates the applicability of graph algorithms to RZ/SOZ detection, opening the door to further exploration of iEEG datasets. Furthermore, this study offers previously inaccessible insights into the relationship between interictal brain connectivity patterns and epileptic brain networks, utilizing the overall topology of the graphs as well as data on edge weights and quantity of edges contained in GC maps. Full article

(This article belongs to the Special Issue Neuroinformatics and Signal Processing)

► Show Figures

Figure 1

15 pages, 5943 KiB

Open AccessArticle

Evaluation of Participant Success in Gamified Drone Training Simulator Using Brain Signals and Key Logs

by Durmuş Koç, Ahmet Çağdaş Seçkin and Zümrüt Ecevit Satı

Brain Sci. 2021, 11(8), 1024; https://doi.org/10.3390/brainsci11081024 - 31 Jul 2021

Cited by 3 | Viewed by 2761

Abstract

The risk of accidents while operating a drone is quite high. The most important solution is training for drone pilots. Drone pilot training can be done in both physical and virtual environments, but the probability of an accident is higher for pilot trainees, [...] Read more.

The risk of accidents while operating a drone is quite high. The most important solution is training for drone pilots. Drone pilot training can be done in both physical and virtual environments, but the probability of an accident is higher for pilot trainees, so the first method is to train in a virtual environment. The purpose of this study is to develop a new system to collect data on students’ educational development performance of students during the use of Gamified Drone Training Simulator and objectively analyze students’ development. A multimodal recording system that can collect simulator, keystroke, and brain activity data has been developed to analyze the cognitive and physical activities of participants trained in the gamified drone simulator. It was found that as the number of trials increased, participants became accustomed to the cognitive load of visual/auditory tasks and therefore the power in the alpha and beta bands decreased. It was observed that participants’ meditation and attention scores increased with the number of repetitions of the educational game. It can be concluded that the number of repetitions lowers stress and anxiety levels, increases attention, and thus enhances game performance. Full article

(This article belongs to the Special Issue Neuroinformatics and Signal Processing)

► Show Figures

Figure 1

9 pages, 1158 KiB

Open AccessArticle

Change in Blood Flow Velocity Pulse Waveform during Plateau Waves of Intracranial Pressure

by Karol Sawicki, Michał M. Placek, Tomasz Łysoń, Zenon Mariak, Robert Chrzanowski and Marek Czosnyka

Brain Sci. 2021, 11(8), 1000; https://doi.org/10.3390/brainsci11081000 - 29 Jul 2021

Cited by 3 | Viewed by 1789

Abstract

A reliable method for non-invasive detection of dangerous intracranial pressure (ICP) elevations is still unavailable. In this preliminary study, we investigate quantitatively our observation that superimposing waveforms of transcranial Doppler blood flow velocity (FV) and arterial blood pressure (ABP) may help in non-invasive [...] Read more.

A reliable method for non-invasive detection of dangerous intracranial pressure (ICP) elevations is still unavailable. In this preliminary study, we investigate quantitatively our observation that superimposing waveforms of transcranial Doppler blood flow velocity (FV) and arterial blood pressure (ABP) may help in non-invasive identification of ICP plateau waves. Recordings of FV, ABP and ICP in 160 patients with severe head injury (treated in the Neurocritical Care Unit at Addenbrookes Hospital, Cambridge, UK) were reviewed retrospectively. From that cohort, we identified 18 plateau waves registered in eight patients. A “measure of dissimilarity” (Dissimilarity/Difference Index, DI) between ABP and FV waveforms was calculated in three following steps: 1. fragmentation of ABP and FV signal according to cardiac cycle; 2. obtaining the normalised representative ABP and FV cycles; and finally; 3. assessing their difference, represented by the area between both curves. DI appeared to discriminate ICP plateau waves from baseline episodes slightly better than conventional pulsatility index did: area under ROC curve 0.92 vs. 0.90, sensitivity 0.81 vs. 0.69, accuracy 0.88 vs. 0.84, respectively. The concept of DI, if further tested and improved, might be used for non-invasive detection of ICP plateau waves. Full article

(This article belongs to the Special Issue Neuroinformatics and Signal Processing)

► Show Figures

Figure 1

21 pages, 3518 KiB

Open AccessArticle

Identification of Neurodegenerative Diseases Based on Vertical Ground Reaction Force Classification Using Time–Frequency Spectrogram and Deep Learning Neural Network Features

by Febryan Setiawan and Che-Wei Lin

Brain Sci. 2021, 11(7), 902; https://doi.org/10.3390/brainsci11070902 - 08 Jul 2021

Cited by 8 | Viewed by 3149

Abstract

A novel identification algorithm using a deep learning approach was developed in this study to classify neurodegenerative diseases (NDDs) based on the vertical ground reaction force (vGRF) signal. The irregularity of NDD vGRF signals caused by gait abnormalities can indicate different force pattern [...] Read more.

A novel identification algorithm using a deep learning approach was developed in this study to classify neurodegenerative diseases (NDDs) based on the vertical ground reaction force (vGRF) signal. The irregularity of NDD vGRF signals caused by gait abnormalities can indicate different force pattern variations compared to a healthy control (HC). The main purpose of this research is to help physicians in the early detection of NDDs, efficient treatment planning, and monitoring of disease progression. The detection algorithm comprises a preprocessing process, a feature transformation process, and a classification process. In the preprocessing process, the five-minute vertical ground reaction force signal was divided into 10, 30, and 60 s successive time windows. In the feature transformation process, the time–domain vGRF signal was modified into a time–frequency spectrogram using a continuous wavelet transform (CWT). Then, feature enhancement with principal component analysis (PCA) was utilized. Finally, a convolutional neural network, as a deep learning classifier, was employed in the classification process of the proposed detection algorithm and evaluated using leave-one-out cross-validation (LOOCV) and k-fold cross-validation (k-fold CV, k = 5). The proposed detection algorithm can effectively differentiate gait patterns based on a time–frequency spectrogram of a vGRF signal between HC subjects and patients with neurodegenerative diseases. Full article

(This article belongs to the Special Issue Neuroinformatics and Signal Processing)

► Show Figures

Figure 1

14 pages, 4039 KiB

Open AccessArticle

Classification of Prefrontal Cortex Activity Based on Functional Near-Infrared Spectroscopy Data upon Olfactory Stimulation

by Cheng-Hsuan Chen, Kuo-Kai Shyu, Cheng-Kai Lu, Chi-Wen Jao and Po-Lei Lee

Brain Sci. 2021, 11(6), 701; https://doi.org/10.3390/brainsci11060701 - 26 May 2021

Cited by 2 | Viewed by 2579

Abstract

The sense of smell is one of the most important organs in humans, and olfactory imaging can detect signals in the anterior orbital frontal lobe. This study assessed olfactory stimuli using support vector machines (SVMs) with signals from functional near-infrared spectroscopy (fNIRS) data [...] Read more.

The sense of smell is one of the most important organs in humans, and olfactory imaging can detect signals in the anterior orbital frontal lobe. This study assessed olfactory stimuli using support vector machines (SVMs) with signals from functional near-infrared spectroscopy (fNIRS) data obtained from the prefrontal cortex. These data included odor stimuli and air state, which triggered the hemodynamic response function (HRF), determined from variations in oxyhemoglobin (oxyHb) and deoxyhemoglobin (deoxyHb) levels; photoplethysmography (PPG) of two wavelengths (raw optical red and near-infrared data); and the ratios of data from two optical datasets. We adopted three SVM kernel functions (i.e., linear, quadratic, and cubic) to analyze signals and compare their performance with the HRF and PPG signals. The results revealed that oxyHb yielded the most efficient single-signal data with a quadratic kernel function, and a combination of HRF and PPG signals yielded the most efficient multi-signal data with the cubic function. Our results revealed superior SVM analysis of HRFs for classifying odor and air status using fNIRS data during olfaction in humans. Furthermore, the olfactory stimulation can be accurately classified by using quadratic and cubic kernel functions in SVM, even for an individual participant data set. Full article

(This article belongs to the Special Issue Neuroinformatics and Signal Processing)

► Show Figures

Figure 1

23 pages, 19939 KiB

Open AccessArticle

Computer-Aided Intracranial EEG Signal Identification Method Based on a Multi-Branch Deep Learning Fusion Model and Clinical Validation

by Yiping Wang, Yang Dai, Zimo Liu, Jinjie Guo, Gongpeng Cao, Mowei Ouyang, Da Liu, Yongzhi Shan, Guixia Kang and Guoguang Zhao

Brain Sci. 2021, 11(5), 615; https://doi.org/10.3390/brainsci11050615 - 11 May 2021

Cited by 17 | Viewed by 3139

Abstract

Surgical intervention or the control of drug-refractory epilepsy requires accurate analysis of invasive inspection intracranial EEG (iEEG) data. A multi-branch deep learning fusion model is proposed to identify epileptogenic signals from the epileptogenic area of the brain. The classical approach extracts multi-domain signal [...] Read more.

Surgical intervention or the control of drug-refractory epilepsy requires accurate analysis of invasive inspection intracranial EEG (iEEG) data. A multi-branch deep learning fusion model is proposed to identify epileptogenic signals from the epileptogenic area of the brain. The classical approach extracts multi-domain signal wave features to construct a time-series feature sequence and then abstracts it through the bi-directional long short-term memory attention machine (Bi-LSTM-AM) classifier. The deep learning approach uses raw time-series signals to build a one-dimensional convolutional neural network (1D-CNN) to achieve end-to-end deep feature extraction and signal detection. These two branches are integrated to obtain deep fusion features and results. Resampling is employed to split the imbalanced epileptogenic and non-epileptogenic samples into balanced subsets for clinical validation. The model is validated over two publicly available benchmark iEEG databases to verify its effectiveness on a private, large-scale, clinical stereo EEG database. The model achieves high sensitivity (97.78%), accuracy (97.60%), and specificity (97.42%) on the Bern–Barcelona database, surpassing the performance of existing state-of-the-art techniques. It is then demonstrated on a clinical dataset with an average intra-subject accuracy of 92.53% and cross-subject accuracy of 88.03%. The results suggest that the proposed method is a valuable and extremely robust approach to help researchers and clinicians develop an automated method to identify the source of iEEG signals. Full article

(This article belongs to the Special Issue Neuroinformatics and Signal Processing)

► Show Figures

Figure 1

Review

Jump to: Research

31 pages, 1516 KiB

Open AccessReview

Brain Image Segmentation in Recent Years: A Narrative Review

by Ali Fawzi, Anusha Achuthan and Bahari Belaton

Brain Sci. 2021, 11(8), 1055; https://doi.org/10.3390/brainsci11081055 - 10 Aug 2021

Cited by 25 | Viewed by 4916

Abstract

Brain image segmentation is one of the most time-consuming and challenging procedures in a clinical environment. Recently, a drastic increase in the number of brain disorders has been noted. This has indirectly led to an increased demand for automated brain segmentation solutions to [...] Read more.

Brain image segmentation is one of the most time-consuming and challenging procedures in a clinical environment. Recently, a drastic increase in the number of brain disorders has been noted. This has indirectly led to an increased demand for automated brain segmentation solutions to assist medical experts in early diagnosis and treatment interventions. This paper aims to present a critical review of the recent trend in segmentation and classification methods for brain magnetic resonance images. Various segmentation methods ranging from simple intensity-based to high-level segmentation approaches such as machine learning, metaheuristic, deep learning, and hybridization are included in the present review. Common issues, advantages, and disadvantages of brain image segmentation methods are also discussed to provide a better understanding of the strengths and limitations of existing methods. From this review, it is found that deep learning-based and hybrid-based metaheuristic approaches are more efficient for the reliable segmentation of brain tumors. However, these methods fall behind in terms of computation and memory complexity. Full article

(This article belongs to the Special Issue Neuroinformatics and Signal Processing)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Neuroinformatics and Signal Processing

Share This Special Issue

Special Issue Editors

Special Issue Information

Keywords

Published Papers (9 papers)

Research

Review

Further Information

Guidelines

MDPI Initiatives

Follow MDPI