Handling Missing MRI Data in Brain Tumors Classification Tasks: Usage of Synthetic Images vs. Duplicate Images and Empty Images.

BACKGROUND: Deep-learning is widely used for lesion classification. However, in the clinic patient data often has missing images. PURPOSE: To evaluate the use of generated, duplicate and empty(black) images for replacing missing MRI data in AI brain tumor classification tasks. STUDY TYPE: Retrospective. POPULATION: 224 patients (local-dataset; low-grade-glioma (LGG) = 37, high-grade-glioma (HGG) = 187) and 335 patients (public-dataset (BraTS); LGG = 76, HGG = 259). The local-dataset was divided into training (64), validation (16), and internal-test-data (20), while the public-dataset was an independent test-set. FIELD STRENGTH/SEQUENCE: T1WI, T1WI+C, T2WI, and FLAIR images (1.5T/3.0T-MR), obtained from different suppliers. ASSESSMENT: Three image-to-image translation generative-adversarial-network (Pix2Pix-GAN) models were trained on the local-dataset, to generate T1WI, T2WI, and FLAIR images. The rating-and-preference-judgment assessment was performed by three human-readers (radiologist (MD) and two MRI-technicians). Resnet152 was used for classification, and inference was performed on both datasets, with baseline input, and with missing data replaced by 1) generated images; 2) duplication of existing images; and 3) black images. STATISTICAL TESTS: The similarity between the generated and the original images was evaluated using the peak-signal-to-noise-ratio (PSNR) and the structural-similarity-index-measure (SSIM). Classification results were evaluated using accuracy, F1-score and the Kolmogorov-Smirnov test and distance. RESULTS: For baseline-state, the classification model reached to accuracy = 0.93,0.82 on the local and public-datasets. For the missing-data methods, high similarity was obtained between the generated and the original images with mean PSNR = 35.65,32.94 and SSIM = 0.87,0.91 on the local and public-datasets; 39% of the generated-images were labeled as real images by the human-readers. The classification model using generated-images to replace missing images produced the highest results with mean accuracy = 0.91,0.82 compared to 0.85,0.79 for duplicated and 0.77,0.68 for use of black images; DATA CONCLUSION: The feasibility for inference classification model on an MRI dataset with missing images using the Pix2pix-GAN generated images, was shown. The stability and generalization ability of the model was demonstrated by producing consistent results on two independent datasets. LEVEL OF EVIDENCE: 3 TECHNICAL EFFICACY: Stage 5.

Utilizing the TractSeg Tool for Automatic Corticospinal Tract Segmentation in Patients With Brain Pathology.

Purpose: White-matter tract segmentation in patients with brain pathology can guide surgical planning and can be used for tissue integrity assessment. Recently, TractSeg was proposed for automatic tract segmentation in healthy subjects. The aim of this study was to assess the use of TractSeg for corticospinal-tract (CST) segmentation in a large cohort of patients with brain pathology and to evaluate its consistency in repeated measurements. Methods: A total of 649 diffusion-tensor-imaging scans were included, of them: 625 patients and 24 scans from 12 healthy controls (scanned twice for consistency assessment). Manual CST labeling was performed in all cases, and by 2 raters for the healthy subjects. Segmentation results were evaluated based on the Dice score. In order to evaluate consistency in repeated measurements, volume, Fractional Anisotropy (FA), and Mean Diffusivity (MD) values were extracted and correlated for the manual versus automatic methods. Results: For the automatic CST segmentation Dice scores of 0.63 and 0.64 for the training and testing datasets were obtained. Higher consistency between measurements was detected for the automatic segmentation, with between measurements correlations of volume = 0.92/0.65, MD = 0.94/0.75 for the automatic versus manual segmentation. Conclusions: The TractSeg method enables automatic CST segmentation in patients with brain pathology. Superior measurements consistency was detected for the automatic in comparison to manual fiber segmentation, which indicates an advantage when using this method for clinical and longitudinal studies.

Recommendations for Responsible Development and Application of Neurotechnologies.

Advancements in novel neurotechnologies, such as brain computer interfaces (BCI) and neuromodulatory devices such as deep brain stimulators (DBS), will have profound implications for society and human rights. While these technologies are improving the diagnosis and treatment of mental and neurological diseases, they can also alter individual agency and estrange those using neurotechnologies from their sense of self, challenging basic notions of what it means to be human. As an international coalition of interdisciplinary scholars and practitioners, we examine these challenges and make recommendations to mitigate negative consequences that could arise from the unregulated development or application of novel neurotechnologies. We explore potential ethical challenges in four key areas: identity and agency, privacy, bias, and enhancement. To address them, we propose (1) democratic and inclusive summits to establish globally-coordinated ethical and societal guidelines for neurotechnology development and application, (2) new measures, including "Neurorights," for data privacy, security, and consent to empower neurotechnology users' control over their data, (3) new methods of identifying and preventing bias, and (4) the adoption of public guidelines for safe and equitable distribution of neurotechnological devices.

EEG generator--a model of potentials in a volume conductor.

EEG generator-a model of potentials in a volume conductor. The potential recorded over the cortex electro-corticogram (ECoG) or over the scalp [electroencephalograph (EEG)] derives from the activity of many sources known as "EEG generators." The recorded amplitude is basically a function of the unitary potential of a generator and the statistical relationship between different EEG generators in the recorded population. In this study, we first suggest a new definition of the EEG generator. We use the theory of potentials in a volume conductor and model the contribution of a single synapse activated to the surface potential. We then model the contribution of the generator to the surface potential. Once the generator and its contribution are well defined, we can quantitatively assess the degree of synchronization among generators. The measures obtained by the model for a real life scenario of a group of generators organized in a specific statistical way were consistent with the expected values that were reported experimentally. The study sheds new light on macroscopic modeling approaches which make use of mean soma membrane potential. We showed major contribution of activity of superficial apical synapses to the ECoG signal recorded relative to lower somatic or basal synapses activity.

Simultaneous remote extraction of multiple speech sources and heart beats from secondary speckles pattern.

The ability of dynamic extraction of remote sounds is very appealing. In this manuscript we propose an optical approach allowing the extraction and the separation of remote sound sources. The approach is very modular and it does not apply any constraints regarding the relative position of the sound sources and the detection device. The optical setup doing the detection is very simple and versatile. The principle is to observe the movement of the secondary speckle patterns that are generated on top of the target when it is illuminated by a spot of laser beam. Proper adaption of the imaging optics allows following the temporal trajectories of those speckles and extracting the sound signals out of the processed trajectory. Various sound sources are imaged in different spatial pixels and thus blind source separation becomes a very simple task.

Resolving the dynamics of EEG generators by multichannel recordings.

The voltage recorded over the cortex (ECoG) or over the scalp (EEG) is generated by currents derived from many sources called "generators". Different patterns and amplitudes are observed in aroused, sleepy, epileptic or other brain states. Differences in amplitude are generally attributed to differences in synchrony among generators. The degree of EEG synchrony is measured by the correlation between electrodes placed over different cortical regions. We present a new way to quantitatively assess the degree of synchronization of these generators via multichannel recordings. We illustrate how situations where there are several groups of generators with different inter-group and intra-group synchronies can be analyzed. Finally, we present a way to identify the organization of groups exhibiting topographic organization. Although the model presented here is highly simplified, several methods are based on averaging activity over increasingly larger areas. These types of measurements may be applied as well to EEG and ECoG recordings.

ADHD and dysgraphia: underlying mechanisms.

Multiple complaints in the domain of writing are common among children with Attention Deficit Hyperactivity Disorder (ADHD). In this work we sought to characterize the writing disorder by studying dysgraphia in twenty 6th grade boys with ADHD and normal reading skills matched to 20 healthy boys who served as a comparison group. Dysgraphia, defined as deficits in spelling and handwriting, was assessed according to neuropsychological explanatory processes within 3 primary domains: linguistic processing, motor programming and motor kinematics. Children with ADHD made significantly more spelling errors, but showed a unique pattern introducing letter insertions, substitutions, transpositions and omissions. This error type, also known as graphemic buffer errors, can be explained by impaired attention aspects needed for motor planning. Kinematic manifestations of writing deficits were fast, inaccurate and an inefficient written product accompanied by higher levels of axial pen pressure. These results suggest that the spelling errors and writing deficits seen in children with ADHD and normal reading skills stem primarily from non-linguistic deficits, while linguistic factors play a secondary role. Recommendations for remediation include educational interventions, use of word processing and judicious use of psychostimulants.

Processing of multichannel recordings for data-mining algorithms.

Data Mining, or knowledge discovery, is the computer-assisted process of digging through and analyzing large quantity of data in order to extract meaningful knowledge. Data mining methods are used in many studies to identify phenomena quicker and better than human experts. One class of these methods was designed for dealing with time series data. However, when several channels of data are collected simultaneously, data mining algorithms encounter numerous difficulties since channels may be measured in different units, may be recorded at different sampling-rates, or may have completely different characteristics. Furthermore, as the size of these data increases, the amount of irrelevant data usually increases as well and the process becomes impractical. Hence, in such cases, the analyst must be capable of focusing on the informational parts while ignoring the noise data. These kinds of difficulties complicate the analysis of multichannel data as compared to the analysis of single-channel data. This paper presents a useful technique for preprocessing multi channel data. Our technique supplies tools for coping with all the above-mentioned difficulties, and prepares the data for further analysis (using common algorithms, especially from the data mining field). The paper is divided as follows. After the introduction (Section I) we describe the state of the art (Section II), follows by the main section-methodology (Section III) which is divided to four steps (3.2-3.5). The results are described in a separate section (Section IV). Then, a discussion and conclusions of the proposed methodology are given in (Sections V and VI). Acknowledgements and the references follow.

Programmed deep brain stimulation synchronizes VTA gamma band field potential and alleviates depressive-like behavior in rats.

Deep brain stimulation (DBS) significantly alleviates symptoms in various neurological disorders. Current research focuses on developing programmed stimulation protocols for customization to individual symptoms. However, the therapeutic mechanism of action of programmed DBS (pDBS) is poorly understood. We previously demonstrated that pDBS in the ventral tegmental area (VTA) normalizes molecular and behavioral abnormalities in the Flinders Sensitive Line (FSL) rat model for depression. Herein, we examined the effect of a short-duration, low-frequency DBS template on local field potential (LFP) synchronization patterns along the anterior-posterior axis of the VTA of FSL rats, and correlation of this effect with depressive-like behavior, as compared with non-programmed, continuous low-frequency DBS (npDBS). We used the wavelet phase coherence (WPC) measure for effective representation of time and frequency of LFP patterns, and the forced swim test to measure immobility (despair). Baseline WPC values were lower in FSLs as compared with SD controls, at the low and high gamma frequency range (above 30 Hz). Baseline immobility scores for FSL rats were higher than those of SD rats, while pDBS, and not npDBS, significantly reduced FSL immobility scores to control SD levels, up to day 14. pDBS also significantly increased the change (between baseline and day 14) in WPC values, in beta, low gamma and high gamma frequency ranges. The change in high gamma (60-100 Hz) WPC values correlated with improvement in depressive-like behavior. Our results suggest that programmed DBS of the VTA increases interaction among local neuronal populations, an effect that may underlie the normalization of depressive-like behavior.

Compositionality in neural control: an interdisciplinary study of scribbling movements in primates.

This article discusses the compositional structure of hand movements by analyzing and modeling neural and behavioral data obtained from experiments where a monkey (Macaca fascicularis) performed scribbling movements induced by a search task. Using geometrically based approaches to movement segmentation, it is shown that the hand trajectories are composed of elementary segments that are primarily parabolic in shape. The segments could be categorized into a small number of classes on the basis of decreasing intra-class variance over the course of training. A separate classification of the neural data employing a hidden Markov model showed a coincidence of the neural states with the behavioral categories. An additional analysis of both types of data by a data mining method provided evidence that the neural activity patterns underlying the behavioral primitives were formed by sets of specific and precise spike patterns. A geometric description of the movement trajectories, together with precise neural timing data indicates a compositional variant of a realistic synfire chain model. This model reproduces the typical shapes and temporal properties of the trajectories; hence the structure and composition of the primitives may reflect meaningful behavior.

A microscope configuration for nanometer 3-D movement monitoring accuracy.

In this paper we present a new microscopy configuration based upon temporal tracking of a secondary reflected speckle by imaging the speckle through properly defocused optics. The configuration is used to monitor three-dimensional (3-D) spontaneous contraction of rat cardiac muscle cells while achieving nanometer tracking accuracy at a rate of 30 frames per second (fps) without using interferometric recording. Estimation of the change in the optical path of accuracy of 50 nm in the transverse direction and of 200 nm in the axial direction was achieved.

Demonstration of remote optical measurement configuration that correlates to glucose concentration in blood.

An optical approach allowing the extraction and the separation of remote vibration sources has recently been proposed. The approach has also been applied for medical related applications as blood pressure and heart beats monitoring. In this paper we demonstrate its capability to monitor glucose concentration in blood stream. The technique is based on the tracking of temporal changes of reflected secondary speckle produced in human skin (wrist) when being illuminated by a laser beam. A temporal change in skin's vibration profile generated due to blood pulsation is analyzed for estimating the glucose concentration. Experimental tests that were carried out in order to verify the proposed approach showed good match with the change of the glucose level at the positive slope stage as it was obtained from conventional reference measurement.

Remote estimation of blood pulse pressure via temporal tracking of reflected secondary speckles pattern.

We present a novel technique for remote noncontact blood pulse pressure measurement. It is based on tracking both temporal and amplitude changes of reflected secondary speckle produced in human skin when illuminated by a laser beam. The implemented technique extracts the difference between the systolic and the diastolic blood pressure. Experimental results are presented showing good agreement when compared with conventional measurement methods.

Data mining techniques for detection of sleep arousals.

Arousals are considered one of the main causes of daytime sleepiness. They impede the proper flow of sleep cycles and cause weariness. Manual scoring of arousals is time-consuming, requires expert knowledge, and has high inter-scorer variability. A major difficulty in detecting arousals automatically is the existing variance across patients. Based on data mining techniques, we present a different approach to the automatic detection of arousals that overcomes the hurdle of differences in signal characteristics across patients. Offline we used a training-set of adult patients to define a set of general rules to detect arousals (termed meta-rules). This was done by analyzing the correlations between occurrences of arousals and the EEG, EMG, pulse and SaO2 signals as follows: (1) each signal was mathematically projected into several spaces (termed projected-signals); (2) from each such projected-signal, the algorithm extracted time points that indicated meaningful changes (termed critical-points); (3) data mining techniques were applied to all the critical-points to discover patterns of repeating behavior; (4) classes of patterns which were highly correlated with manually scored arousals were formalized as meta-rules. Online we used a test-set of adult patients from two other different sleep laboratories. Using the meta-rules, the algorithm extracted individual rules for each patient (termed actual-rules), and used them to automatically detect the patients' arousals. These arousals were significantly correlated (R=0.88, p<0.0001; sensitivity=75.2%, positive predictive value=76.5%) with those detected manually by experts. Since the total number of arousals is a measure of sleep quality, this algorithm constitutes a novel approach to automatically estimate sleep quality.

Emergence and size of the giant component in clustered random graphs with a given degree distribution.

Standard techniques for analyzing network models usually break down in the presence of clustering. Here we introduce a new analytic tool, the "free-excess degree" distribution, which extends the generating function framework, making it applicable for clustered networks (C>0). The methodology is general and provides a new expression for the threshold point at which the giant component emerges and shows that it scales as (1-C)(-1). In addition, the size of the giant component may be predicted even for more complicated scenarios such as the removal of a fixed fraction of nodes at random.

Source localization of temporal lobe epilepsy using PCA-LORETA analysis on ictal EEG recordings.

Localizing the source of an epileptic seizure using noninvasive EEG suffers from inaccuracies produced by other generators not related to the epileptic source. The authors isolated the ictal epileptic activity, and applied a source localization algorithm to identify its estimated location. Ten ictal EEG scalp recordings from five different patients were analyzed. The patients were known to have temporal lobe epilepsy with a single epileptic focus that had a concordant MRI lesion. The patients had become seizure-free following partial temporal lobectomy. A midinterval (approximately 5 seconds) period of ictal activity was used for Principal Component Analysis starting at ictal onset. The level of epileptic activity at each electrode (i.e., the eigenvector of the component that manifest epileptic characteristic), was used as an input for low-resolution tomography analysis for EEG inverse solution (Zilberstain et al., 2004). The algorithm accurately and robustly identified the epileptic focus in these patients. Principal component analysis and source localization methods can be used in the future to monitor the progression of an epileptic seizure and its expansion to other areas.

Evolving synaptic plasticity with an evolutionary cellular development model.

Since synaptic plasticity is regarded as a potential mechanism for memory formation and learning, there is growing interest in the study of its underlying mechanisms. Recently several evolutionary models of cellular development have been presented, but none have been shown to be able to evolve a range of biological synaptic plasticity regimes. In this paper we present a biologically plausible evolutionary cellular development model and test its ability to evolve different biological synaptic plasticity regimes. The core of the model is a genomic and proteomic regulation network which controls cells and their neurites in a 2D environment. The model has previously been shown to successfully evolve behaving organisms, enable gene related phenomena, and produce biological neural mechanisms such as temporal representations. Several experiments are described in which the model evolves different synaptic plasticity regimes using a direct fitness function. Other experiments examine the ability of the model to evolve simple plasticity regimes in a task -based fitness function environment. These results suggest that such evolutionary cellular development models have the potential to be used as a research tool for investigating the evolutionary aspects of synaptic plasticity and at the same time can serve as the basis for novel artificial computational systems.

Inevitable evolutionary temporal elements in neural processing: a study based on evolutionary simulations.

Recent studies have suggested that some neural computational mechanisms are based on the fine temporal structure of spiking activity. However, less effort has been devoted to investigating the evolutionary aspects of such mechanisms. In this paper we explore the issue of temporal neural computation from an evolutionary point of view, using a genetic simulation of the evolutionary development of neural systems. We evolve neural systems in an environment with selective pressure based on mate finding, and examine the temporal aspects of the evolved systems. In repeating evolutionary sessions, there was a significant increase during evolution in the mutual information between the evolved agent's temporal neural representation and the external environment. In ten different simulated evolutionary sessions, there was an increased effect of time-related neural ablations on the agents' fitness. These results suggest that in some fitness landscapes the emergence of temporal elements in neural computation is almost inevitable. Future research using similar evolutionary simulations may shed new light on various biological mechanisms.

Three-dimensional mapping and range measurement by means of projected speckle patterns.

We present a novel approach for three-dimensional (3D) measurements that includes the projection of coherent light through ground glass. Such a projection generates random speckle patterns on the object or on the camera, depending if the configuration is transmissive or reflective. In both cases the spatially random patterns are seen by the sensor. Different spatially random patterns are generated at different planes. The patterns are highly random and not correlated. This low correlation between different patterns is used for both 3D mapping of objects and range finding.