Reduced Deep Convolutional Activation Features (R-DeCAF) in Histopathology Images to Improve the Classification Performance for Breast Cancer Diagnosis.

Breast cancer is the second most common cancer among women worldwide, and the diagnosis by pathologists is a time-consuming procedure and subjective. Computer-aided diagnosis frameworks are utilized to relieve pathologist workload by classifying the data automatically, in which deep convolutional neural networks (CNNs) are effective solutions. The features extracted from the activation layer of pre-trained CNNs are called deep convolutional activation features (DeCAF). In this paper, we have analyzed that all DeCAF features are not necessarily led to higher accuracy in the classification task and dimension reduction plays an important role. We have proposed reduced DeCAF (R-DeCAF) for this purpose, and different dimension reduction methods are applied to achieve an effective combination of features by capturing the essence of DeCAF features. This framework uses pre-trained CNNs such as AlexNet, VGG-16, and VGG-19 as feature extractors in transfer learning mode. The DeCAF features are extracted from the first fully connected layer of the mentioned CNNs, and a support vector machine is used for classification. Among linear and nonlinear dimensionality reduction algorithms, linear approaches such as principal component analysis (PCA) represent a better combination among deep features and lead to higher accuracy in the classification task using a small number of features considering a specific amount of cumulative explained variance (CEV) of features. The proposed method is validated using experimental BreakHis and ICIAR datasets. Comprehensive results show improvement in the classification accuracy up to 4.3% with a feature vector size (FVS) of 23 and CEV equal to 0.15.

LFP polarity changes across cortical and eccentricity in primary visual cortex.

Local field potentials (LFPs) can evaluate neural population activity in the cortex and their interaction with other cortical areas. Analyzing current source density (CSD) rather than LFPs is very significant due to the reduction of volume conduction effects. Current sinks are construed as net inward transmembrane currents, while current sources are net outward ones. Despite extensive studies of LFPs and CSDs, their morphology in different cortical layers and eccentricities are still largely unknown. Because LFP polarity changes provide a measure of neural activity, they can be useful in implanting brain-computer interface (BCI) chips and effectively communicating the BCI devices to the brain. We hypothesize that sinks and sources analyses could be a way to quantitatively achieve their characteristics in response to changes in stimulus size and layer-dependent differences with increasing eccentricities. In this study, we show that stimulus properties play a crucial role in determining the flow. The present work focusses on the primary visual cortex (V1). In this study, we investigate a map of the LFP-CSD in V1 area by presenting different stimulus properties (e.g., size and type) in the visual field area of Macaque monkeys. Our aim is to use the morphology of sinks and sources to measure the input and output information in different layers as well as different eccentricities. According to the value of CSDs, the results show that the stimuli smaller than RF's size had lower strength than the others and the larger RF's stimulus size showed smaller strength than the optimized stimulus size, which indicated the suppression phenomenon. Additionally, with the increased eccentricity, CSD's strengths were increased across cortical layers.

CCTCOVID: COVID-19 detection from chest X-ray images using Compact Convolutional Transformers.

COVID-19 is a novel virus that attacks the upper respiratory tract and the lungs. Its person-to-person transmissibility is considerably rapid and this has caused serious problems in approximately every facet of individuals' lives. While some infected individuals may remain completely asymptomatic, others have been frequently witnessed to have mild to severe symptoms. In addition to this, thousands of death cases around the globe indicated that detecting COVID-19 is an urgent demand in the communities. Practically, this is prominently done with the help of screening medical images such as Computed Tomography (CT) and X-ray images. However, the cumbersome clinical procedures and a large number of daily cases have imposed great challenges on medical practitioners. Deep Learning-based approaches have demonstrated a profound potential in a wide range of medical tasks. As a result, we introduce a transformer-based method for automatically detecting COVID-19 from X-ray images using Compact Convolutional Transformers (CCT). Our extensive experiments prove the efficacy of the proposed method with an accuracy of 99.22% which outperforms the previous works.

Neural oscillatory characteristics of feedback-associated activity in globus pallidus interna.

Neural oscillatory activities in basal ganglia have prominent roles in cognitive processes. However, the characteristics of oscillatory activities during cognitive tasks have not been extensively explored in human Globus Pallidus internus (GPi). This study aimed to compare oscillatory characteristics of GPi between dystonia and Parkinson's Disease (PD). A dystonia and a PD patient performed the Intra-Extra-Dimension shift (IED) task during both on and off-medication states. During the IED task, patients had to correctly choose between two visual stimuli containing shapes or lines based on a hidden rule via trial and error. Immediate auditory and visual feedback was provided upon the choice to inform participants if they chose correctly. Bilateral GPi Local Field Potentials (LFP) activity was recorded via externalized DBS leads. Transient high gamma activity (~ 100-150 Hz) was observed immediately after feedback in the dystonia patient. Moreover, these bursts were phase synchronous between left and right GPi with an antiphase clustering of phase differences. In contrast, no synchronous high gamma activity was detected in the PD patient with or without dopamine administration. The off-med PD patient also displayed enhanced low frequency clusters, which were ameliorated by medication. The current study provides a rare report of antiphase homotopic synchrony in human GPi, potentially related to incorporating and processing feedback information. The absence of these activities in off and on-med PD patient indicates the potential presence of impaired medication independent feedback processing circuits. Together, these findings suggest a potential role for GPi's synchronized activity in shaping feedback processing mechanisms required in cognitive tasks.

Exploring Methodological Approaches of Experimental Studies in the Field of Neuroarchitecture: A Systematic Review.

OBJECTIVES: This systematic review aims to strengthen the relationship between architecture and neuroscience by classifying data measurement techniques in the field of neuroarchitecture with a focus on the most practical and common methodological approaches. It classifies data recording techniques in different architectural categories (e.g., interior, urban, built environment). BACKGROUNDS: With regard to urban life developments and technological breakthroughs, studies of human interactions with environments have been expanding in recent years. Additionally, recent advances in neuroscience have allowed architects to find out more about human experiences in built environments, but there are few valid frameworks about what methodologies and instruments are more common to conduct experimental tasks in this interdisciplinary field. METHODS: Twenty-eight experimental studies were selected based on the preferred reporting items for systematic reviews and meta-analyses literature search extension (PRISMA) systematic review protocol and a comprehensive analysis. The task-space of selected articles was categorized into three subfields, namely, "interior design," "urban design," and "building design" based on environments and their stimuli. As for this context-based categorization, recording techniques and methodology were distinguished for each subfield division. RESULTS: More than 50% of the studies were incorporated in the first two categories, and the EEG recording was the most frequently employed neuroimaging technique thanks to the technical efficacy of its setup and the high temporal resolution of its electrophysiological signals. CONCLUSION: In this study, a summary of techniques and methodological approaches applied in the field is provided in a nut shell, and a general framework of instruments is presented to help scholars to carry out more practical research in the future leading to designing built environments more efficiently.

Ripples in macaque V1 and V4 are modulated by top-down visual attention.

Sharp-wave ripples (SWRs) are highly synchronous neuronal activity events. They have been predominantly observed in the hippocampus during offline states such as pause in exploration, slow-wave sleep, and quiescent wakefulness. SWRs have been linked to memory consolidation, spatial navigation, and spatial decision-making. Recently, SWRs have been reported during visual search, a form of remote spatial exploration, in macaque hippocampus. However, the association between SWRs and multiple forms of awake conscious and goal-directed behavior is unknown. We report that ripple activity occurs in macaque visual areas V1 and V4 during focused spatial attention. The occurrence of ripples is modulated by stimulus characteristics, increased by attention toward the receptive field, and by the size of the attentional focus. During attention cued to the receptive field, the monkey's reaction time in detecting behaviorally relevant events was reduced by ripples. These results show that ripple activity is not limited to hippocampal activity during offline states, rather they occur in the neocortex during active attentive states and vigilance behaviors.

Automated prediction of COVID-19 mortality outcome using clinical and laboratory data based on hierarchical feature selection and random forest classifier.

Early prediction of COVID-19 mortality outcome can decrease expiration risk by alerting healthcare personnel to assure efficient resource allocation and treatment planning. This study introduces a machine learning framework for the prediction of COVID-19 mortality using demographics, vital signs, and laboratory blood tests (complete blood count (CBC), coagulation, kidney, liver, blood gas, and general). 41 features from 244 COVID-19 patients were recorded on the first day of admission. In this study, first, the features in each of the eight categories were investigated. Afterward, features that have an area under the receiver operating characteristic curve (AUC) above 0.6 and the p-value criterion from the Wilcoxon rank-sum test below 0.005 were used as selected features for further analysis. Then five feature reduction methods, Forward Feature selection, minimum Redundancy Maximum Relevance, Relieff, Linear Discriminant Analysis, and Neighborhood Component Analysis were utilized to select the best combination of features. Finally, seven classifiers frameworks, random forest (RF), support vector machine, logistic regression (LR), K nearest neighbors, Artifical neural network, bagging, and boosting were used to predict the mortality outcome of COVID-19 patients. The results revealed that the combination of features in CBC and then vital signs had the highest mortality classification parameters, respectively. Furthermore, the RF classifier with hierarchical feature selection algorithms via Forward Feature selection had the highest classification power with an accuracy of 92.08 ± 2.56. Therefore, our proposed method can be confidently used as a valuable assistant prognostic tool to sieve patients with high mortality risks.

Pre-stimulus Alpha Activity Modulates Face and Object Processing in the Intra-Parietal Sulcus, a MEG Study.

Face perception is crucial in all social animals. Recent studies have shown that pre-stimulus oscillations of brain activity modulate the perceptual performance of face vs. non-face stimuli, specifically under challenging conditions. However, it is unclear if this effect also occurs during simple tasks, and if so in which brain regions. Here we used magnetoencephalography (MEG) and a 1-back task in which participants decided if the two sequentially presented stimuli were the same or not in each trial. The aim of the study was to explore the effect of pre-stimulus alpha oscillation on the perception of face (human and monkey) and non-face stimuli. Our results showed that pre-stimulus activity in the left occipital face area (OFA) modulated responses in the intra-parietal sulcus (IPS) at around 170 ms after the presentation of human face stimuli. This effect was also found after participants were shown images of motorcycles. In this case, the IPS was modulated by pre-stimulus activity in the right OFA and the right fusiform face area (FFA). We conclude that pre-stimulus modulation of post-stimulus response also occurs during simple tasks and is therefore independent of behavioral responses.

Brain-inspired multiple-target tracking using Dynamic Neural Fields.

Despite considerable progress in the field of automatic multi-target tracking, several problems such as data association remained challenging. On the other hand, cognitive studies have reported that humans can robustly track several objects simultaneously. Such circumstances happen regularly in daily life, and humans have evolved to handle the associated problems. Accordingly, using brain-inspired processing principles may contribute to significantly increase the performance of automatic systems able to follow the trajectories of multiple objects. In this paper, we propose a multiple-object tracking algorithm based on dynamic neural field theory which has been proven to provide neuro-plausible processing mechanisms for cognitive functions of the brain. We define several input neural fields responsible for representing previous location and orientation information as well as instantaneous linear and angular speed of the objects in successive video frames. Image processing techniques are applied to extract the critical object features including target location and orientation. Two prediction fields anticipate the objects' locations and orientations in the upcoming frame after receiving excitatory and inhibitory inputs from the input fields in a feed-forward architecture. This information is used in the data association and labeling process. We tested the proposed algorithm on a zebrafish larvae segmentation and tracking dataset and an ant-tracking dataset containing non-rigid objects with spiky movements and frequently occurring occlusions. The results showed a significant improvement in tracking metrics compared to state-of-the-art algorithms.

Survival Analysis in Cognitively Normal Subjects and in Patients with Mild Cognitive Impairment Using a Proportional Hazards Model with Extreme Gradient Boosting Regression.

BACKGROUND: Evaluating the risk of Alzheimer's disease (AD) in cognitively normal (CN) and patients with mild cognitive impairment (MCI) is extremely important. While MCI-to-AD progression risk has been studied extensively, few studies estimate CN-to-MCI conversion risk. The Cox proportional hazards (PH), a widely used survival analysis model, assumes a linear predictor-risk relationship. Generalizing the PH model to more complex predictor-risk relationships may increase risk estimation accuracy. OBJECTIVE: The aim of this study was to develop a PH model using an Xgboost regressor, based on demographic, genetic, neuropsychiatric, and neuroimaging predictors to estimate risk of AD in patients with MCI, and the risk of MCI in CN subjects. METHODS: We replaced the Cox PH linear model with an Xgboost regressor to capture complex interactions between predictors, and non-linear predictor-risk associations. We endeavored to limit model inputs to noninvasive and more widely available predictors in order to facilitate future applicability in a wider setting. RESULTS: In MCI-to-AD (n = 882), the Xgboost model achieved a concordance index (C-index) of 84.5%. When the model was used for MCI risk prediction in CN (n = 100) individuals, the C-index was 73.3%. In both applications, the C-index was statistically significantly higher in the Xgboost in comparison to the Cox PH model. CONCLUSION: Using non-linear regressors such as Xgboost improves AD dementia risk assessment in CN and MCI. It is possible to achieve reasonable risk stratification using predictors that are relatively low-cost in terms of time, invasiveness, and availability. Future strategies for improving AD dementia risk estimation are discussed.

Correction: ai-corona: Radiologist-assistant deep learning framework for COVID-19 diagnosis in chest CT scans.

[This corrects the article DOI: 10.1371/journal.pone.0250952.].

A machine learning based exploration of COVID-19 mortality risk.

Early prediction of patient mortality risks during a pandemic can decrease mortality by assuring efficient resource allocation and treatment planning. This study aimed to develop and compare prognosis prediction machine learning models based on invasive laboratory and noninvasive clinical and demographic data from patients' day of admission. Three Support Vector Machine (SVM) models were developed and compared using invasive, non-invasive, and both groups. The results suggested that non-invasive features could provide mortality predictions that are similar to the invasive and roughly on par with the joint model. Feature inspection results from SVM-RFE and sparsity analysis displayed that, compared with the invasive model, the non-invasive model can provide better performances with a fewer number of features, pointing to the presence of high predictive information contents in several non-invasive features, including SPO2, age, and cardiovascular disorders. Furthermore, while the invasive model was able to provide better mortality predictions for the imminent future, non-invasive features displayed better performance for more distant expiration intervals. Early mortality prediction using non-invasive models can give us insights as to where and with whom to intervene. Combined with novel technologies, such as wireless wearable devices, these models can create powerful frameworks for various medical assignments and patient triage.

ai-corona: Radiologist-assistant deep learning framework for COVID-19 diagnosis in chest CT scans.

The development of medical assisting tools based on artificial intelligence advances is essential in the global fight against COVID-19 outbreak and the future of medical systems. In this study, we introduce ai-corona, a radiologist-assistant deep learning framework for COVID-19 infection diagnosis using chest CT scans. Our framework incorporates an EfficientNetB3-based feature extractor. We employed three datasets; the CC-CCII set, the MasihDaneshvari Hospital (MDH) cohort, and the MosMedData cohort. Overall, these datasets constitute 7184 scans from 5693 subjects and include the COVID-19, non-COVID abnormal (NCA), common pneumonia (CP), non-pneumonia, and Normal classes. We evaluate ai-corona on test sets from the CC-CCII set, MDH cohort, and the entirety of the MosMedData cohort, for which it gained AUC scores of 0.997, 0.989, and 0.954, respectively. Our results indicates ai-corona outperforms all the alternative models. Lastly, our framework's diagnosis capabilities were evaluated as assistant to several experts. Accordingly, We observed an increase in both speed and accuracy of expert diagnosis when incorporating ai-corona's assistance.

Effectiveness of "rescue saccades" on the accuracy of tracking multiple moving targets: An eye-tracking study on the effects of target occlusions.

Occlusion is one of the main challenges in tracking multiple moving objects. In almost all real-world scenarios, a moving object or a stationary obstacle occludes targets partially or completely for a short or long time during their movement. A previous study (Zelinsky & Todor, 2010) reported that subjects make timely saccades toward the object in danger of being occluded. Observers make these so-called "rescue saccades" to prevent target swapping. In this study, we examined whether these saccades are helpful. To this aim, we used as the stimuli recorded videos from natural movement of zebrafish larvae swimming freely in a circular container. We considered two main types of occlusion: object-object occlusions that naturally exist in the videos, and object-occluder occlusions created by adding a stationary doughnut-shape occluder in some videos. Four different scenarios were studied: (1) no occlusions, (2) only object-object occlusions, (3) only object-occluder occlusion, or (4) both object-object and object-occluder occlusions. For each condition, two set sizes (two and four) were applied. Participants' eye movements were recorded during tracking, and rescue saccades were extracted afterward. The results showed that rescue saccades are helpful in handling object-object occlusions but had no reliable effect on tracking through object-occluder occlusions. The presence of occlusions generally increased visual sampling of the scenes; nevertheless, tracking accuracy declined due to occlusion.

Reward uncertainty asymmetrically affects information transmission within the monkey fronto-parietal network.

A central hypothesis in research on executive function is that controlled information processing is costly and is allocated according to the behavioral benefits it brings. However, while computational theories predict that the benefits of new information depend on prior uncertainty, the cellular effects of uncertainty on the executive network are incompletely understood. Using simultaneous recordings in monkeys, we describe several mechanisms by which the fronto-parietal network reacts to uncertainty. We show that the variance of expected rewards, independently of the value of the rewards, was encoded in single neuron and population spiking activity and local field potential (LFP) oscillations, and, importantly, asymmetrically affected fronto-parietal information transmission (measured through the coherence between spikes and LFPs). Higher uncertainty selectively enhanced information transmission from the parietal to the frontal lobe and suppressed it in the opposite direction, consistent with Bayesian principles that prioritize sensory information according to a decision maker's prior uncertainty.

Multiple-target tracking in human and machine vision.

Humans are able to track multiple objects at any given time in their daily activities-for example, we can drive a car while monitoring obstacles, pedestrians, and other vehicles. Several past studies have examined how humans track targets simultaneously and what underlying behavioral and neural mechanisms they use. At the same time, computer-vision researchers have proposed different algorithms to track multiple targets automatically. These algorithms are useful for video surveillance, team-sport analysis, video analysis, video summarization, and human-computer interaction. Although there are several efficient biologically inspired algorithms in artificial intelligence, the human multiple-target tracking (MTT) ability is rarely imitated in computer-vision algorithms. In this paper, we review MTT studies in neuroscience and biologically inspired MTT methods in computer vision and discuss the ways in which they can be seen as complementary.

Encoding Pleasant and Unpleasant Expression of the Architectural Window Shapes: An ERP Study.

The evaluation of building facades is one of the most important elements in built environments for helping architects and professionals to develop future designs. The form or shape of windows in building facades has direct impacts on perceivers' affective state and emotions. To understand the impacts of geometric windows on the subject's feedback and cortical activity, psychophysics experiments and electroencephalogram (EEG) recordings were measured from the participants. Our behavioral results show a distinguished categorization of the window shapes as pleasant and unpleasant stimuli. The rectangular, square, circular and semi-circular arch were determined as the pleasant window shapes, while the triangular and triangular arch window shapes were distinguished as unpleasant. Furthermore, event-related potential (ERP) components (N1, P2 and P3) were investigated to determine the influence of window shapes on the local brain activity. To measure reliable cortical responses, a Butterworth notch filter (50 Hz), band pass filter (0.1-60 Hz) and ADJUST filter were employed to remove the artifacts. The electrophysiological results show increased activity for the unpleasant in comparison to the pleasant windows (p < 0.05, Rank-Sum test) in both frontal (for P2 component) and posterio-occipital (ERP amplitudes; the N1 through to the P3 peak) channels. The ERP amplitudes of the right hemisphere were significantly larger than in the left hemisphere, not only in response to the unpleasant (p < 0.001) but also to the pleasant window stimuli (p < 0.001, Signed-Rank test). However, the unpleasant stimuli evoked significantly larger ERP amplitude than the pleasant stimuli. Moreover, the significant ERPP2 amplitude was more distinguished for unpleasant (p = 0.01, Signed-Rank test) than pleasant windows (p = 0.01, Rank-Sum test) between frontal and central cortical lobes. Overall, our behavioral and electrophysiological studies demonstrate a distinguished categorization of pleasant and unpleasant window shapes and more significant ERP modulations in the right than left hemisphere for unpleasant windows compared to pleasant ones.

Multifractal detrended fluctuation analysis of continuous neural time series in primate visual cortex.

BACKGROUND: Local field potential (LFP) recordings have become an important tool to study the activity of populations of neurons. The functional activity of LFPs is usually compared with the activity of neighboring single spike neurons with sampling rates much higher than those of the continuous field potential channel (5 kHz). However, comparison of these signals generated with the lower sampling rate technique is important. NEW METHOD: In this study, we provide an analysis of extracellular field potential time series using the sophisticated nonlinear multifractal detrended fluctuation analysis (MF-DFA). Using the MF-DFA, we demonstrate that the integral of the singularity spectrum is a powerful new method to measure the response tuning of spikes in the continuous field potential channel. RESULTS: Results show that the spikes in the continuous channel at frequency ranges above the LFP component signals were consistently tuned similar to those in the spike channel. Our results also show that using a low-pass filter (<250 Hz), which is commonly applied as a preprocessing step to insulate LFPs from spikes, significantly influences the nonlinearity of the multifractal time series. COMPARISON WITH EXISTING METHODS AND CONCLUSIONS: Our approach for inferring the tuning curve of spiking activity from the continuous channel has some advantages compared to conventional methods such as spike trains. The MF-DFA does not require any preprocessing of the raw signal data and makes no assumptions about the time series characteristics. This method is robust and can be applied to short time series of continuous raw signals.

Cortical Balance Between ON and OFF Visual Responses Is Modulated by the Spatial Properties of the Visual Stimulus.

The primary visual cortex of carnivores and primates is dominated by the OFF visual pathway and responds more strongly to dark than light stimuli. Here, we demonstrate that this cortical OFF dominance is modulated by the size and spatial frequency of the stimulus in awake primates and we uncover a main neuronal mechanism underlying this modulation. We show that large grating patterns with low spatial frequencies drive five times more OFF-dominated than ON-dominated neurons, but this pronounced cortical OFF dominance is strongly reduced when the grating size decreases and the spatial frequency increases, as when the stimulus moves away from the observer. We demonstrate that the reduction in cortical OFF dominance is not caused by a selective reduction of visual responses in OFF-dominated neurons but by a change in the ON/OFF response balance of neurons with diverse receptive field properties that can be ON or OFF dominated, simple, or complex. We conclude that cortical OFF dominance is continuously adjusted by a neuronal mechanism that modulates ON/OFF response balance in multiple cortical neurons when the spatial properties of the visual stimulus change with viewing distance and/or optical blur.