Meningioma brain tumor detection and classification using hybrid CNN method and RIDGELET transform.

The detection of meningioma tumors is the most crucial task compared with other tumors because of their lower pixel intensity. Modern medical platforms require a fully automated system for meningioma detection. Hence, this study proposes a novel and highly efficient hybrid Convolutional neural network (HCNN) classifier to distinguish meningioma brain images from non-meningioma brain images. The HCNN classification technique consists of the Ridgelet transform, feature computations, classifier module, and segmentation algorithm. Pixel stability during the decomposition process was improved by the Ridgelet transform, and the features were computed from the coefficient of the Ridgelet. These features were classified using the HCNN classification approach, and tumor pixels were detected using the segmentation algorithm. The experimental results were analyzed for meningioma tumor images by applying the proposed method to the BRATS 2019 and Nanfang dataset. The proposed HCNN-based meningioma detection system achieved 99.31% sensitivity, 99.37% specificity, and 99.24% segmentation accuracy for the BRATS 2019 dataset. The proposed HCNN technique achieved99.35% sensitivity, 99.22% specificity, and 99.04% segmentation accuracy on brain Magnetic Resonance Imaging (MRI) in the Nanfang dataset. The proposed system obtains 99.81% classification accuracy, 99.2% sensitivity, 99.7% specificity and 99.8% segmentation accuracy on BRATS 2022 dataset. The experimental results of the proposed HCNN algorithm were compared with those of the state-of-the-art meningioma detection algorithms in this study.

Lung_PAYNet: a pyramidal attention based deep learning network for lung nodule segmentation.

Accurate and reliable lung nodule segmentation in computed tomography (CT) images is required for early diagnosis of lung cancer. Some of the difficulties in detecting lung nodules include the various types and shapes of lung nodules, lung nodules near other lung structures, and similar visual aspects. This study proposes a new model named Lung_PAYNet, a pyramidal attention-based architecture, for improved lung nodule segmentation in low-dose CT images. In this architecture, the encoder and decoder are designed using an inverted residual block and swish activation function. It also employs a feature pyramid attention network between the encoder and decoder to extract exact dense features for pixel classification. The proposed architecture was compared to the existing UNet architecture, and the proposed methodology yielded significant results. The proposed model was comprehensively trained and validated using the LIDC-IDRI dataset available in the public domain. The experimental results revealed that the Lung_PAYNet delivered remarkable segmentation with a Dice similarity coefficient of 95.7%, mIOU of 91.75%, sensitivity of 92.57%, and precision of 96.75%.

Mood-Driven Colorization of Virtual Indoor Scenes.

One of the challenging tasks in virtual scene design for Virtual Reality (VR) is causing it to invoke a particular mood in viewers. The subjective nature of moods brings uncertainty to the purpose. We propose a novel approach to automatic adjustment of the colors of textures for objects in a virtual indoor scene, enabling it to match a target mood. A dataset of 25,000 images, including building/home interiors, was used to train a classifier with the features extracted via deep learning. It contributes to an optimization process that colorizes virtual scenes automatically according to the target mood. Our approach was tested on four different indoor scenes, and we conducted a user study demonstrating its efficacy through statistical analysis with the focus on the impact of the scenes experienced with a VR headset.

Eye movement control during visual pursuit in Parkinson's disease.

BACKGROUND: Prior studies of oculomotor function in Parkinson's disease (PD) have either focused on saccades without considering smooth pursuit, or tested smooth pursuit while excluding saccades. The present study investigated the control of saccadic eye movements during pursuit tasksand assessed the quality of binocular coordinationas potential sensitive markers of PD. METHODS: Observers fixated on a central cross while a target moved toward it. Once the target reached the fixation cross, observers began to pursue the moving target. To further investigate binocular coordination, the moving target was presented on both eyes (binocular condition), or on one eye only (dichoptic condition). RESULTS: The PD group made more saccades than age-matched normal control adults (NC) both during fixation and pursuit. The difference between left and right gaze positions increased over time during the pursuit period for PD but not for NC. The findings were not related to age, as NC and young-adult control group (YC) performed similarly on most of the eye movement measures, and were not correlated with classical measures of PD severity (e.g., Unified Parkinson's Disease Rating Scale (UPDRS) score). DISCUSSION: Our results suggest that PD may be associated with impairment not only in saccade inhibition, but also in binocular coordination during pursuit, and these aspects of dysfunction may be useful in PD diagnosis or tracking of disease course.

Clinical, Social, and Neuropsychological Dimensions of the Intersection of Addiction and Criminality.

To examine the social cognitive processes underlying the relationship of addiction and criminality, we administered the Addiction Severity Index-CF (ASI-CF) and the Iowa Gambling Task (IGT) to 35 participants (11 women) who had been released recently from jail or prison. ASI-CF revealed highest lifetime drug use for alcohol, followed by cannabis, cocaine, and heroin, with an average of 42 lifetime arrests in this ex-offender sample. The men and the women showed similar psychiatric histories marked by depression and anxiety, but the women had more lifetime problems with thinking than did the men, who had higher lifetime problems with hallucinations. On the IGT, participants showed evidence of reward-learning across the initial three blocks of 20 trials, but their performance declined over the last 40 trials, suggesting a failure to sustain gains: that is, to learn from feedback in deciding among advantageous and disadvantageous decks of cards. These deficits in motivated decision-making were moderated by current social and psychological factors, as assessed by ASI-CF. These results are discussed in regard to how disturbances in social cognitive processes may underlie the relationship of addiction and criminality.

Automatic Optimization of Wayfinding Design.

Wayfinding signs play an important role in guiding users to navigate in a virtual environment and in helping pedestrians to find their ways in a real-world architectural site. Conventionally, the wayfinding design of a virtual environment is created manually, so as the wayfinding design of a real-world architectural site. The many possible navigation scenarios, as well as the interplay between signs and human navigation, can make the manual design process overwhelming and non-trivial. As a result, creating a wayfinding design for a typical layout can take months to several years. In this paper, we introduce the Way to Go! approach for automatically generating a wayfinding design for a given layout. The designer simply has to specify some navigation scenarios; our approach will automatically generate an optimized wayfinding design with signs properly placed considering human agents' visibility and possibility of making mistakes during a navigation. We demonstrate the effectiveness of our approach in generating wayfinding designs for different layouts such as a train station, a downtown and a canyon. We evaluate our results by comparing different wayfinding designs and show that our optimized wayfinding design can guide pedestrians to their destinations effectively and efficiently. Our approach can also help the designer visualize the accessibility of a destination from different locations, and correct any "blind zone" with additional signs.

Saccadic Adaptation Alters the Attentional Field.

It is currently unknown whether changes to the oculomotor system can induce changes to the distribution of spatial attention around a fixated target. Previous studies have used perceptual performance tasks to show that adaptation of saccadic eye movements affects dynamic properties of visual attention, in particular, attentional shifts to a cued location. In this study, we examined the effects of saccadic adaptation on the static distribution of visual attention around fixation (attentional field). We used the classic double step adaptation procedure and a flanker task to test for differences in the attentional field after forward and backward adaptation. Reaction time (RT) measures revealed that the shape of the attentional field changed significantly after backward adaptation as shown through altered interference from distracters at different eccentricities but not after forward adaptation. This finding reveals that modification of saccadic amplitudes can affect metrics of not only dynamic properties of attention but also its static properties. A major implication is that the neural mechanisms underlying fundamental selection mechanisms and the oculomotor system can reweight each other.

Is Reading Impairment Associated with Enhanced Holistic Processing in Comparative Visual Search?

This study explores a proposition that individuals with dyslexia develop enhanced peripheral vision to process visual-spatial information holistically. Participants included 18 individuals diagnosed with dyslexia and 18 who were not. The experiment used a comparative visual search design consisting of two blocks of 72 trials. Each trial presented two halves of the display each comprising three kinds of shapes in three colours to be compared side-by-side. Participants performed a conjunctive search to ascertain whether the two halves were identical. In the first block, participants were provided no instruction regarding the visual-spatial processing strategy they were to employ. In the second block, participants were instructed to use a holistic processing strategy-to defocus their attention and perform the comparison by examining the whole screen at once. The results did not support the hypothesis associating dyslexia with talents for holistic visual processing. Using holistic processing strategy, both groups scored lower in accuracy and reacted faster, compared to the first block. Impaired readers consistently reacted more slowly and did not exhibit enhanced accuracy. Given the extant evidence of strengths for holistic visual processing in impaired readers, these findings are important because they suggest such strengths may be task dependent. Copyright © 2016 John Wiley & Sons, Ltd.

Working memory load predicts visual search efficiency: Evidence from a novel pupillary response paradigm.

An observer's pupil dilates and constricts in response to variables such as ambient and focal luminance, cognitive effort, the emotional stimulus content, and working memory load. The pupil's memory load response is of particular interest, as it might be used for estimating observers' memory load while they are performing a complex task, without adding an interruptive and confounding memory test to the protocol. One important task in which working memory's involvement is still being debated is visual search, and indeed a previous experiment by Porter, Troscianko, and Gilchrist (Quarterly Journal of Experimental Psychology, 60, 211-229, 2007) analyzed observers' pupil sizes during search to study this issue. These authors found that pupil size increased over the course of the search, and they attributed this finding to accumulating working memory load. However, since the pupil response is slow and does not depend on memory load alone, this conclusion is rather speculative. In the present study, we estimated working memory load in visual search during the presentation of intermittent fixation screens, thought to induce a low, stable level of arousal and cognitive effort. Using standard visual search and control tasks, we showed that this paradigm reduces the influence of non-memory-related factors on pupil size. Furthermore, we found an early increase in working memory load to be associated with more efficient search, indicating a significant role of working memory in the search process.

Accurate refinement of docked protein complexes using evolutionary information and deep learning.

One of the major challenges for protein docking methods is to accurately discriminate native-like structures from false positives. Docking methods are often inaccurate and the results have to be refined and re-ranked to obtain native-like complexes and remove outliers. In a previous work, we introduced AccuRefiner, a machine learning based tool for refining protein-protein complexes. Given a docked complex, the refinement tool produces a small set of refined versions of the input complex, with lower root-mean-square-deviation (RMSD) of atomic positions with respect to the native structure. The method employs a unique ranking tool that accurately predicts the RMSD of docked complexes with respect to the native structure. In this work, we use a deep learning network with a similar set of features and five layers. We show that a properly trained deep learning network can accurately predict the RMSD of a docked complex with 1.40 Å error margin on average, by approximating the complex relationship between a wide set of scoring function terms and the RMSD of a docked structure. The network was trained on 35000 unbound docking complexes generated by RosettaDock. We tested our method on 25 different putative docked complexes produced also by RosettaDock for five proteins that were not included in the training data. The results demonstrate that the high accuracy of the ranking tool enables AccuRefiner to consistently choose the refinement candidates with lower RMSD values compared to the coarsely docked input structures.

Accurate Prediction of Docked Protein Structure Similarity.

One of the major challenges for protein-protein docking methods is to accurately discriminate nativelike structures. The protein docking community agrees on the existence of a relationship between various favorable intermolecular interactions (e.g. Van der Waals, electrostatic, desolvation forces, etc.) and the similarity of a conformation to its native structure. Different docking algorithms often formulate this relationship as a weighted sum of selected terms and calibrate their weights against specific training data to evaluate and rank candidate structures. However, the exact form of this relationship is unknown and the accuracy of such methods is impaired by the pervasiveness of false positives. Unlike the conventional scoring functions, we propose a novel machine learning approach that not only ranks the candidate structures relative to each other but also indicates how similar each candidate is to the native conformation. We trained the AccuRMSD neural network with an extensive dataset using the back-propagation learning algorithm. Our method achieved predicting RMSDs of unbound docked complexes with 0.4Å error margin.

The roles of scene gist and spatial dependency among objects in the semantic guidance of attention in real-world scenes.

A previous study (Vision Research 51 (2011) 1192-1205) found evidence for semantic guidance of visual attention during the inspection of real-world scenes, i.e., an influence of semantic relationships among scene objects on overt shifts of attention. In particular, the results revealed an observer bias toward gaze transitions between semantically similar objects. However, this effect is not necessarily indicative of semantic processing of individual objects but may be mediated by knowledge of the scene gist, which does not require object recognition, or by known spatial dependency among objects. To examine the mechanisms underlying semantic guidance, in the present study, participants were asked to view a series of displays with the scene gist excluded and spatial dependency varied. Our results show that spatial dependency among objects seems to be sufficient to induce semantic guidance. Scene gist, on the other hand, does not seem to affect how observers use semantic information to guide attention while viewing natural scenes. Extracting semantic information mainly based on spatial dependency may be an efficient strategy of the visual system that only adds little cognitive load to the viewing task.

Salient stimulus attracts focus of peri-saccadic mislocalization.

Visual localization during saccadic eye movements is prone to error. Flashes shortly before and after the onset of saccades are usually perceived to shift towards the saccade target, creating a "compression" pattern. Typically, the saccade landing point coincides with a salient saccade target. We investigated whether the mislocalization focus follows the actual saccade landing point or a salient stimulus. Subjects made saccades to either a target or a memorized location without target. In some conditions, another salient marker was presented between the initial fixation and the saccade landing point. The experiments were conducted on both black and picture backgrounds. The results show that: (a) when a saccade target or a marker (spatially separated from the saccade landing point) was present, the compression pattern of mislocalization was significantly stronger than in conditions without them, for both black and picture background conditions, and (b) the mislocalization focus tended towards the salient stimulus regardless of whether it was the saccade target or the marker. Our results suggest that a salient stimulus presented in the scene may have an attracting effect and therefore contribute to the non-uniformity of saccadic mislocalization of a probing flash.

Guidance of visual attention by semantic information in real-world scenes.

Recent research on attentional guidance in real-world scenes has focused on object recognition within the context of a scene. This approach has been valuable for determining some factors that drive the allocation of visual attention and determine visual selection. This article provides a review of experimental work on how different components of context, especially semantic information, affect attentional deployment. We review work from the areas of object recognition, scene perception, and visual search, highlighting recent studies examining semantic structure in real-world scenes. A better understanding on how humans parse scene representations will not only improve current models of visual attention but also advance next-generation computer vision systems and human-computer interfaces.

Predicting raters' transparency judgments of English and Chinese morphological constituents using latent semantic analysis.

The morphological constituents of English compounds (e.g., "butter" and "fly" for "butterfly") and two-character Chinese compounds may differ in meaning from the whole word. Subjective differences and ambiguity of transparency make judgments difficult, and a computational alternative based on a general model might be a way to average across subjective differences. In the present study, we propose two approaches based on latent semantic analysis (Landauer & Dumais in Psychological Review 104:211-240, 1997): Model 1 compares the semantic similarity between a compound word and each of its constituents, and Model 2 derives the dominant meaning of a constituent from a clustering analysis of morphological family members (e.g., "butterfingers" or "buttermilk" for "butter"). The proposed models successfully predicted participants' transparency ratings, and we recommend that experimenters use Model 1 for English compounds and Model 2 for Chinese compounds, on the basis of differences in raters' morphological processing in the different writing systems. The dominance of lexical meaning, semantic transparency, and the average similarity between all pairs within a morphological family are provided, and practical applications for future studies are discussed.

E-readers are more effective than paper for some with dyslexia.

E-readers are fast rivaling print as a dominant method for reading. Because they offer accessibility options that are impossible in print, they are potentially beneficial for those with impairments, such as dyslexia. Yet, little is known about how the use of these devices influences reading in those who struggle. Here, we observe reading comprehension and speed in 103 high school students with dyslexia. Reading on paper was compared with reading on a small handheld e-reader device, formatted to display few words per line. We found that use of the device significantly improved speed and comprehension, when compared with traditional presentations on paper for specific subsets of these individuals: Those who struggled most with phoneme decoding or efficient sight word reading read more rapidly using the device, and those with limited VA Spans gained in comprehension. Prior eye tracking studies demonstrated that short lines facilitate reading in dyslexia, suggesting that it is the use of short lines (and not the device per se) that leads to the observed benefits. We propose that these findings may be understood as a consequence of visual attention deficits, in some with dyslexia, that make it difficult to allocate attention to uncrowded text near fixation, as the gaze advances during reading. Short lines ameliorate this by guiding attention to the uncrowded span.

Shorter lines facilitate reading in those who struggle.

People with dyslexia, who ordinarily struggle to read, sometimes remark that reading is easier when e-readers are used. Here, we used eye tracking to observe high school students with dyslexia as they read using these devices. Among the factors investigated, we found that reading using a small device resulted in substantial benefits, improving reading speeds by 27%, reducing the number of fixations by 11%, and importantly, reducing the number of regressive saccades by more than a factor of 2, with no cost to comprehension. Given that an expected trade-off between horizontal and vertical regression was not observed when line lengths were altered, we speculate that these effects occur because sluggish attention spreads perception to the left as the gaze shifts during reading. Short lines eliminate crowded text to the left, reducing regression. The effects of attention modulation by the hand, and of increased letter spacing to reduce crowding, were also found to modulate the oculomotor dynamics in reading, but whether these factors resulted in benefits or costs depended on characteristics, such as visual attention span, that varied within our sample.

The effects of task difficulty on visual search strategy in virtual 3D displays.

Analyzing the factors that determine our choice of visual search strategy may shed light on visual behavior in everyday situations. Previous results suggest that increasing task difficulty leads to more systematic search paths. Here we analyze observers' eye movements in an "easy" conjunction search task and a "difficult" shape search task to study visual search strategies in stereoscopic search displays with virtual depth induced by binocular disparity. Standard eye-movement variables, such as fixation duration and initial saccade latency, as well as new measures proposed here, such as saccadic step size, relative saccadic selectivity, and x-y target distance, revealed systematic effects on search dynamics in the horizontal-vertical plane throughout the search process. We found that in the "easy" task, observers start with the processing of display items in the display center immediately after stimulus onset and subsequently move their gaze outwards, guided by extrafoveally perceived stimulus color. In contrast, the "difficult" task induced an initial gaze shift to the upper-left display corner, followed by a systematic left-right and top-down search process. The only consistent depth effect was a trend of initial saccades in the easy task with smallest displays to the items closest to the observer. The results demonstrate the utility of eye-movement analysis for understanding search strategies and provide a first step toward studying search strategies in actual 3D scenarios.

Using singular value decomposition to investigate degraded Chinese character recognition: evidence from eye movements during reading.

Previous research indicates that removing initial strokes from Chinese characters makes them harder to read than removing final or internal ones. In the present study, we examined the contribution of important components to character configuration via singular value decomposition. The results indicated that when the least important segments, which did not seriously alter the configuration (contour) of the character, were deleted, subjects read as fast as when no segments were deleted. When the most important segments, which are located in the left side of a character and written first, were deleted, reading speed was greatly slowed. These results suggest that singular value decomposition, which has no information about stroke writing order, can identify the most important strokes for Chinese character identification. Furthermore, they also suggest that contour may be correlated with stroke writing order.

The effects of circadian phase, time awake, and imposed sleep restriction on performing complex visual tasks: evidence from comparative visual search.

Cognitive performance not only differs between individuals, but also varies within them, influenced by factors that include sleep-wakefulness and biological time of day (circadian phase). Previous studies have shown that both factors influence accuracy rather than the speed of performing a visual search task, which can be hazardous in safety-critical tasks such as air-traffic control or baggage screening. However, prior investigations used simple, brief search tasks requiring little use of working memory. In order to study the effects of circadian phase, time awake, and chronic sleep restriction on the more realistic scenario of longer tasks requiring the sustained interaction of visual working memory and attentional control, the present study employed two comparative visual search tasks. In these tasks, participants had to detect a mismatch between two otherwise identical object distributions, with one of the tasks (mirror task) requiring an additional mental image transformation. Time awake and circadian phase both had significant influences on the speed, but not the accuracy of task performance. Over the course of three weeks of chronic sleep restriction, speed but not accuracy of task performance was impacted. The results suggest measures for safer performance of important tasks and point out the importance of minimizing the impact of circadian phase and sleep-wake history in laboratory vision experiments.