Robust detection and refinement of saliency identification.

Salient object detection is an increasingly popular topic in the computer vision field, particularly for images with complex backgrounds and diverse object parts. Background information is an essential factor in detecting salient objects. This paper suggests a robust and effective methodology for salient object detection. This method involves two main stages. The first stage is to produce a saliency detection map based on the dense and sparse reconstruction of image regions using a refined background dictionary. The refined background dictionary uses a boundary conductivity measurement to exclude salient object regions near the image's boundary from a background dictionary. In the second stage, the CascadePSP network is integrated to refine and correct the local boundaries of the saliency mask to highlight saliency objects more uniformly. Using six evaluation indexes, experimental outcomes conducted on three datasets show that the proposed approach performs effectively compared to the state-of-the-art methods in salient object detection, particularly in identifying the challenging salient objects located near the image's boundary. These results demonstrate the potential of the proposed framework for various computer vision applications.

Identification of Differentially Expressed Genes in Human Colorectal Cancer Using RNASeq Data Validated on the Molecular Level with Real-Time PCR.

Colorectal cancer (CRC) is a prevalent cancer with high morbidity and mortality rates worldwide. Late diagnosis is a significant contributor to low survival rates in a minority of cases. The study aimed to perform a robust pipeline using integrated bioinformatics tools that will enable us to identify potential diagnostic and prognostic biomarkers for early detection of CRC by exploring differentially expressed genes (DEGs). In addition to, testing the capability of replacing chemotherapy with plant extract in CRC treatment by validating it using real-time PCR. RNA-seq data from cancerous and adjacent normal tissues were pre-processed and analyzed using various tools such as FastQC, Kallisto, DESeq@ R package, g:Profiler, GNEMANIA-CytoScape and CytoHubba, resulting in the identification of 1641 DEGs enriched in various signaling routes. MMP7, TCF21, and VEGFD were found to be promising diagnostic biomarkers for CRC. An in vitro experiment was conducted to examine the potential anticancer properties of 5-fluorouracile, Withania somnifera extract, and their combination. The extract was found to exhibit a positive trend in gene expression and potential therapeutic value by targeting the three genes; however, further trials are required to regulate the methylation promoter. Molecular docking tests supported the findings by revealing a stable ligand-receptor complex. In conclusion, the study's analysis workflow is precise and robust in identifying DEGs in CRC that may serve as biomarkers for diagnosis and treatment. Additionally, the identified DEGs can be used in future research with larger sample sizes to analyze CRC survival.

Human cornea thermo-viscoelastic behavior modelling using standard linear solid model.

BACKGROUND: Corneal biomechanics is of great interest to researchers recently. Clinical findings relate them to corneal diseases and to outcomes of refractive surgery. To have a solid understanding of corneal diseases' progression, it is important to understand corneal biomechanics. Also, they are essential for better explaining outcomes of refractive surgeries and their undesired consequences. There is a difficulty for studying corneal biomechanics in-vivo and multiple limitations arise for ex-vivo studies. Hence mathematical modelling is considered as a proper solution to overcome such obstacles. Mathematical modelling of cornea in-vivo allows studying corneal viscoelasticity with taking into consideration all boundary conditions existing in real in-vivo situation. METHODS: Three mathematical models are used to simulate corneal viscoelasticity and thermal behavior in two different loading situations: constant and transient loading. Two models of the three are used for viscoelasticity simulation which are Kelvin-Voigt and standard linear solid models. Also, temperature rise due to the ultrasound pressure push is calculated using bioheat transfer model for both the axial direction and as a 2D spatial map using the third model (standard linear solid model). RESULTS: Viscoelasticity simulation results show that standard linear solid model is efficient for describing the viscoelastic behavior of human cornea in both loading conditions. Results show also that the deformation amplitude obtained from standard linear solid model is more reasonable for corneal soft-tissue deformation with respect to corresponding clinical findings than that obtained from Kelvin-Voigt model. Thermal behavior results estimated corneal temperature rise to be roughly 0.2 °C, which conforms with FDA regulations for soft tissue safety. CONCLUSION: Standard Linear Solid (SLS) model is better describing the human corneal behavior in response to constant and transient load more efficiently. Temperature rise (TR) for the corneal tissue of about 0.2 °C is conforming with FDA regulations and even less than the FDA regulations for soft tissue safety.

A hybrid deep learning approach for COVID-19 detection based on genomic image processing techniques.

The coronavirus disease 2019 (COVID-19) pandemic has been spreading quickly, threatening the public health system. Consequently, positive COVID-19 cases must be rapidly detected and treated. Automatic detection systems are essential for controlling the COVID-19 pandemic. Molecular techniques and medical imaging scans are among the most effective approaches for detecting COVID-19. Although these approaches are crucial for controlling the COVID-19 pandemic, they have certain limitations. This study proposes an effective hybrid approach based on genomic image processing (GIP) techniques to rapidly detect COVID-19 while avoiding the limitations of traditional detection techniques, using whole and partial genome sequences of human coronavirus (HCoV) diseases. In this work, the GIP techniques convert the genome sequences of HCoVs into genomic grayscale images using a genomic image mapping technique known as the frequency chaos game representation. Then, the pre-trained convolution neural network, AlexNet, is used to extract deep features from these images using the last convolution (conv5) and second fully-connected (fc7) layers. The most significant features were obtained by removing the redundant ones using the ReliefF and least absolute shrinkage and selection operator (LASSO) algorithms. These features are then passed to two classifiers: decision trees and k-nearest neighbors (KNN). Results showed that extracting deep features from the fc7 layer, selecting the most significant features using the LASSO algorithm, and executing the classification process using the KNN classifier is the best hybrid approach. The proposed hybrid deep learning approach detected COVID-19, among other HCoV diseases, with 99.71% accuracy, 99.78% specificity, and 99.62% sensitivity.

Detection of Simulated Tactile Gratings by Electro-Static Friction Show a Dependency on Bar Width for Blind and Sighted Observers, and Preliminary Neural Correlates in Sighted Observers.

The three-dimensional micro-structure of physical surfaces produces frictional forces that provide sensory cues about properties of felt surfaces such as roughness. This tactile information activates somatosensory cortices, and frontal and temporal brain regions. Recent advances in haptic-feedback technologies allow the simulation of surface micro-structures via electro-static friction to produce touch sensations on otherwise flat screens. These sensations may benefit those with visual impairment or blindness. The primary aim of the current study was to test blind and sighted participants' perceptual sensitivity to simulated tactile gratings. A secondary aim was to explore which brain regions were involved in simulated touch to further understand the somatosensory brain network for touch. We used a haptic-feedback touchscreen which simulated tactile gratings using digitally manipulated electro-static friction. In Experiment 1, we compared blind and sighted participants' ability to detect the gratings by touch alone as a function of their spatial frequency (bar width) and intensity. Both blind and sighted participants showed high sensitivity to detect simulated tactile gratings, and their tactile sensitivity functions showed both linear and quadratic dependency on spatial frequency. In Experiment 2, using functional magnetic resonance imaging, we conducted a preliminary investigation to explore whether brain activation to physical vibrations correlated with blindfolded (but sighted) participants' performance with simulated tactile gratings outside the scanner. At the neural level, blindfolded (but sighted) participants' detection performance correlated with brain activation in bi-lateral supplementary motor cortex, left frontal cortex and right occipital cortex. Taken together with previous studies, these results suggest that there are similar perceptual and neural mechanisms for real and simulated touch sensations.

A scalable data transmission scheme for implantable optogenetic visual prostheses.

OBJECTIVE: This work described a video information processing scheme for optogenetic forms of visual cortical prosthetics. APPROACH: The architecture is designed to perform a processing sequence: Initially simplifying the scene, followed by a pragmatic visual encoding scheme which assumes that initially optical stimulation will be stimulating bulk neural tissue rather than driving individual phosphenes. We demonstrate an optical encoder, combined with what we called a zero-run length encoding (zRLE) video compression and decompression scheme-to wirelessly transfer information to an implantable unit in an efficient manner. In the final step, we have incorporated an even power distribution driver to prevent excessive power fluctuations in the optogenetic driving. SIGNIFICANCE: The key novelty in this work centres on the completeness of the scheme, the new zRLE compression algorithm and our even power distributor. MAIN RESULTS: Furthermore, although the paper focusses on the algorithm, we confirm that it can be implemented on real time portable processing hardware which we will use for our visual prosthetics.

Automated brain tumor segmentation from multi-slices FLAIR MRI images.

Brain tumors are considered to be a leading cause of cancer death among young people. Early diagnosis is thus essential for treatment. The brain segmentation process is still challenging due to complexity and variation of the tumor structure, intensity similarity between tumor tissues and normal brain tissues. In this paper, a fully automated and reliable brain tumor segmentation system is proposed. This system is able to detect range of slices from a volume that is likely to contain tumor in MRI images. An iterated k-means algorithm is used for the segmentation process in conjunction with a cluster validity index to select the optimal number of clusters. The proposed approach is evaluated using simulated and real MRI of human brain from multimodal brain tumor image segmentation benchmark (BRATS) organized by MICCAI 2012 challenge. Our results achieved average for Dice overlap and Jaccard index for complete tumor region of 91.96% and 98.31% respectively when testing a set of 77 volumes. This shows the robustness of the new technique for clinical routine use.

Review of Different Sequence Motif Finding Algorithms.

The DNA motif discovery is a primary step in many systems for studying gene function. Motif discovery plays a vital role in identification of Transcription Factor Binding Sites (TFBSs) that help in learning the mechanisms for regulation of gene expression. Over the past decades, different algorithms were used to design fast and accurate motif discovery tools. These algorithms are generally classified into consensus or probabilistic approaches that many of them are time-consuming and easily trapped in a local optimum. Nature-inspired algorithms and many of combinatorial algorithms are recently proposed to overcome these problems. This paper presents a general classification of motif discovery algorithms with new sub-categories that facilitate building a successful motif discovery algorithm. It also presents a summary of comparison between them.

A head mounted device stimulator for optogenetic retinal prosthesis.

OBJECTIVE: Our main objective is to demonstrate that compact high radiance gallium nitride displays can be used with conventional virtual reality optics to stimulate an optogenetic retina. Hence, we aim to introduce a non-invasive approach to restore vision for people with conditions such as retinitis pigmentosa where there is a remaining viable communication link between the retina and the visual cortex. APPROACH: We design and implement the headset using a high-density µLED matrix, Raspberry Pi, microcontroller from NXP and virtual reality lens. Then, a test platform is developed to evaluate the performance of the headset and the optical system. Furthermore, image simplification algorithms are used to simplify the scene to be sent to the retina. Moreover, in vivo evaluation of the genetically modified retina response at different light intensity is discussed to prove the reliability of the proposed system. MAIN RESULTS: We demonstrate that in keeping with regulatory guidance, the headset displays need to limit their luminance to 90 kcd m-2. We demonstrate an optical system with 5.75% efficiency which allows for 0.16 mW mm-2 irradiance on the retina within the regulatory guidance, but which is capable of an average peak irradiance of 1.35 mW mm-2. As this is lower than the commonly accepted threshold for channelrhodopsin-2, we demonstrate efficacy through an optical model of an eye onto a biological retina. SIGNIFICANCE: We demonstrate a fully functional 8100-pixel headset system including software/hardware which can operate on a standard consumer battery for periods exceeding a 24 h recharge cycle. The headset is capable of delivering enough light to stimulate the genetically modified retina cells and also keeping the amount of light below the regulation threshold for safety.

Extraspectral Imaging for Improving the Perceived Information Presented in Retinal Prosthesis.

Retinal prosthesis is steadily improving as a clinical treatment for blindness caused by retinitis pigmentosa. However, despite the continued exciting progress, the level of visual return is still very poor. It is also unlikely that those utilising these devices will stop being legally blind in the near future. Therefore, it is important to develop methods to maximise the transfer of useful information extracted from the visual scene. Such an approach can be achieved by digitally suppressing less important visual features and textures within the scene. The result can be interpreted as a cartoon-like image of the scene. Furthermore, utilising extravisual wavelengths such as infrared can be useful in the decision process to determine the optimal information to present. In this paper, we, therefore, present a processing methodology that utilises information extracted from the infrared spectrum to assist in the preprocessing of the visual image prior to conversion to retinal information. We demonstrate how this allows for enhanced recognition and how it could be implemented for optogenetic forms of retinal prosthesis. The new approach has been quantitatively evaluated on volunteers showing 112% enhancement in recognizing objects over normal approaches.

FPGA design for dual-spectrum Visual Scene Preparation in retinal prosthesis.

A method of Visual Scene Preparation for the patients suffering Retinitis Pigmentosa is implemented in hardware for the first time. The scene is captured with two cameras, one visible spectrum and one infra-red, in order to distinguish between the live and non-live objects. The live objects are subsequently emphasized in the output image, thus helping a patient to see the most significant detail with the healthy part of the retina. The implementation uses Verilog language and FPGA platform. A system prototype is analyzed and compared to MATLAB results.

Automatic synthesis of cine viability MRI images for evaluation of coronary heart disease.

Coronary heart disease (CHD) is the leading cause of death worldwide. Cardiac magnetic resonance imaging (MRI) is a valuable imaging modality, as it can noninvasively provide information about myocardial function, viability, and morphology. Viability delayed-enhancement (DE) images are acquired at a single timeframe while myocardial functional (tagged) images are acquired as a cine loop of timeframes throughout the cardiac cycle. In this work, we propose a method for estimating DE images at all timeframes in the cardiac cycle without additional scan time to show both viability and functional information in the same image. The method is based on generating a dense motion field of the heart from the acquired tagged images, and then applying the extracted field to the acquired DE image. The developed technique is accurate in generating cine DE images and providing simultaneous information about myocardial viability and wall motion for comprehensive patient evaluation and optimal treatment selection.

A processing platform for optoelectronic/optogenetic retinal prosthesis.

The field of retinal prosthesis has been steadily developing over the last two decades. Despite the many obstacles, clinical trials for electronic approaches are in progress and already demonstrating some success. Optogenetic/optoelectronic retinal prosthesis may prove to have even greater capabilities. Although resolutions are now moving beyond recognition of simple shapes, it will nevertheless be poor compared to normal vision. If we define the aim to be to return mobility and natural scene recognition to the patient, it is important to maximize the useful visual information we attempt to transfer. In this paper, we highlight a method to simplify the scene, perform spatial image compression, and then apply spike coding. We then show the potential for translation on standard consumer processors. The algorithms are applicable to all forms of visual prosthesis, but we particularly focus on optogenetic approaches.

Improved content aware scene retargeting for retinitis pigmentosa patients.

BACKGROUND: In this paper we present a novel scene retargeting technique to reduce the visual scene while maintaining the size of the key features. The algorithm is scalable to implementation onto portable devices, and thus, has potential for augmented reality systems to provide visual support for those with tunnel vision. We therefore test the efficacy of our algorithm on shrinking the visual scene into the remaining field of view for those patients. METHODS: Simple spatial compression of visual scenes makes objects appear further away. We have therefore developed an algorithm which removes low importance information, maintaining the size of the significant features. Previous approaches in this field have included seam carving, which removes low importance seams from the scene, and shrinkability which dynamically shrinks the scene according to a generated importance map. The former method causes significant artifacts and the latter is inefficient. In this work we have developed a new algorithm, combining the best aspects of both these two previous methods. In particular, our approach is to generate a shrinkability importance map using as seam based approach. We then use it to dynamically shrink the scene in similar fashion to the shrinkability method. Importantly, we have implemented it so that it can be used in real time without prior knowledge of future frames. RESULTS: We have evaluated and compared our algorithm to the seam carving and image shrinkability approaches from a content preservation perspective and a compression quality perspective. Also our technique has been evaluated and tested on a trial included 20 participants with simulated tunnel vision. Results show the robustness of our method at reducing scenes up to 50% with minimal distortion. We also demonstrate efficacy in its use for those with simulated tunnel vision of 22 degrees of field of view or less. CONCLUSIONS: Our approach allows us to perform content aware video resizing in real time using only information from previous frames to avoid jitter. Also our method has a great benefit over the ordinary resizing method and even over other image retargeting methods. We show that the benefit derived from this algorithm is significant to patients with fields of view 20° or less.

Designing and testing scene enhancement algorithms for patients with retina degenerative disorders.

BACKGROUND: Retina degenerative disorders represent the primary cause of blindness in UK and in the developed world. In particular, Age Related Macular Degeneration (AMD) and Retina Pigmentosa (RP) diseases are of interest to this study. We have therefore created new image processing algorithms for enhancing the visual scenes for them. METHODS: In this paper we present three novel image enhancement techniques aimed at enhancing the remaining visual information for patients suffering from retina dystrophies. Currently, the only effective way to test novel technology for visual enhancement is to undergo testing on large numbers of patients. To test our techniques, we have therefore built a retinal image processing model and compared the results to data from patient testing. In particular we focus on the ability of our image processing techniques to achieve improved face detection and enhanced edge perception. RESULTS: Results from our model are compared to actual data obtained from testing the performance of these algorithms on 27 patients with an average visual acuity of 0.63 and an average contrast sensitivity of 1.22. Results show that Tinted Reduced Outlined Nature (TRON) and Edge Overlaying algorithms are most beneficial for dynamic scenes such as motion detection. Image Cartoonization was most beneficial for spatial feature detection such as face detection. Patient's stated that they would most like to see Cartoonized images for use in daily life. CONCLUSIONS: Results obtained from our retinal model and from patients show that there is potential for these image processing techniques to improve visual function amongst the visually impaired community. In addition our methodology using face detection and efficiency of perceived edges in determining potential benefit derived from different image enhancement algorithms could also prove to be useful in quantitatively assessing algorithms in future studies.