2,939 results match your criteria gradient visual


A Knowledge Distillation Ensemble Framework for Predicting Short and Long-term Hospitalisation Outcomes from Electronic Health Records Data.

IEEE J Biomed Health Inform 2021 Jun 15;PP. Epub 2021 Jun 15.

The ability to perform accurate prognosis of patients is crucial for proactive clinical decision making, informed resource management and personalised care. Existing outcome prediction models suffer from a low recall of infrequent positive outcomes. We present a highly-scalable and robust machine learning framework to automatically predict adversity represented by mortality and ICU admission from time-series vital signs and laboratory results obtained within the first 24 hours of hospital admission. Read More

View Article and Full-Text PDF

Extensive cone-dependent spectral opponency within a discrete zone of the lateral geniculate nucleus supporting mouse color vision.

Curr Biol 2021 Jun 2. Epub 2021 Jun 2.

Centre for Biological Timing, Faculty of Biology, Medicine and Health, University of Manchester, Manchester M13 9PT, UK. Electronic address:

Color vision, originating with opponent processing of spectrally distinct photoreceptor signals, plays important roles in animal behavior. Surprisingly, however, comparatively little is understood about color processing in the brain, including in widely used laboratory mammals such as mice. The retinal gradient in S- and M-cone opsin (co-)expression has traditionally been considered an impediment to mouse color vision. Read More

View Article and Full-Text PDF

Development of a Web-Based Ensemble Machine Learning Application to Select the Optimal Size of Posterior Chamber Phakic Intraocular Lens.

Transl Vis Sci Technol 2021 May;10(6)

B&VIIT Eye Center, Seoul, South Korea.

Purpose: Selecting the optimal lens size by predicting the postoperative vault can reduce complications after implantation of an implantable collamer lens with a central-hole (ICL with KS-aquaport). We built a web-based machine learning application that incorporated clinical measurements to predict the postoperative ICL vault and select the optimal ICL size.

Methods: We applied the stacking ensemble technique based on eXtreme Gradient Boosting (XGBoost) and a light gradient boosting machine to pre-operative ocular data from two eye centers to predict the postoperative vault. Read More

View Article and Full-Text PDF

Data-driven beamforming technique to attenuate ballistocardiogram artefacts in electroencephalography-functional magnetic resonance imaging without detecting cardiac pulses in electrocardiography recordings.

Hum Brain Mapp 2021 Jun 8. Epub 2021 Jun 8.

Multimodal Functional Imaging Lab, Department of Physics and PERFORM Centre, Concordia University, Montréal, Québec, Canada.

Simultaneous recording of electroencephalography (EEG) and functional magnetic resonance imaging (fMRI) is a very promising non-invasive neuroimaging technique. However, EEG data obtained from the simultaneous EEG-fMRI are strongly influenced by MRI-related artefacts, namely gradient artefacts (GA) and ballistocardiogram (BCG) artefacts. When compared to the GA correction, the BCG correction is more challenging to remove due to its inherent variabilities and dynamic changes over time. Read More

View Article and Full-Text PDF

Variations in photoreceptor throughput to mouse visual cortex and the unique effects on tuning.

Sci Rep 2021 Jun 7;11(1):11937. Epub 2021 Jun 7.

Department of Psychology, University of Texas At Austin, 108 E. Dean Keeton, Austin, TX, 78712, USA.

Visual input to primary visual cortex (V1) depends on highly adaptive filtering in the retina. In turn, isolation of V1 computations requires experimental control of retinal adaptation to infer its spatio-temporal-chromatic output. Here, we measure the balance of input to mouse V1, in the anesthetized setup, from the three main photoreceptor opsins-M-opsin, S-opsin, and rhodopsin-as a function of two stimulus dimensions. Read More

View Article and Full-Text PDF

Quantifying groundwater flow variability in a poorly cemented fractured sandstone aquifer to inform in situ remediation.

J Contam Hydrol 2021 May 27;241:103838. Epub 2021 May 27.

G360 Institute for Groundwater Research, University of Guelph, Canada.

This study applies innovative methods to characterize and quantify the magnitude of groundwater flow in a fractured and variably cemented sandstone aquifer to inform an in-situ remediation strategy for trichloroethene (TCE) contamination. A modified active-distributed temperature sensing (A-DTS) approach in which fiber optic cables were permanently grouted in the borehole was used to quantify groundwater flow rates. Two additional tracer tests were conducted: 1) fluorescein tracer injection followed by rock coring and sampling for visual mapping and porewater analysis, and 2) deployment of passive flux meters in conventional monitoring wells to evaluate groundwater velocity and mass flux distributions. Read More

View Article and Full-Text PDF

A deep cascade of ensemble of dual domain networks with gradient-based T1 assistance and perceptual refinement for fast MRI reconstruction.

Comput Med Imaging Graph 2021 May 24;91:101942. Epub 2021 May 24.

Department of Electrical Engineering, Indian Institute of Technology Madras, Chennai, Tamil Nadu, India; Healthcare Technology Innovation Centre, Indian Institute of Technology Madras, Chennai, Tamil Nadu, India.

Deep learning networks have shown promising results in fast magnetic resonance imaging (MRI) reconstruction. In our work, we develop deep networks to further improve the quantitative and the perceptual quality of reconstruction. To begin with, we propose reconsynergynet (RSN), a network that combines the complementary benefits of independently operating on both the image and the Fourier domain. Read More

View Article and Full-Text PDF

Normative Data for Nonstrabismic Binocular Vision Parameters in African Schoolchildren.

Optom Vis Sci 2021 Jun;98(6):620-628

Department of Optometry and Vision Science, University of Cape Coast, Cape Coast, Ghana.

Significance: With reported population differences in parameters of nonstrabismic binocular vision, the present study investigated and reports normative data among a sample of African children.

Purpose: This study aimed to determine expected binocular visual function data among schoolchildren in the Central Region of Ghana.

Methods: The study used a prospective cross-sectional design and used a multistage cluster sampling approach. Read More

View Article and Full-Text PDF

LightGBM Indoor Positioning Method Based on Merged Wi-Fi and Image Fingerprints.

Sensors (Basel) 2021 May 25;21(11). Epub 2021 May 25.

Faculty of Information Technology, Beijing University of Technology, Beijing 100124, China.

Smartphones are increasingly becoming an efficient platform for solving indoor positioning problems. Fingerprint-based positioning methods are popular because of the wide deployment of wireless local area networks in indoor environments and the lack of model propagation paths. However, Wi-Fi fingerprint information is singular, and its positioning accuracy is typically 2-10 m; thus, it struggles to meet the requirements of high-precision indoor positioning. Read More

View Article and Full-Text PDF

Automated Identification of Referable Retinal Pathology in Teleophthalmology Setting.

Transl Vis Sci Technol 2021 May;10(6):30

Department of Ophthalmology, Duke University, Durham, NC, USA.

Purpose: This study aims to meet a growing need for a fully automated, learning-based interpretation tool for retinal images obtained remotely (e.g. teleophthalmology) through different imaging modalities that may include imperfect (uninterpretable) images. Read More

View Article and Full-Text PDF

Progressive Disruption of Dynamic Functional Network Connectivity in Patients With Hepatitis B Virus-related cirrhosis.

J Magn Reson Imaging 2021 May 24. Epub 2021 May 24.

Department of Radiology, The Third Affiliated Hospital of Guangzhou Medical University, Guangzhou Medical University, Guangzhou, Guangdong, China.

Background: The diseased-related dynamic functional network connectivity (dFNC) disruption and its relationship with cognitive impairment in hepatitis B virus-related cirrhosis (HBV-RC) patients with minimal hepatic encephalopathy (MHE) and no MHE (NMHE) remain unknown. This knowledge would help identify MHE pathophysiology and monitor disease progression in HBV-RC patients.

Purpose: To investigate the dFNC in patients with NMHE and MHE and the relationship between dFNC indices with the psychometric hepatic encephalopathy score (PHES). Read More

View Article and Full-Text PDF

Laminar fMRI using T-prepared multi-echo FLASH.

Neuroimage 2021 May 21:118163. Epub 2021 May 21.

Erwin L. Hahn Institute for Magnetic Resonance Imaging, University of Duisburg-Essen, 45141 Essen, Germany; High-Field and Hybrid MR Imaging, University Hospital Essen, University of Duisburg-Essen, 45147 Essen, Germany.

Functional magnetic resonance imaging (fMRI) using blood oxygenation level dependent (BOLD) contrast at a sub-millimeter scale is a promising technique to probe neural activity at the level of cortical layers. While gradient echo (GRE) BOLD sequences exhibit the highest sensitivity, their signal is confounded by unspecific extravascular (EV) and intravascular (IV) effects of large intracortical ascending veins and pial veins leading to a downstream blurring effect of local signal changes. In contrast, spin echo (SE) fMRI promises higher specificity towards signal changes near the microvascular compartment. Read More

View Article and Full-Text PDF

Multiparametric Rest and Dobutamine Stress Magnetic Resonance in Assessment of Myocardial Viability.

J Magn Reson Imaging 2021 May 20. Epub 2021 May 20.

Aswan Heart Centre (Magdi Yacoub Foundation), Aswan, Egypt.

Background: MR feature-tracking (FT) is a novel technique that quantitatively calculates myocardial strain and can assess myocardial viability.

Purpose: To evaluate the feasibility of FT at rest and with low-dose dobutamine (LDD), visual assessment of contractility with LDD and left ventricle (LV) end-diastolic wall thickness (EDWT) in the assessment of viability in ischemic cardiomyopathy (ICM) patients compared to delayed gadolinium enhancement (DGE).

Study Type: Prospective. Read More

View Article and Full-Text PDF

Inferior occipital gyrus is organised along common gradients of spatial and face-part selectivity.

J Neurosci 2021 May 14. Epub 2021 May 14.

Experimental Psychology, University College London, London WC1E 6BT, UK.

The ventral visual stream of the human brain is subdivided into patches with categorical stimulus preferences, like faces or scenes. However, the functional organization these areas is less clear. Here, we used functional magnetic resonance imaging and vertex-wise tuning models to independently probe spatial and face-part preferences in the inferior occipital gyrus (IOG) of healthy adult males and females. Read More

View Article and Full-Text PDF

Abundance and population characteristics of the invasive sea urchin Diadema setosum (Leske, 1778) in the south Aegean Sea (eastern Mediterranean).

J Biol Res (Thessalon) 2021 May 21;28(1):11. Epub 2021 May 21.

School of Agricultural Sciences, Department of Ichthyology and Aquatic Environment, University of Thessaly, 38445, Nea Ionia, Magnesia, Greece.

Background: The Indo-Pacific sea urchin Diadema setosum has invaded the Mediterranean Sea and has spread along many locations in the southeastern part of the basin, where established populations exist on the shallow subtidal rocky shore. Diadema setosum is a ubiquitous species, of particular ecological importance due to the high levels of grazing pressure it imposes on benthic communities. Its biology, however, is not adequately studied, especially along its introduced range of distribution. Read More

View Article and Full-Text PDF

Liver fibrosis staging by deep learning: a visual-based explanation of diagnostic decisions of the model.

Eur Radiol 2021 May 20. Epub 2021 May 20.

Department of Radiology, Medical Imaging Center Groningen, University of Groningen, University Medical Center Groningen, PO Box 30001, 9700 RB, Groningen, The Netherlands.

Objectives: Deep learning has been proven to be able to stage liver fibrosis based on contrast-enhanced CT images. However, until now, the algorithm is used as a black box and lacks transparency. This study aimed to provide a visual-based explanation of the diagnostic decisions made by deep learning. Read More

View Article and Full-Text PDF

Quantity and Morphology of Perivascular Spaces: Associations With Vascular Risk Factors and Cerebral Small Vessel Disease.

J Magn Reson Imaging 2021 May 17. Epub 2021 May 17.

Department of Radiology, The Second Affiliated Hospital of Zhejiang University School of Medicine, Hangzhou, China.

Background: Perivascular spaces (PVSs) are important component of the brain glymphatic system. While visual rating has been widely used to assess PVS, computational measures may have higher sensitivity for capturing PVS characteristics under disease conditions.

Purpose: To compute quantitative and morphological PVS features and to assess their associations with vascular risk factors and cerebral small vessel disease (CSVD). Read More

View Article and Full-Text PDF

Learning where to look for COVID-19 growth: Multivariate analysis of COVID-19 cases over time using explainable convolution-LSTM.

Appl Soft Comput 2021 Sep 7;109:107469. Epub 2021 May 7.

Indonesian Agency for Meteorology, Climatology and Geophysics, Center for Research and Development, Indonesia.

Determinant factors which contribute to the prediction should take into account multivariate analysis for capturing coarse-to-fine contextual information. From the preliminary descriptive analysis, it shows that environmental factor such as UV (ultraviolet) is one of the essential factors that should be considered to observe the COVID-19 epidemic drivers. Moreover, there are education, government, morphological, health, economic, and behavioral factors contributing to the growth of COVID-19. Read More

View Article and Full-Text PDF
September 2021

Gradient activation of speech categories facilitates listeners' recovery from lexical garden paths, but not perception of speech-in-noise.

J Exp Psychol Hum Percept Perform 2021 04;47(4):578-595

Department of Psychological and Brain Sciences, University of Iowa

Listeners activate speech-sound categories in a gradient way, and this information is maintained and affects activation of items at higher levels of processing (McMurray et al., 2002; Toscano et al., 2010). Read More

View Article and Full-Text PDF

A deep learning system to diagnose the malignant potential of urothelial carcinoma cells in cytology specimens.

Cancer Cytopathol 2021 May 12. Epub 2021 May 12.

Department of Urology, Osaka University Graduate School of Medicine, Osaka, Japan.

Background: Although deep learning algorithms for clinical cytology have recently been developed, their application to practical assistance systems has not been achieved. In addition, whether deep learning systems (DLSs) can perform diagnoses that cannot be performed by pathologists has not been fully evaluated.

Methods: The authors initially obtained low-power field cytology images from archived Papanicolaou-stained urinary cytology glass slides from 232 patients. Read More

View Article and Full-Text PDF

Tongue image quality assessment based on a deep convolutional neural network.

BMC Med Inform Decis Mak 2021 05 5;21(1):147. Epub 2021 May 5.

Basic Medical College Shanghai University of Traditional Chinese Medicine, 1200 Cailun Road, Pudong New Area, Shanghai, 201203, China.

Background: Tongue diagnosis is an important research field of TCM diagnostic technology modernization. The quality of tongue images is the basis for constructing a standard dataset in the field of tongue diagnosis. To establish a standard tongue image database in the TCM industry, we need to evaluate the quality of a massive number of tongue images and add qualified images to the database. Read More

View Article and Full-Text PDF

The human visual system differentially represents subjectively and objectively invisible stimuli.

PLoS Biol 2021 May 5;19(5):e3001241. Epub 2021 May 5.

Brain and Cognition, Department of Psychology, University of Amsterdam, the Netherlands.

The study of unconscious processing requires a measure of conscious awareness. Awareness measures can be either subjective (based on participant's report) or objective (based on perceptual performance). The preferred awareness measure depends on the theoretical position about consciousness and may influence conclusions about the extent of unconscious processing and about the neural correlates of consciousness. Read More

View Article and Full-Text PDF

Molecular analysis of a fungal disease in the habitat-forming brown macroalga Phyllospora comosa (Fucales) along a latitudinal gradient.

J Phycol 2021 May 4. Epub 2021 May 4.

Sydney Institute of Marine Science, Mosman, NSW, 2088, Australia.

Infectious diseases affecting habitat-forming species can have significant impacts on population dynamics and alter the structure and functioning of marine ecosystems. Recently, a fungal infection was described as the causative agent of necrotic lesions on the stipe of the forest-forming macroalga Phyllospora comosa, a disease named "stipe rot" (SR). Here, we developed a quantitative PCR (qPCR) method for rapid detection and quantification of this pathogen, which was applied to evaluate the level of SR infection in eight P. Read More

View Article and Full-Text PDF

Improvement of the Diagnostic Performance of Facial Neuritis Using Contrast-Enhanced 3D T1 Black-Blood Imaging: Comparison with Contrast-Enhanced 3D T1-Spoiled Gradient-Echo Imaging.

J Clin Med 2021 Apr 24;10(9). Epub 2021 Apr 24.

Department of Neurology, Dongtan Sacred Heart Hospital, Hallym University Medical Center, 7, Keunjaebong-gil, Hwaseong-si 18450, Gyeonggi-do, Korea.

This study aims to investigate the diagnostic ability of the contrast-enhanced 3D T1 black-blood fast spin-echo (T1 BB-FSE) sequence compared with the contrast-enhanced 3D T1-spoiled gradient-echo (CE-GRE) sequence in patients with facial neuritis. Forty-five patients with facial neuritis who underwent temporal bone MR imaging, including T1 BB-FSE and CE-GRE imaging, were examined. Two reviewers independently assessed the T1 BB-FSE and CE-GRE images in terms of diagnostic performance, and qualitative (diagnostic confidence and visual asymmetric enhancement) and quantitative analysis (contrast-enhancing lesion extent of the canalicular segment of the affected facial nerve (LEC) and the affected side-to-normal signal intensity ratio (rSI)). Read More

View Article and Full-Text PDF

Robust video content analysis schemes for human action recognition.

Sci Prog 2021 Apr-Jun;104(2):368504211005480

Faculty of Engineering and Technology, Multimedia University, Melaka, Malaysia.

Introduction: Action recognition is a challenging time series classification task that has received much attention in the recent past due to its importance in critical applications, such as surveillance, visual behavior study, topic discovery, security, and content retrieval.

Objectives: The main objective of the research is to develop a robust and high-performance human action recognition techniques. A combination of local and holistic feature extraction methods used through analyzing the most effective features to extract to reach the objective, followed by using simple and high-performance machine learning algorithms. Read More

View Article and Full-Text PDF

Environmental DNA metabarcoding reveals and unpacks a biodiversity conservation paradox in Mediterranean marine reserves.

Proc Biol Sci 2021 04 28;288(1949):20210112. Epub 2021 Apr 28.

MARBEC, Univ Montpellier, CNRS, Ifremer, IRD, Montpellier, France.

Although we are currently experiencing worldwide biodiversity loss, local species richness does not always decline under anthropogenic pressure. This conservation paradox may also apply in protected areas but has not yet received conclusive evidence in marine ecosystems. Here, we survey fish assemblages in six Mediterranean no-take reserves and their adjacent fishing grounds using environmental DNA (eDNA) while controlling for environmental conditions. Read More

View Article and Full-Text PDF

Coronal Gradient Echo MRI to Visualize the Zona Incerta for Deep Brain Stimulation Targeting in Parkinson's Disease.

Stereotact Funct Neurosurg 2021 Apr 26:1-8. Epub 2021 Apr 26.

Department of Neurology, University of Colorado Anschutz Medical Campus, Aurora, Colorado, USA.

Introduction: Deep brain stimulation of the zona incerta is effective at treating tremor and other forms of parkinsonism. However, the structure is not well visualized with standard MRI protocols making direct surgical targeting unfeasible and contributing to inconsistent clinical outcomes. In this study, we applied coronal gradient echo MRI to directly visualize the rostral zona incerta in Parkinson's disease patients to improve targeting for deep brain stimulation. Read More

View Article and Full-Text PDF

MicroRNA Signatures of the Developing Primate Fovea.

Front Cell Dev Biol 2021 8;9:654385. Epub 2021 Apr 8.

Department of Cell Biology and Human Anatomy, University of California, Davis, Davis, CA, United States.

Rod and cone photoreceptors differ in their shape, photopigment expression, synaptic connection patterns, light sensitivity, and distribution across the retina. Although rods greatly outnumber cones, human vision is mostly dependent on cone photoreceptors since cones are essential for our sharp visual acuity and color discrimination. In humans and other primates, the (fovea), a specialized region of the central retina, contains the highest density of cones. Read More

View Article and Full-Text PDF

Visual interpretability in 3D brain tumor segmentation network.

Comput Biol Med 2021 Jun 19;133:104410. Epub 2021 Apr 19.

Medical Imaging and Diagnostics Lab, National Centre of Artificial Intelligence (NCAI), Pakistan; Department of Computer Science, COMSATS University Islamabad (CUI), Islamabad, 45550, Pakistan. Electronic address:

Medical image segmentation is a complex yet one of the most essential tasks for diagnostic procedures such as brain tumor detection. Several 3D Convolutional Neural Network (CNN) architectures have achieved remarkable results in brain tumor segmentation. However, due to the black-box nature of CNNs, the integration of such models to make decisions about diagnosis and treatment is high-risk in the domain of healthcare. Read More

View Article and Full-Text PDF

Intracranial Access: Dural Venous Sinus Stenting: 2-Dimensional Operative Video.

Oper Neurosurg (Hagerstown) 2021 Apr 23. Epub 2021 Apr 23.

Department of Neurologic Surgery, Mayo Clinic, Jacksonville, Florida, USA.

Cerebral venous sinus stenting has gained popularity in recent years as a safe and efficacious treatment of selected patients with idiopathic intracranial hypertension (IIH) and focal venous sinus stenosis.1-3 The main goal of treatment is to prevent visual loss, and often patients report resolution of headache and visual symptoms within 21 mo of mean follow-up.4-8 We present the case of a 57-yr-old woman with medically refractory IIH, bilateral sinus stenosis, and a mass lesion causing stenosis on the left. Read More

View Article and Full-Text PDF