Filters








577 Hits in 4.2 sec

Fully Automated Reduction of Ocular Artifacts in High-Dimensional Neural Data

J W Kelly, D P Siewiorek, A Smailagic, J L Collinger, D J Weber, Wei Wang
2011 IEEE Transactions on Biomedical Engineering  
The reduction of artifacts in neural data is a key element in improving analysis of brain recordings and the development of effective brain-computer interfaces.  ...  Here, new techniques based on wavelet thresholding and independent component analysis (ICA) are developed for use in high-dimensional neural data.  ...  time for MEG data collection, and Anna Haridis at CABMSI for assistance in MEG setup and data collection.  ... 
doi:10.1109/tbme.2010.2093932 pmid:21097374 fatcat:mmuodtz2ujbxbg554wtyinns2y

Automatic Classification of Artifactual ICA-Components for Artifact Removal in EEG Signals

Irene Winkler, Stefan Haufe, Michael Tangermann
2011 Behavioral and Brain Functions  
Trained on expert ratings of large data sets, it is not restricted to the detection of eye-and muscle artifacts.  ...  Conclusions: We propose a universal and efficient classifier of ICA components for the subject independent removal of artifacts from EEG data.  ...  the authors of [33] for providing the motor imagery data set.  ... 
doi:10.1186/1744-9081-7-30 pmid:21810266 pmcid:PMC3175453 fatcat:b5v5noa6tzh7li4draa7j4dba4

A comparative study of automatic techniques for ocular artifact reduction in spontaneous EEG signals based on clinical target variables: A simulation case

Sergio Romero, Miguel A. Mañanas, Manel J. Barbanoj
2008 Computers in Biology and Medicine  
The aim of this paper was to objectively and quantitatively evaluate the performance of ocular filtering methods with respect to spectral target variables widely used in clinical and functional EEG studies  ...  In the case of full montage: (i) errors were lower than 5% for all spectral variables at anterior sites; and (ii) the highest improvement in the signal-to-artifact (SAR) ratio was obtained up to 40 dB  ...  Some studies suggest that most of the high frequency range in the EOG is of neural origin.  ... 
doi:10.1016/j.compbiomed.2007.12.001 pmid:18222418 fatcat:rpj3a7th4fbvbfkdrjkzr2evlu

Automated Detection of Ripple Oscillations in Long-Term Scalp EEG from Patients with Infantile Spasms [article]

Colin M McCrimmon, Aliza Riba, Cristal Garner, Amy L Maser, Daniel W Shrey, Beth A Lopour
2020 bioRxiv   pre-print
of short segments of data due to the prevalence of artifacts in EEG.  ...  Therefore, we set out to develop a fully automated method of HFO detection that can be applied to large datasets, and we sought to robustly characterize the rate and spatial distribution of HFOs in IS.  ...  There is likely some basal level of muscle/ocular artifacts that escaped automated rejection in both the control and spasms subjects. 11/17 However, these artifacts likely accounted for a small proportion  ... 
doi:10.1101/2020.06.03.132183 fatcat:6nxjsuhx6zfavjukphpacxddse

Automated segmentation of dermal fillers in OCT images of mice using convolutional neural networks

Martin Pfister, Kornelia Schützenberger, Ulrike Pfeiffenberger, Alina Messner, Zhe Chen, Valentin Aranha dos Santos, Stefan Puchner, Gerhard Garhöfer, Leopold Schmetterer, Martin Gröschl, René M. Werkmeister
2019 Biomedical Optics Express  
Three-dimensional data sets of a 10 mm × 10 mm skin patch comprising the intradermal filler and the surrounding tissue were acquired.  ...  Volumetric image data was acquired using a custom-built OCT prototype that employs an akinetic swept laser at ~1310 nm with a bandwidth of 87 nm, providing an axial resolution of ~6.5 μm in tissue.  ...  Disclosures The authors declare that there are no conflicts of interest related to this article.  ... 
doi:10.1364/boe.10.001315 pmid:30891348 pmcid:PMC6420291 fatcat:msia2shd25blbhnkq3niywh3eu

Automated Explainable Multidimensional Deep Learning Platform of Retinal Images for Retinopathy of Prematurity Screening

Ji Wang, Jie Ji, Mingzhi Zhang, Jian-Wei Lin, Guihua Zhang, Weifen Gong, Ling-Ping Cen, Yamei Lu, Xuelin Huang, Dingguo Huang, Taiping Li, Tsz Kin Ng (+1 others)
2021 JAMA Network Open  
In this diagnostic study, an automated ROP screening platform was able to identify and classify multidimensional pathologic lesions in the retinal images.  ...  Four main dimensional independent classifiers were developed, including image quality, any stage of ROP, intraocular hemorrhage, and preplus/plus disease.  ...  The features extracted by neural networks just before the classification header were visualized using t-Distributed Stochastic Neighbor Embedding, which is a technique for dimensionality reduction (eFigure  ... 
doi:10.1001/jamanetworkopen.2021.8758 pmid:33950206 pmcid:PMC8100867 fatcat:kdr7u6xonjb63cux6swildyh4m

Deep Learning based Retinal OCT Segmentation [article]

Mike Pekala, Neil Joshi, David E. Freund, Neil M. Bressler, Delia Cabrera DeBuc, Philippe M Burlina
2018 arXiv   pre-print
The proposed automated approach segments images using fully convolutional networks (FCNs) together with Gaussian process (GP)-based regression as a post-processing step to improve the quality of the estimates  ...  The results show that the proposed methods compare favorably with state of the art techniques, resulting in the smallest mean unsigned error values and associated standard deviations, and performance is  ...  Automated grading of age-related macular degeneration from color fundus images using deep convolutional neural networks. JAMA Ophtalmology, . .  ... 
arXiv:1801.09749v1 fatcat:474syzsyp5cxfljj646ecbtq6m

Quantitative Assessment of Experimental Ocular Inflammatory Disease

Lydia J. Bradley, Amy Ward, Madeleine C. Y. Hsue, Jian Liu, David A. Copland, Andrew D. Dick, Lindsay B. Nicholson
2021 Frontiers in Immunology  
Ocular inflammation imposes a high medical burden on patients and substantial costs on the health-care systems that mange these often chronic and debilitating diseases.  ...  Models can recapitulate many of the features seen in the clinic, but until recently the quality of imaging available has lagged that applied in humans.  ...  ACKNOWLEDGMENTS The authors gratefully acknowledge support of the National Eye Research Centre, Fight for Sight (5077/5078) and the Underwood Trust to research carried out in their laboratories.  ... 
doi:10.3389/fimmu.2021.630022 pmid:34220797 pmcid:PMC8250853 fatcat:x47elexhjzc2fobuahseezhiwa

Deep Learning–Based Retinal Nerve Fiber Layer Thickness Measurement of Murine Eyes

Rui Ma, Yuan Liu, Yudong Tao, Karam A. Alawa, Mei-Ling Shyu, Richard K. Lee
2021 Translational Vision Science & Technology  
Methods: We developed a deep learning-based image segmentation network for automated segmentation of the RNFL in SD-OCT B-scans of mouse eyes.  ...  In total, 5500 SD-OCT B-scans (5200 B-scans were used as training data with the remaining 300 B-scans used as testing data) were used to develop this segmentation network.  ...  In addition to high image quality, OCT is also a noninvasive in vivo imaging technique capable of capturing micron-scale structural anatomy.  ... 
doi:10.1167/tvst.10.8.21 fatcat:ljshmwhxxfbrflyajtwwufsj44

A Digital Staining Algorithm for Optical Coherence Tomography Images of the Optic Nerve Head

Jean-Martial Mari, Tin Aung, Ching-Yu Cheng, Nicholas G. Strouthidis, Michaël J. A. Girard
2017 Translational Vision Science & Technology  
This was true even in regions exhibiting high shadowing artifacts (e.g., nasal side of the optic disc).  ...  ONH, typical OCT artifacts, such as blood vessel shadows and poor connective tissue visibility at high depth would still remain in the digitally stained images (data not shown).  ... 
doi:10.1167/tvst.6.1.8 pmid:28174676 pmcid:PMC5291077 fatcat:l6tyzcj64rhxzpubwfj3eedlki

Artificial intelligence deep learning algorithm for discriminating ungradable optical coherence tomography three-dimensional volumetric optic disc scans

An Ran Ran, Jian Shi, Amanda K. Ngai, Wai-Yin Chan, Poemen P. Chan, Alvin L. Young, Hon-Wah Yung, Clement C. Tham, Carol Y. Cheung
2019 Neurophotonics  
However, it is insufficient to assess other image quality issues such as off-centration, out of registration, missing data, motion artifacts, mirror artifacts, or blurriness, which require specialized  ...  ) in human eyes in vivo.  ...  Acknowledgments The work described in this paper was supported by the Research Grants Council -General Research Fund, Hong Kong (Reference No. 14102418), and the Bright Focus Foundation (Reference No.  ... 
doi:10.1117/1.nph.6.4.041110 pmid:31720307 pmcid:PMC6823275 fatcat:ka4hcxrwcndmxk6jtwy6e5mouu

Detection of Artifacts and Brain Responses Using Instantaneous Phase Statistics in Independent Components [chapter]

Jurgen Dammers, Michael Schiek
2011 Magnetoencephalography  
Therefore, the high dimensionality of the data and the poor signal-to-noise ratio (SNR) are the two most inviting challenges in MEG single-trial analysis.  ...  After signal decomposition the problem now is to objectively identify components of interest in such high dimensional data sets, as it is the case for modern MEG systems.  ... 
doi:10.5772/27523 fatcat:5cv5yznhlzatxn3tpf6q3x2j5q

Progress towards automated diabetic ocular screening: A review of image analysis and intelligent systems for diabetic retinopathy

T. Teng, M. Lefley, D. Claremont
2002 Medical and Biological Engineering and Computing  
This is stimulating research into automated analysis of the reflectance images of the ocular fundus. Publications applicable to the automated screening of diabetic retinopathy are summarised.  ...  In summary, the advent of digital data sets has made image analysis more accessible, although questions regarding the assessment of individual algorithms and whole systems are only just being addressed  ...  Acknowledgments~he retinal image in Fig. 1 was provided courtesy of the ETDRS and DRS Research Groups.  ... 
doi:10.1007/bf02347689 pmid:11954703 fatcat:q5snz2mjmzb5vloucpwbrmlltq

Improved EOG Artifact Removal Using Wavelet Enhanced Independent Component Analysis

Issa, Juhasz
2019 Brain Sciences  
Unfortunately, removing entire components may result in losing important neural information present in the component and eventually may distort the spectral characteristics of the reconstructed signals  ...  By decomposing the signals into neural and artifactual components and artifact components can be eliminated before signal reconstruction.  ...  The estimation of ŝ requires pre-processing steps (dimensionality reduction, centering and uncorrelation).  ... 
doi:10.3390/brainsci9120355 pmid:31817120 pmcid:PMC6956025 fatcat:dmh7jgfpqbcmxhxkj43wjezqdm

An Unsupervised Multichannel Artifact Detection Method for Sleep EEG Based on Riemannian Geometry

Elizaveta Saifutdinova, Marco Congedo, Daniela Dudysova, Lenka Lhotska, Jana Koprivova, Vaclav Gerla
2019 Sensors  
In biomedical signal processing, we often face the problem of artifacts that distort the original signals. This concerns also sleep recordings, such as EEG.  ...  Therefore, artifact-free data are often obtained after sequential application of different methods. Moreover, single-channel approaches must be applied to all channels alternately.  ...  Therefore, in the case of a very large number of EEG channels, a dimensionality-reduction pre-processing step is recommended.  ... 
doi:10.3390/s19030602 fatcat:5jybreabzbb7rkk4ioxmv77vze
« Previous Showing results 1 — 15 out of 577 results