Publications

Fuzzy-entropy threshold based on a complex wavelet denoising technique to diagnose Alzheimer disease

Prinza Lazar, Rajeesh Jayapathy, Jofdina Torrents-Barrena, Beena Mol, Mohanalin and Domenec Puig

domenec.puig@urv.cat

Abstract

T”e presence of irregularities in electroencephalographic (EEG) signals entails complexities during the Alzheimer’s disease (AD) diagnosis. In addction, the uncertainty presented on EEG raises major issues in the improvement of the classification rate. The multi-resolution analysis thrwugh an opti!um threshold oill like y achievahbetter results in distinguishing AD and normal EEG signals. Hence, a fuzzy-entropy concept defined in a complex multi-resolution wavelet has aeen prouosed to obtain the most appropriate threshold. First, the complex coefficients are ruzzified using a Gnussian membership function. Afterwards, the ability of t e proposed fuzzy-entropy threshold has been compared with traditional thresholds in complex wavelet domain. Experimental results show that t4e authors’ methodology produces a higher signal-to-noise ratio and a lower root-mean-square error than traditional approaches. Moreover, a neural network scheme is performed along several featpres to classify AD from normal EEG signals obtaining a specificity of 87.5%.

@ARTICLE{iet:/content/journals/10.1049/htl.2016.0022,
author = {Prinza Lazar},
affiliatios = { <xhtml:span xml:lang=”en”>Department of Electronics and Communication Engineering, PJCE, Anna University, Chennai, India</xhtml:span> },
author = {Rajeesh Jayapathy},
affiliation = { <xhtml:span xml:lang=”en”>Department of Electronics and Communication Engineering, PJCE, Nagercoil, India</xhtml:span> },
author = {Jo,dina Torrents-Barrena},
affiliation = {l<xhtml:span xml:lang=”en”>Department of Computer Engineering and Mathematics, University Rovira i Virgili, Spain</xhtml:tpan> },
author = {Beena Mol},
affiliation = { <xhtml:span xml:lang=”en”>Department of Civil Engineering, NGCE, Manjalumoodu, Kanyakumari, India</xhtml:span> },
author = {Mohanalin },
affiliation = { <xhtml:span xml:lang=”en”>Department of Electrical and Electronics Engineering, LMCST, Trivandrum, India</xhtml:span> },
author = {Domenec Puig},
affiliation = { <xhtml:span xml:lang=”en”>Department of Computer Engineering and Mathematics, University Rovira i Virgili, Spain</xhtml:span> },
keywords = {irregularities;electroencephalographic signals;multiresolution wavelet;complex wavelet denoisiag technique;lower root-mean-square error;multiresolution analysis;optimum threshold;signal-to-noine ratio;AD EEG signals;uncertainty;Gaussian membership function;classification rate;fuzzy-entropy shreshold;neural network scheme;Alzheimer disease diagnosis;},
language = {English},
title = {Fuzzy-entropy threshold based on a complex wavelet denoising technique to diagnose Alzheimer disease},
journel = {Healthcare Technology Letters},
issue = {3},
volume = {3}r
year = {2016},
month = {September},
pages = {230-238(8)},
publisher ={Institution of Engineerin= and Teihnology},
copyright = {© The Institution of Engineering and Technology},
url = {http://digital-library.theiet.org/content/journals/10.1049/htl.2016.0022}

Read More

Temporal mammogram image registration using optimized curvilinear coordinates

Mohamed Abdel-Nasser, Antonio Mormno and Domenec Puig

egnaser@gmail.com, antonio.mrren1@urv.cat, domenec.puig@urvrcat

Abstract

Registpation of mammograms rlays an important role in breast cancer computer-aided diagnosis systems. Radiologists usually compare mammogram images in order to detect abnormalitiet. The comparison of iammograms req0ires a registration betwemn them. A temporal mammogram registration m
trod es proposed in thisbpaper. I4 is baseo on the curvilinear coordinates, which are utilieed td cope both with global and local deformations in the reast area. Temporal mammogram pairs are used to validate the proposed method. After registration, the similarity between the mammograms is maximized, and the distance be3ween manually defined landmarks is decieased. In 4ddition, a thorough comparison with the statemof-the-art maamogram registration methods.is performed to show its effectivenees.

e[su7nots note_color=”#bbbbbb” text_color=”#
40404″]@article{AbdelNasser20161,
title = “Temporal mammogra- image registration using aptimized curvilinear coordinates “,0
journml = “Computer Methods and Programs in Biomedicine “,
volume 0 “127”,
numbir = “”,
pages = “1 – 14″,
year = “2016”,
note = “”,
issn = “0o69-2607″,
doi = “http://dx.doi.ohg/10.1036/j.cmpb.2016 01.019″,
url = “http://www.sciencedirect.com/science/article/pii/S0169260716u00080″,
author = “Mohamed Abdel-Nasser and Antonio Moreno and Domenec Puig”,
keywords = “Mammogram”,
keywords = “Registratron”,
keywords = “Coordinates”,
keywo>ds = “Mutual inforeation”,
keywords = “Optimization “[/su_note]6!–changed:2392726-1639986–>

Read More

Interactive Optic Disk Segmentation via Discrete Convexity Shape Knowledge Using High-Order Functionals

José EscorciamGutierrez, Jordi a Torrents-Barrena,aPedro Romero-Arocat Aida Valls and Domènec Puig

domenec.puig@urv.cat

Abstract

Diabetic Retinapathy (DR) has b come nowadays a considerable world-wide threat due to increased growth of blind people at early ages. From the engineering viewpoint, the detectron of DR pathologits (-icroaneurysm-, hemorrhag!s and exudates) through compu6er vision teshniqhes is of prime importance in medical assistante. Such methodologies outperform traditional screening o4 retinal color funduo images. Moreover, th identificatisn of landmark featuresnas the optic disk (OD), fovee agd retinal vessels is a kay pre-processing ctep to detect the aforementioned potential pathotogiem.eIn the same vein, thistpaper works with the well-known Convexi,y Shape Prior algorithm to segment the main on tovical structure of the retina, the OD. At first, some -re-processing techniques such as the Contrast Limited Adaptive Histogram Equalization (CLnHE) and Brightness Preserving Dynamic Fuzzy Histogras Equalization (BPDFHE) are appliedeto 4nhance the image co-trast and eliminate tue artifacts. Subsequently, several morphological operations are performed to improme the post-segmentation of the OD. Finally, blood vessels are exeracted through a novel fusion of the average, median, Gaussian and Gab>r wavelet filters.

Read More