A hybrid unsupervised-Deep learning tandem for electrooculography time series analysis

PloS One
Ruxandra StoeanGonzalo Joya

Abstract

Medical data are often tricky to get mined for patterns even by the generally demonstrated successful modern methodologies of deep learning. This paper puts forward such a medical classification task, where patient registers of two of the categories are sometimes hard to be distinguished because of samples showing characteristics of both labels in turn in several repetitions of the screening procedure. To this end, the current research appoints a pre-processing clustering step (through self-organizing maps) to group the data based on shape similarity and relabel it accordingly. Subsequently, a deep learning approach (a tandem of convolutional and long short-term memory networks) performs the training classification phase on the 'cleaned' samples. The dual methodology was applied for the computational diagnosis of electrooculography tests within spino-cerebral ataxia of type 2. The accuracy obtained for the discrimination into three classes was of 78.24%. The improvement that this duo brings over the deep learner alone does not stem from significantly higher accuracy results when the performance is considered for all classes. The major finding of this combination is that half of the presymptomatic cases were correctly found, in ...Continue Reading

References

Mar 4, 2003·IEEE Transactions on Neural Systems and Rehabilitation Engineering : a Publication of the IEEE Engineering in Medicine and Biology Society·Rafael BareaElena López
May 24, 2007·IEEE Transactions on Bio-medical Engineering·Paul R DavidsonMalik T R Peiris
Oct 20, 2009·Clinical Neurophysiology : Official Journal of the International Federation of Clinical Neurophysiology·Piotr MirowskiRuben Kuzniecky
Jul 31, 2016·Briefings in Bioinformatics·Seonwoo MinSungroh Yoon
Apr 6, 2018·Journal of the Royal Society, Interface·Travers ChingCasey S Greene
Oct 3, 2018·Computational and Structural Biotechnology Journal·Daisuke Komura, Shumpei Ishikawa
Dec 17, 2018·Zeitschrift für medizinische Physik·Alexander Selvikvåg Lundervold, Arvid Lundervold
Apr 22, 2019·European Journal of Radiology·Luca SabaJasjit S Suri
May 23, 2019·Neural Computation·Yong YuJianxun Zhang
Jun 24, 2019·Magnetic Resonance Imaging·Mahmoud Mostapha, Martin Styner
Jul 26, 2019·Scientific Reports·Jaakko SahlstenKimmo Kaski
Sep 26, 2019·NPJ Digital Medicine·Filippo ArcaduMarco Prunotto
Nov 5, 2019·Frontiers in Bioengineering and Biotechnology·Shachi MittalRohit Bhargava
Sep 20, 2019·NPJ Digital Medicine·Filippo ArcaduMarco Prunotto

❮ Previous
Next ❯

Methods Mentioned

BETA
feature extraction

Software Mentioned

Vara
DL
SOM

Related Concepts

Related Feeds

Ataxias (MDS)

Ataxia is a neurological condition characterized by lack of voluntary coordination of muscle movements including loss of coordination, balance, and speech. Discover the latest research on ataxia here.

Ataxia

Ataxia is a neurological condition characterized by lack of voluntary coordination of muscle movements including loss of coordination, balance, and speech. Discover the latest research on ataxia here.

Related Papers

Current Medical Imaging
Hafiz Mughees AhmadKhurram Khurshid
Revue d'électroencéphalographie et de neurophysiologie clinique
V GabersekA Monot
Sborník Vědeckých Prací Lékařské Fakulty Karlovy University V Hradci Králové
J PeregrinC Veselý
© 2021 Meta ULC. All rights reserved