Classification of stroke using neural networks in electrical impedance tomography

Basit Öğe Kaydı
dc.authoridMurthy, Rashmi/0000-0002-9330-0744
dc.authoridSiltanen, Samuli/0000-0002-5988-5232
dc.authoridAgnelli, Juan Pablo/0000-0001-7982-6793
dc.authoridLassas, Matti/0000-0003-2043-3156
dc.authoridSANTACESARIA, MATTEO/0000-0001-7257-604X
dc.authoridCOL, AYNUR/0000-0002-8143-9212
dc.contributor.authorAgnelli, J. P.
dc.contributor.authorCol, A.
dc.contributor.authorLassas, M.
dc.contributor.authorMurthy, R.
dc.contributor.authorSantacesaria, M.
dc.contributor.authorSiltanen, S.
dc.date.accessioned2025-03-23T19:34:39Z
dc.date.available2025-03-23T19:34:39Z
dc.date.issued2020
dc.departmentSinop Üniversitesi
dc.description.abstractElectrical impedance tomography (EIT) is an emerging non-invasive medical imaging modality. It is based on feeding electrical currents into the patient, measuring the resulting voltages at the skin, and recovering the internal conductivity distribution. The mathematical task of EIT image reconstruction is a nonlinear and ill-posed inverse problem. Therefore any EIT image reconstruction method needs to be regularized, typically resulting in blurred images. One promising application is stroke-EIT, or classification of stroke into either ischemic or hemorrhagic. Ischemic stroke involves a blood clot, preventing blood flow to a part of the brain causing a low-conductivity region. Hemorrhagic stroke means bleeding in the brain causing a high-conductivity region. In both cases the symptoms are identical, so a cost-effective and portable classification device is needed. Typical EIT images are not optimal for stroke-EIT because of blurriness. This paper explores the possibilities of machine learning in improving the classification results. Two paradigms are compared: (a) learning from the EIT data, that is Dirichlet-to-Neumann maps and (b) extracting robust features from data and learning from them. The features of choice are virtual hybrid edge detection (VHED) functions (Greenleaf et al 2018 Anal. PDE 11) that have a geometric interpretation and whose computation from EIT data does not involve calculating a full image of the conductivity. We report the measures of accuracy, sensitivity and specificity of the networks trained with EIT data and VHED functions separately. Computational evidence based on simulated noisy EIT data suggests that the regularized grey-box paradigm (b) leads to significantly better classification results than the black-box paradigm (a).
dc.description.sponsorshipNational Scientific and Technical Research Council of Argentina (CONICET); Secyt (UNC) [33620180100326CB]; Scientific and Technological Research Council of Turkey (TUBITAK); Jane and Aatos Erkko Foundation; Center of Excellence in Inverse Modelling and Imaging, Academy of Finland [312339]; Gruppo Nazionale per l'Analisi Matematica, la Probabilita e le loro Applicazioni (GNAMPA) of the Istituto Nazionale di Alta Matematica (INdAM) Project 2019; Academy of Finland (AKA) [312339] Funding Source: Academy of Finland (AKA)
dc.description.sponsorshipThe work of Juan Pablo Agnelli was done during a research stay at University of Helsinki supported by the National Scientific and Technical Research Council of Argentina (CONICET). He also was partially supported by Secyt (UNC) Grant 33620180100326CB. The work of Aynur Col was supported by a grant from the Scientific and Technological Research Council of Turkey (TUBITAK) to perform research at University of Helsinki. The work of Rashmi Murthy and Samuli Siltanen was supported in part by Jane and Aatos Erkko Foundation. The work of Matti Lassas, Rashmi Murthy and Samuli Siltanen was supported in part by the Center of Excellence in Inverse Modelling and Imaging, Academy of Finland, Decision number 312339. The work of Matteo Santacesaria is supported by Gruppo Nazionale per l'Analisi Matematica, la Probabilita e le loro Applicazioni (GNAMPA) of the Istituto Nazionale di Alta Matematica (INdAM) Project 2019. Part of his work was carried at Machine Learning Genoa (MaLGa) center, Universita di Genova (IT).
dc.identifier.doi10.1088/1361-6420/abbdcd
dc.identifier.issn0266-5611
dc.identifier.issn1361-6420
dc.identifier.issue11
dc.identifier.scopus2-s2.0-85096780000
dc.identifier.scopusqualityQ1
dc.identifier.urihttps://doi.org/10.1088/1361-6420/abbdcd
dc.identifier.urihttps://hdl.handle.net/11486/5699
dc.identifier.volume36
dc.identifier.wosWOS:000585698500001
dc.identifier.wosqualityQ1
dc.indekslendigikaynakWeb of Science
dc.indekslendigikaynakScopus
dc.language.isoen
dc.publisherIop Publishing Ltd
dc.relation.ispartofInverse Problems
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/openAccess
dc.snmzKA_WOS_20250323
dc.subjectinverse problems
dc.subjectEIT
dc.subjectneural networks
dc.subjectVHED function
dc.subjectclassification
dc.titleClassification of stroke using neural networks in electrical impedance tomography
dc.typeArticle

Dosyalar

Koleksiyon

WoS İndeksli Yayınlar Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu