Inferior Myocardial Infarction Detection From Lead II of ECG: A Gramian Angular Field-Based 2D-CNN Approach
This letter presents a novel method for inferior myocardial infarction (MI) detection using lead II of electrocardiogram (ECG). We evaluate our proposed method on a public dataset, namely, Physikalisch Technische Bundesanstalt (PTB) ECG dataset from PhysioNet. Under our proposed method, we first cle...
Gespeichert in:
Veröffentlicht in: | IEEE sensors letters 2024-10, Vol.8 (10), p.1-4 |
---|---|
Hauptverfasser: | , , , , , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | 4 |
---|---|
container_issue | 10 |
container_start_page | 1 |
container_title | IEEE sensors letters |
container_volume | 8 |
creator | Yousuf, Asim Hafiz, Rehan Riaz, Saqib Farooq, Muhammad Riaz, Kashif Rahman, Muhammad Mahboob Ur |
description | This letter presents a novel method for inferior myocardial infarction (MI) detection using lead II of electrocardiogram (ECG). We evaluate our proposed method on a public dataset, namely, Physikalisch Technische Bundesanstalt (PTB) ECG dataset from PhysioNet. Under our proposed method, we first clean the noisy ECG signals using db4 wavelet, followed by an R-peak detection algorithm to segment the ECG signals into beats. We then translate the ECG timeseries dataset to an equivalent dataset of grayscale images using Gramian angular summation field (GASF) and Gramian angular difference field (GADF) operations. Subsequently, the grayscale images are fed into a custom 2-D convolutional neural network (CNN), which efficiently differentiates between a healthy subject and a subject with MI. Our proposed approach achieves an average classification accuracy of 99.68%, 99.80%, 99.82%, and 99.84% under GASF dataset with noise and baseline wander, GADF dataset with noise and baseline wander, GASF dataset with noise and baseline wander removed, and GADF dataset with noise and baseline wander removed, respectively. Most importantly, this work opens the floor for innovation in wearable devices to measure lead II ECG (e.g., by a smart watch worn on right wrist, along with a smart patch on left leg), in order to do accurate, real-time, and early detection of inferior wall MI. |
doi_str_mv | 10.1109/LSENS.2024.3450176 |
format | Article |
fullrecord | <record><control><sourceid>proquest_RIE</sourceid><recordid>TN_cdi_ieee_primary_10648729</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>10648729</ieee_id><sourcerecordid>3102975036</sourcerecordid><originalsourceid>FETCH-LOGICAL-c177t-8dc108d1b5da1571ca6c1906c2fec1d5951e512eef0195e96a9e6811faffcfb83</originalsourceid><addsrcrecordid>eNpNkLtOwzAUhiMEElXpCyAGS8wpPk4cJ2whvRAplKEwW659DClpUpx06NuTkg6dzq-j_yJ9nncPdApAk6diPV-tp4yycBqEnIKIrrwRCwX3IRTs-kLfepO23VJKIWaCBnTk_eS1RVc2jrwdG62cKVVF-p9yuiubmsyww0EtXLMjBSpD8pw0lsyz5TNJydKpXalqktZfh0o5siixMv6LatEQNvOz1Yqk-71rlP6-826sqlqcnO_Y-1zMP7JXv3hf5lla-BqE6PzYaKCxgQ03CrgArSINCY00s6jB8IQDcmCIlkLCMYlUglEMYJW12m7iYOw9Dr397O8B205um4Or-0kZAGWJ4DSIehcbXNo1bevQyr0rd8odJVB54ir_ucoTV3nm2ocehlCJiBeBKIwFS4I_YBVyZw</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>3102975036</pqid></control><display><type>article</type><title>Inferior Myocardial Infarction Detection From Lead II of ECG: A Gramian Angular Field-Based 2D-CNN Approach</title><source>IEEE Electronic Library (IEL)</source><creator>Yousuf, Asim ; Hafiz, Rehan ; Riaz, Saqib ; Farooq, Muhammad ; Riaz, Kashif ; Rahman, Muhammad Mahboob Ur</creator><creatorcontrib>Yousuf, Asim ; Hafiz, Rehan ; Riaz, Saqib ; Farooq, Muhammad ; Riaz, Kashif ; Rahman, Muhammad Mahboob Ur</creatorcontrib><description>This letter presents a novel method for inferior myocardial infarction (MI) detection using lead II of electrocardiogram (ECG). We evaluate our proposed method on a public dataset, namely, Physikalisch Technische Bundesanstalt (PTB) ECG dataset from PhysioNet. Under our proposed method, we first clean the noisy ECG signals using db4 wavelet, followed by an R-peak detection algorithm to segment the ECG signals into beats. We then translate the ECG timeseries dataset to an equivalent dataset of grayscale images using Gramian angular summation field (GASF) and Gramian angular difference field (GADF) operations. Subsequently, the grayscale images are fed into a custom 2-D convolutional neural network (CNN), which efficiently differentiates between a healthy subject and a subject with MI. Our proposed approach achieves an average classification accuracy of 99.68%, 99.80%, 99.82%, and 99.84% under GASF dataset with noise and baseline wander, GADF dataset with noise and baseline wander, GASF dataset with noise and baseline wander removed, and GADF dataset with noise and baseline wander removed, respectively. Most importantly, this work opens the floor for innovation in wearable devices to measure lead II ECG (e.g., by a smart watch worn on right wrist, along with a smart patch on left leg), in order to do accurate, real-time, and early detection of inferior wall MI.</description><identifier>ISSN: 2475-1472</identifier><identifier>EISSN: 2475-1472</identifier><identifier>DOI: 10.1109/LSENS.2024.3450176</identifier><identifier>CODEN: ISLECD</identifier><language>eng</language><publisher>Piscataway: IEEE</publisher><subject>Algorithms ; Arrhythmia ; Artificial neural networks ; cardiovascular diseases (CVDs) ; convolutional neural network (CNN) ; Datasets ; electrocardiogram (ECG) ; Electrocardiography ; Feature extraction ; Gramian angular difference field (GADF) ; Gramian angular summation field (GASF) ; Gray scale ; Heart attacks ; Lead ; Myocardial infarction ; myocardial infarction (MI) ; Myocardium ; Noise ; Noise measurement ; Real time ; Sensor applications ; Wearable technology ; Wrist</subject><ispartof>IEEE sensors letters, 2024-10, Vol.8 (10), p.1-4</ispartof><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2024</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><cites>FETCH-LOGICAL-c177t-8dc108d1b5da1571ca6c1906c2fec1d5951e512eef0195e96a9e6811faffcfb83</cites><orcidid>0000-0002-5062-3068 ; 0000-0002-6768-0886 ; 0000-0001-5000-0402 ; 0000-0001-6141-079X</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/10648729$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>315,782,786,798,27933,27934,54767</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/10648729$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Yousuf, Asim</creatorcontrib><creatorcontrib>Hafiz, Rehan</creatorcontrib><creatorcontrib>Riaz, Saqib</creatorcontrib><creatorcontrib>Farooq, Muhammad</creatorcontrib><creatorcontrib>Riaz, Kashif</creatorcontrib><creatorcontrib>Rahman, Muhammad Mahboob Ur</creatorcontrib><title>Inferior Myocardial Infarction Detection From Lead II of ECG: A Gramian Angular Field-Based 2D-CNN Approach</title><title>IEEE sensors letters</title><addtitle>LSENS</addtitle><description>This letter presents a novel method for inferior myocardial infarction (MI) detection using lead II of electrocardiogram (ECG). We evaluate our proposed method on a public dataset, namely, Physikalisch Technische Bundesanstalt (PTB) ECG dataset from PhysioNet. Under our proposed method, we first clean the noisy ECG signals using db4 wavelet, followed by an R-peak detection algorithm to segment the ECG signals into beats. We then translate the ECG timeseries dataset to an equivalent dataset of grayscale images using Gramian angular summation field (GASF) and Gramian angular difference field (GADF) operations. Subsequently, the grayscale images are fed into a custom 2-D convolutional neural network (CNN), which efficiently differentiates between a healthy subject and a subject with MI. Our proposed approach achieves an average classification accuracy of 99.68%, 99.80%, 99.82%, and 99.84% under GASF dataset with noise and baseline wander, GADF dataset with noise and baseline wander, GASF dataset with noise and baseline wander removed, and GADF dataset with noise and baseline wander removed, respectively. Most importantly, this work opens the floor for innovation in wearable devices to measure lead II ECG (e.g., by a smart watch worn on right wrist, along with a smart patch on left leg), in order to do accurate, real-time, and early detection of inferior wall MI.</description><subject>Algorithms</subject><subject>Arrhythmia</subject><subject>Artificial neural networks</subject><subject>cardiovascular diseases (CVDs)</subject><subject>convolutional neural network (CNN)</subject><subject>Datasets</subject><subject>electrocardiogram (ECG)</subject><subject>Electrocardiography</subject><subject>Feature extraction</subject><subject>Gramian angular difference field (GADF)</subject><subject>Gramian angular summation field (GASF)</subject><subject>Gray scale</subject><subject>Heart attacks</subject><subject>Lead</subject><subject>Myocardial infarction</subject><subject>myocardial infarction (MI)</subject><subject>Myocardium</subject><subject>Noise</subject><subject>Noise measurement</subject><subject>Real time</subject><subject>Sensor applications</subject><subject>Wearable technology</subject><subject>Wrist</subject><issn>2475-1472</issn><issn>2475-1472</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>RIE</sourceid><recordid>eNpNkLtOwzAUhiMEElXpCyAGS8wpPk4cJ2whvRAplKEwW659DClpUpx06NuTkg6dzq-j_yJ9nncPdApAk6diPV-tp4yycBqEnIKIrrwRCwX3IRTs-kLfepO23VJKIWaCBnTk_eS1RVc2jrwdG62cKVVF-p9yuiubmsyww0EtXLMjBSpD8pw0lsyz5TNJydKpXalqktZfh0o5siixMv6LatEQNvOz1Yqk-71rlP6-826sqlqcnO_Y-1zMP7JXv3hf5lla-BqE6PzYaKCxgQ03CrgArSINCY00s6jB8IQDcmCIlkLCMYlUglEMYJW12m7iYOw9Dr397O8B205um4Or-0kZAGWJ4DSIehcbXNo1bevQyr0rd8odJVB54ir_ucoTV3nm2ocehlCJiBeBKIwFS4I_YBVyZw</recordid><startdate>20241001</startdate><enddate>20241001</enddate><creator>Yousuf, Asim</creator><creator>Hafiz, Rehan</creator><creator>Riaz, Saqib</creator><creator>Farooq, Muhammad</creator><creator>Riaz, Kashif</creator><creator>Rahman, Muhammad Mahboob Ur</creator><general>IEEE</general><general>The Institute of Electrical and Electronics Engineers, Inc. (IEEE)</general><scope>97E</scope><scope>RIA</scope><scope>RIE</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7SP</scope><scope>8FD</scope><scope>L7M</scope><orcidid>https://orcid.org/0000-0002-5062-3068</orcidid><orcidid>https://orcid.org/0000-0002-6768-0886</orcidid><orcidid>https://orcid.org/0000-0001-5000-0402</orcidid><orcidid>https://orcid.org/0000-0001-6141-079X</orcidid></search><sort><creationdate>20241001</creationdate><title>Inferior Myocardial Infarction Detection From Lead II of ECG: A Gramian Angular Field-Based 2D-CNN Approach</title><author>Yousuf, Asim ; Hafiz, Rehan ; Riaz, Saqib ; Farooq, Muhammad ; Riaz, Kashif ; Rahman, Muhammad Mahboob Ur</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c177t-8dc108d1b5da1571ca6c1906c2fec1d5951e512eef0195e96a9e6811faffcfb83</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Algorithms</topic><topic>Arrhythmia</topic><topic>Artificial neural networks</topic><topic>cardiovascular diseases (CVDs)</topic><topic>convolutional neural network (CNN)</topic><topic>Datasets</topic><topic>electrocardiogram (ECG)</topic><topic>Electrocardiography</topic><topic>Feature extraction</topic><topic>Gramian angular difference field (GADF)</topic><topic>Gramian angular summation field (GASF)</topic><topic>Gray scale</topic><topic>Heart attacks</topic><topic>Lead</topic><topic>Myocardial infarction</topic><topic>myocardial infarction (MI)</topic><topic>Myocardium</topic><topic>Noise</topic><topic>Noise measurement</topic><topic>Real time</topic><topic>Sensor applications</topic><topic>Wearable technology</topic><topic>Wrist</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Yousuf, Asim</creatorcontrib><creatorcontrib>Hafiz, Rehan</creatorcontrib><creatorcontrib>Riaz, Saqib</creatorcontrib><creatorcontrib>Farooq, Muhammad</creatorcontrib><creatorcontrib>Riaz, Kashif</creatorcontrib><creatorcontrib>Rahman, Muhammad Mahboob Ur</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 2005-present</collection><collection>IEEE All-Society Periodicals Package (ASPP) 1998-Present</collection><collection>IEEE Electronic Library (IEL)</collection><collection>CrossRef</collection><collection>Electronics & Communications Abstracts</collection><collection>Technology Research Database</collection><collection>Advanced Technologies Database with Aerospace</collection><jtitle>IEEE sensors letters</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Yousuf, Asim</au><au>Hafiz, Rehan</au><au>Riaz, Saqib</au><au>Farooq, Muhammad</au><au>Riaz, Kashif</au><au>Rahman, Muhammad Mahboob Ur</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Inferior Myocardial Infarction Detection From Lead II of ECG: A Gramian Angular Field-Based 2D-CNN Approach</atitle><jtitle>IEEE sensors letters</jtitle><stitle>LSENS</stitle><date>2024-10-01</date><risdate>2024</risdate><volume>8</volume><issue>10</issue><spage>1</spage><epage>4</epage><pages>1-4</pages><issn>2475-1472</issn><eissn>2475-1472</eissn><coden>ISLECD</coden><abstract>This letter presents a novel method for inferior myocardial infarction (MI) detection using lead II of electrocardiogram (ECG). We evaluate our proposed method on a public dataset, namely, Physikalisch Technische Bundesanstalt (PTB) ECG dataset from PhysioNet. Under our proposed method, we first clean the noisy ECG signals using db4 wavelet, followed by an R-peak detection algorithm to segment the ECG signals into beats. We then translate the ECG timeseries dataset to an equivalent dataset of grayscale images using Gramian angular summation field (GASF) and Gramian angular difference field (GADF) operations. Subsequently, the grayscale images are fed into a custom 2-D convolutional neural network (CNN), which efficiently differentiates between a healthy subject and a subject with MI. Our proposed approach achieves an average classification accuracy of 99.68%, 99.80%, 99.82%, and 99.84% under GASF dataset with noise and baseline wander, GADF dataset with noise and baseline wander, GASF dataset with noise and baseline wander removed, and GADF dataset with noise and baseline wander removed, respectively. Most importantly, this work opens the floor for innovation in wearable devices to measure lead II ECG (e.g., by a smart watch worn on right wrist, along with a smart patch on left leg), in order to do accurate, real-time, and early detection of inferior wall MI.</abstract><cop>Piscataway</cop><pub>IEEE</pub><doi>10.1109/LSENS.2024.3450176</doi><tpages>4</tpages><orcidid>https://orcid.org/0000-0002-5062-3068</orcidid><orcidid>https://orcid.org/0000-0002-6768-0886</orcidid><orcidid>https://orcid.org/0000-0001-5000-0402</orcidid><orcidid>https://orcid.org/0000-0001-6141-079X</orcidid></addata></record> |
fulltext | fulltext_linktorsrc |
identifier | ISSN: 2475-1472 |
ispartof | IEEE sensors letters, 2024-10, Vol.8 (10), p.1-4 |
issn | 2475-1472 2475-1472 |
language | eng |
recordid | cdi_ieee_primary_10648729 |
source | IEEE Electronic Library (IEL) |
subjects | Algorithms Arrhythmia Artificial neural networks cardiovascular diseases (CVDs) convolutional neural network (CNN) Datasets electrocardiogram (ECG) Electrocardiography Feature extraction Gramian angular difference field (GADF) Gramian angular summation field (GASF) Gray scale Heart attacks Lead Myocardial infarction myocardial infarction (MI) Myocardium Noise Noise measurement Real time Sensor applications Wearable technology Wrist |
title | Inferior Myocardial Infarction Detection From Lead II of ECG: A Gramian Angular Field-Based 2D-CNN Approach |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-11-30T04%3A31%3A21IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_RIE&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Inferior%20Myocardial%20Infarction%20Detection%20From%20Lead%20II%20of%20ECG:%20A%20Gramian%20Angular%20Field-Based%202D-CNN%20Approach&rft.jtitle=IEEE%20sensors%20letters&rft.au=Yousuf,%20Asim&rft.date=2024-10-01&rft.volume=8&rft.issue=10&rft.spage=1&rft.epage=4&rft.pages=1-4&rft.issn=2475-1472&rft.eissn=2475-1472&rft.coden=ISLECD&rft_id=info:doi/10.1109/LSENS.2024.3450176&rft_dat=%3Cproquest_RIE%3E3102975036%3C/proquest_RIE%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=3102975036&rft_id=info:pmid/&rft_ieee_id=10648729&rfr_iscdi=true |