Image Analysis System for Early Detection of Cardiothoracic Surgery Wound Alterations Based on Artificial Intelligence Models

Detalhes bibliográficos
Autor(a) principal: Pereira, Catarina
Data de Publicação: 2023
Outros Autores: Guede-Fernández, Federico, Vigário, Ricardo, Coelho, Pedro, Fragata, José, Londral, Ana
Tipo de documento: Artigo
Idioma: eng
Título da fonte: Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
Texto Completo: http://hdl.handle.net/10362/155245
Resumo: Funding Information: This work is part of a research project funded by Fundação para a Ciência e Tecnologia, which aims to design and implement a post-surgical digital telemonitoring service for cardiothoracic surgery patients. The main goals of the research project are: to study the impact of daily telemonitoring on early diagnosis, to reduce hospital readmissions, and to improve patient safety, during the 30-day period after hospital discharge. This remote follow-up involves a digital remote patient monitoring kit which includes a sphygmomanometer, a scale, a smartwatch, and a smartphone, allowing daily patient data collection. One of the daily outcomes was the daily photographs taken by patients regarding surgical wounds. Every day, the clinical team had to analyze the image of each patient, which could take a long time. The automatic analysis of these images would allow implementing an alert related to the detection of wound modifications that could represent a risk of infection. Such an alert would spare time for the clinical team in follow-up care. Funding Information: This research has been supported by Fundação para a Ciência e Tecnologia (FCT) under CardioFollow.AI project (DSAIPA/AI/0094/2020), Lisboa-05-3559-FSE-000003 and UIDB/04559/2020. Publisher Copyright: © 2023 by the authors.
id RCAP_10951450a0dca7ff64c710c5bd4a2d75
oai_identifier_str oai:run.unl.pt:10362/155245
network_acronym_str RCAP
network_name_str Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
repository_id_str 7160
spelling Image Analysis System for Early Detection of Cardiothoracic Surgery Wound Alterations Based on Artificial Intelligence Modelscardiothoracic surgerydeep learningimage analysismachine learningwound infectionMaterials Science(all)InstrumentationEngineering(all)Process Chemistry and TechnologyComputer Science ApplicationsFluid Flow and Transfer ProcessesFunding Information: This work is part of a research project funded by Fundação para a Ciência e Tecnologia, which aims to design and implement a post-surgical digital telemonitoring service for cardiothoracic surgery patients. The main goals of the research project are: to study the impact of daily telemonitoring on early diagnosis, to reduce hospital readmissions, and to improve patient safety, during the 30-day period after hospital discharge. This remote follow-up involves a digital remote patient monitoring kit which includes a sphygmomanometer, a scale, a smartwatch, and a smartphone, allowing daily patient data collection. One of the daily outcomes was the daily photographs taken by patients regarding surgical wounds. Every day, the clinical team had to analyze the image of each patient, which could take a long time. The automatic analysis of these images would allow implementing an alert related to the detection of wound modifications that could represent a risk of infection. Such an alert would spare time for the clinical team in follow-up care. Funding Information: This research has been supported by Fundação para a Ciência e Tecnologia (FCT) under CardioFollow.AI project (DSAIPA/AI/0094/2020), Lisboa-05-3559-FSE-000003 and UIDB/04559/2020. Publisher Copyright: © 2023 by the authors.Cardiothoracic surgery patients have the risk of developing surgical site infections which cause hospital readmissions, increase healthcare costs, and may lead to mortality. This work aims to tackle the problem of surgical site infections by predicting the existence of worrying alterations in wound images with a wound image analysis system based on artificial intelligence. The developed system comprises a deep learning segmentation model (MobileNet-Unet), which detects the wound region area and categorizes the wound type (chest, drain, and leg), and a machine learning classification model, which predicts the occurrence of wound alterations (random forest, support vector machine and k-nearest neighbors for chest, drain, and leg, respectively). The deep learning model segments the image and assigns the wound type. Then, the machine learning models classify the images from a group of color and textural features extracted from the output region of interest to feed one of the three wound-type classifiers that reach the final binary decision of wound alteration. The segmentation model achieved a mean Intersection over Union of 89.9% and a mean average precision of 90.1%. Separating the final classification into different classifiers was more effective than a single classifier for all the wound types. The leg wound classifier exhibited the best results with an 87.6% recall and 52.6% precision.LIBPhys-UNLComprehensive Health Research Centre (CHRC) - pólo NMSNOVA Medical School|Faculdade de Ciências Médicas (NMS|FCM)RUNPereira, CatarinaGuede-Fernández, FedericoVigário, RicardoCoelho, PedroFragata, JoséLondral, Ana2023-07-13T22:17:47Z2023-02-072023-02-07T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/article24application/pdfhttp://hdl.handle.net/10362/155245eng2076-3417PURE: 66015240https://doi.org/10.3390/app13042120info:eu-repo/semantics/openAccessreponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãoinstacron:RCAAP2024-03-11T05:37:47Zoai:run.unl.pt:10362/155245Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-20T03:55:59.541754Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãofalse
dc.title.none.fl_str_mv Image Analysis System for Early Detection of Cardiothoracic Surgery Wound Alterations Based on Artificial Intelligence Models
title Image Analysis System for Early Detection of Cardiothoracic Surgery Wound Alterations Based on Artificial Intelligence Models
spellingShingle Image Analysis System for Early Detection of Cardiothoracic Surgery Wound Alterations Based on Artificial Intelligence Models
Pereira, Catarina
cardiothoracic surgery
deep learning
image analysis
machine learning
wound infection
Materials Science(all)
Instrumentation
Engineering(all)
Process Chemistry and Technology
Computer Science Applications
Fluid Flow and Transfer Processes
title_short Image Analysis System for Early Detection of Cardiothoracic Surgery Wound Alterations Based on Artificial Intelligence Models
title_full Image Analysis System for Early Detection of Cardiothoracic Surgery Wound Alterations Based on Artificial Intelligence Models
title_fullStr Image Analysis System for Early Detection of Cardiothoracic Surgery Wound Alterations Based on Artificial Intelligence Models
title_full_unstemmed Image Analysis System for Early Detection of Cardiothoracic Surgery Wound Alterations Based on Artificial Intelligence Models
title_sort Image Analysis System for Early Detection of Cardiothoracic Surgery Wound Alterations Based on Artificial Intelligence Models
author Pereira, Catarina
author_facet Pereira, Catarina
Guede-Fernández, Federico
Vigário, Ricardo
Coelho, Pedro
Fragata, José
Londral, Ana
author_role author
author2 Guede-Fernández, Federico
Vigário, Ricardo
Coelho, Pedro
Fragata, José
Londral, Ana
author2_role author
author
author
author
author
dc.contributor.none.fl_str_mv LIBPhys-UNL
Comprehensive Health Research Centre (CHRC) - pólo NMS
NOVA Medical School|Faculdade de Ciências Médicas (NMS|FCM)
RUN
dc.contributor.author.fl_str_mv Pereira, Catarina
Guede-Fernández, Federico
Vigário, Ricardo
Coelho, Pedro
Fragata, José
Londral, Ana
dc.subject.por.fl_str_mv cardiothoracic surgery
deep learning
image analysis
machine learning
wound infection
Materials Science(all)
Instrumentation
Engineering(all)
Process Chemistry and Technology
Computer Science Applications
Fluid Flow and Transfer Processes
topic cardiothoracic surgery
deep learning
image analysis
machine learning
wound infection
Materials Science(all)
Instrumentation
Engineering(all)
Process Chemistry and Technology
Computer Science Applications
Fluid Flow and Transfer Processes
description Funding Information: This work is part of a research project funded by Fundação para a Ciência e Tecnologia, which aims to design and implement a post-surgical digital telemonitoring service for cardiothoracic surgery patients. The main goals of the research project are: to study the impact of daily telemonitoring on early diagnosis, to reduce hospital readmissions, and to improve patient safety, during the 30-day period after hospital discharge. This remote follow-up involves a digital remote patient monitoring kit which includes a sphygmomanometer, a scale, a smartwatch, and a smartphone, allowing daily patient data collection. One of the daily outcomes was the daily photographs taken by patients regarding surgical wounds. Every day, the clinical team had to analyze the image of each patient, which could take a long time. The automatic analysis of these images would allow implementing an alert related to the detection of wound modifications that could represent a risk of infection. Such an alert would spare time for the clinical team in follow-up care. Funding Information: This research has been supported by Fundação para a Ciência e Tecnologia (FCT) under CardioFollow.AI project (DSAIPA/AI/0094/2020), Lisboa-05-3559-FSE-000003 and UIDB/04559/2020. Publisher Copyright: © 2023 by the authors.
publishDate 2023
dc.date.none.fl_str_mv 2023-07-13T22:17:47Z
2023-02-07
2023-02-07T00:00:00Z
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
dc.type.driver.fl_str_mv info:eu-repo/semantics/article
format article
status_str publishedVersion
dc.identifier.uri.fl_str_mv http://hdl.handle.net/10362/155245
url http://hdl.handle.net/10362/155245
dc.language.iso.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv 2076-3417
PURE: 66015240
https://doi.org/10.3390/app13042120
dc.rights.driver.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv 24
application/pdf
dc.source.none.fl_str_mv reponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
instacron:RCAAP
instname_str Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
instacron_str RCAAP
institution RCAAP
reponame_str Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
collection Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
repository.name.fl_str_mv Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
repository.mail.fl_str_mv
_version_ 1799138145918255104

Registros relacionados