Accuracy of artificial intelligence software for the detection of confirmed pleural effusion in thoracic radiographs in dogs
Autor(a) principal: | |
---|---|
Data de Publicação: | 2022 |
Outros Autores: | , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UNESP |
Texto Completo: | http://dx.doi.org/10.1111/vru.13089 http://hdl.handle.net/11449/239914 |
Resumo: | The use of artificial intelligence (AI) algorithms in diagnostic radiology is a developing area in veterinary medicine and may provide substantial benefit in many clinical settings. These range from timely image interpretation in the emergency setting when no boarded radiologist is available to allowing boarded radiologists to focus on more challenging cases that require complex medical decision making. Testing the performance of artificial intelligence (AI) software in veterinary medicine is at its early stages, and only a scant number of reports of validation of AI software have been published. The purpose of this study was to investigate the performance of an AI algorithm (Vetology AI®) in the detection of pleural effusion in thoracic radiographs of dogs. In this retrospective, diagnostic case–controlled study, 62 canine patients were recruited. A control group of 21 dogs with normal thoracic radiographs and a sample group of 41 dogs with confirmed pleural effusion were selected from the electronic medical records at the Cummings School of Veterinary Medicine. The images were cropped to include only the area of interest (i.e., thorax). The software then classified images into those with pleural effusion and those without. The AI algorithm was able to determine the presence of pleural effusion with 88.7% accuracy (P < 0.05). The sensitivity and specificity were 90.2% and 81.8%, respectively (positive predictive value, 92.5%; negative predictive value, 81.8%). The application of this technology in the diagnostic interpretation of thoracic radiographs in veterinary medicine appears to be of value and warrants further investigation and testing. |
id |
UNSP_c1a8e7c4e9bc4cbedc61936cdca3d9aa |
---|---|
oai_identifier_str |
oai:repositorio.unesp.br:11449/239914 |
network_acronym_str |
UNSP |
network_name_str |
Repositório Institucional da UNESP |
repository_id_str |
2946 |
spelling |
Accuracy of artificial intelligence software for the detection of confirmed pleural effusion in thoracic radiographs in dogscanineconvolutional neural networkdogimaging algorithmsmachine learningpleural effusionradiographthoraxX-rayThe use of artificial intelligence (AI) algorithms in diagnostic radiology is a developing area in veterinary medicine and may provide substantial benefit in many clinical settings. These range from timely image interpretation in the emergency setting when no boarded radiologist is available to allowing boarded radiologists to focus on more challenging cases that require complex medical decision making. Testing the performance of artificial intelligence (AI) software in veterinary medicine is at its early stages, and only a scant number of reports of validation of AI software have been published. The purpose of this study was to investigate the performance of an AI algorithm (Vetology AI®) in the detection of pleural effusion in thoracic radiographs of dogs. In this retrospective, diagnostic case–controlled study, 62 canine patients were recruited. A control group of 21 dogs with normal thoracic radiographs and a sample group of 41 dogs with confirmed pleural effusion were selected from the electronic medical records at the Cummings School of Veterinary Medicine. The images were cropped to include only the area of interest (i.e., thorax). The software then classified images into those with pleural effusion and those without. The AI algorithm was able to determine the presence of pleural effusion with 88.7% accuracy (P < 0.05). The sensitivity and specificity were 90.2% and 81.8%, respectively (positive predictive value, 92.5%; negative predictive value, 81.8%). The application of this technology in the diagnostic interpretation of thoracic radiographs in veterinary medicine appears to be of value and warrants further investigation and testing.Department Clinical Sciences Tufts University Cummings School of Veterinary MedicineDepartment of Biostatistics São Paulo State University. R. Prof. Dr. Antônio Celso Wagner ZaninDepartment of Biostatistics São Paulo State University. R. Prof. Dr. Antônio Celso Wagner ZaninTufts University Cummings School of Veterinary MedicineUniversidade Estadual Paulista (UNESP)Müller, Thiago RinaldiSolano, MauricioTsunemi, Mirian Harumi [UNESP]2023-03-01T19:53:05Z2023-03-01T19:53:05Z2022-01-01info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articlehttp://dx.doi.org/10.1111/vru.13089Veterinary Radiology and Ultrasound.1740-82611058-8183http://hdl.handle.net/11449/23991410.1111/vru.130892-s2.0-85128560964Scopusreponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPengVeterinary Radiology and Ultrasoundinfo:eu-repo/semantics/openAccess2023-03-01T19:53:05Zoai:repositorio.unesp.br:11449/239914Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462024-08-05T18:05:17.439950Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false |
dc.title.none.fl_str_mv |
Accuracy of artificial intelligence software for the detection of confirmed pleural effusion in thoracic radiographs in dogs |
title |
Accuracy of artificial intelligence software for the detection of confirmed pleural effusion in thoracic radiographs in dogs |
spellingShingle |
Accuracy of artificial intelligence software for the detection of confirmed pleural effusion in thoracic radiographs in dogs Müller, Thiago Rinaldi canine convolutional neural network dog imaging algorithms machine learning pleural effusion radiograph thorax X-ray |
title_short |
Accuracy of artificial intelligence software for the detection of confirmed pleural effusion in thoracic radiographs in dogs |
title_full |
Accuracy of artificial intelligence software for the detection of confirmed pleural effusion in thoracic radiographs in dogs |
title_fullStr |
Accuracy of artificial intelligence software for the detection of confirmed pleural effusion in thoracic radiographs in dogs |
title_full_unstemmed |
Accuracy of artificial intelligence software for the detection of confirmed pleural effusion in thoracic radiographs in dogs |
title_sort |
Accuracy of artificial intelligence software for the detection of confirmed pleural effusion in thoracic radiographs in dogs |
author |
Müller, Thiago Rinaldi |
author_facet |
Müller, Thiago Rinaldi Solano, Mauricio Tsunemi, Mirian Harumi [UNESP] |
author_role |
author |
author2 |
Solano, Mauricio Tsunemi, Mirian Harumi [UNESP] |
author2_role |
author author |
dc.contributor.none.fl_str_mv |
Tufts University Cummings School of Veterinary Medicine Universidade Estadual Paulista (UNESP) |
dc.contributor.author.fl_str_mv |
Müller, Thiago Rinaldi Solano, Mauricio Tsunemi, Mirian Harumi [UNESP] |
dc.subject.por.fl_str_mv |
canine convolutional neural network dog imaging algorithms machine learning pleural effusion radiograph thorax X-ray |
topic |
canine convolutional neural network dog imaging algorithms machine learning pleural effusion radiograph thorax X-ray |
description |
The use of artificial intelligence (AI) algorithms in diagnostic radiology is a developing area in veterinary medicine and may provide substantial benefit in many clinical settings. These range from timely image interpretation in the emergency setting when no boarded radiologist is available to allowing boarded radiologists to focus on more challenging cases that require complex medical decision making. Testing the performance of artificial intelligence (AI) software in veterinary medicine is at its early stages, and only a scant number of reports of validation of AI software have been published. The purpose of this study was to investigate the performance of an AI algorithm (Vetology AI®) in the detection of pleural effusion in thoracic radiographs of dogs. In this retrospective, diagnostic case–controlled study, 62 canine patients were recruited. A control group of 21 dogs with normal thoracic radiographs and a sample group of 41 dogs with confirmed pleural effusion were selected from the electronic medical records at the Cummings School of Veterinary Medicine. The images were cropped to include only the area of interest (i.e., thorax). The software then classified images into those with pleural effusion and those without. The AI algorithm was able to determine the presence of pleural effusion with 88.7% accuracy (P < 0.05). The sensitivity and specificity were 90.2% and 81.8%, respectively (positive predictive value, 92.5%; negative predictive value, 81.8%). The application of this technology in the diagnostic interpretation of thoracic radiographs in veterinary medicine appears to be of value and warrants further investigation and testing. |
publishDate |
2022 |
dc.date.none.fl_str_mv |
2022-01-01 2023-03-01T19:53:05Z 2023-03-01T19:53:05Z |
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://dx.doi.org/10.1111/vru.13089 Veterinary Radiology and Ultrasound. 1740-8261 1058-8183 http://hdl.handle.net/11449/239914 10.1111/vru.13089 2-s2.0-85128560964 |
url |
http://dx.doi.org/10.1111/vru.13089 http://hdl.handle.net/11449/239914 |
identifier_str_mv |
Veterinary Radiology and Ultrasound. 1740-8261 1058-8183 10.1111/vru.13089 2-s2.0-85128560964 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
Veterinary Radiology and Ultrasound |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.source.none.fl_str_mv |
Scopus reponame:Repositório Institucional da UNESP instname:Universidade Estadual Paulista (UNESP) instacron:UNESP |
instname_str |
Universidade Estadual Paulista (UNESP) |
instacron_str |
UNESP |
institution |
UNESP |
reponame_str |
Repositório Institucional da UNESP |
collection |
Repositório Institucional da UNESP |
repository.name.fl_str_mv |
Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP) |
repository.mail.fl_str_mv |
|
_version_ |
1808128892454567936 |