Digital pattern recognition for the identification and classification of hypospadias using artificial intelligence vs experienced pediatric urologist

Objective: To improve hypospadias classification system, we hereby, show the use of machine learning/image recognition to increase objectivity of hypospadias recognition and classification. Hypospadias anatomical variables such as meatal location, quality of urethral plate, glans size, and ventral c...

Full description

Autores:
Fernandez, Nicolas
Lorenzo, Armando J.
Rickard, Mandy
Chua, Michael
Pippi-Salle, Joao L.
Perez Niño, Jaime
Braga, Luis H.
Matava, Clyde
Tipo de recurso:
Article of journal
Fecha de publicación:
2020
Institución:
Pontificia Universidad Javeriana
Repositorio:
Repositorio Universidad Javeriana
Idioma:
eng
OAI Identifier:
oai:repository.javeriana.edu.co:10554/60051
Acceso en línea:
https://www.goldjournal.net/article/S0090-4295(20)31129-8/fulltext
http://hdl.handle.net/10554/60051
https://doi.org/10.1016/j.urology.2020.09.019
Palabra clave:
Article
Artificial Intelligence
Automated Pattern Recognition
Child Urology
Clinical Outcome
Clinician
Data Base
Diagnostic Accuracy
Disease Classification
Functional Assessment
Functional Disease
Human
Hypospadias
Image Analysis
Learning Al
Rights
License
Atribución-NoComercial 4.0 Internacional
id JAVERIANA2_a814951724016004882b2fc8c3bb99ce
oai_identifier_str oai:repository.javeriana.edu.co:10554/60051
network_acronym_str JAVERIANA2
network_name_str Repositorio Universidad Javeriana
repository_id_str
spelling Atribución-NoComercial 4.0 Internacionalhttp://creativecommons.org/licenses/by-nc/4.0/http://purl.org/coar/access_right/c_abf2Fernandez, NicolasLorenzo, Armando J.Rickard, MandyChua, MichaelPippi-Salle, Joao L.Perez Niño, JaimeBraga, Luis H.Matava, ClydePontificia Universidad Javeriana. Facultad de Medicina. Departamento de Cirugía y Especialidades. UrologíaPontificia Universidad Javeriana. Facultad de Medicina. Hospital Universitario San IgnacioPerez Niño, Jaime2022-05-31T17:11:31Z2022-05-31T17:11:31Z2020-09-25https://www.goldjournal.net/article/S0090-4295(20)31129-8/fulltext0090-4295 / 1527-9995 (Electrónico)http://hdl.handle.net/10554/60051https://doi.org/10.1016/j.urology.2020.09.019instname:Pontificia Universidad Javerianareponame:Repositorio Institucional - Pontificia Universidad Javerianarepourl:https://repository.javeriana.edu.coObjective: To improve hypospadias classification system, we hereby, show the use of machine learning/image recognition to increase objectivity of hypospadias recognition and classification. Hypospadias anatomical variables such as meatal location, quality of urethral plate, glans size, and ventral curvature have been identified as predictors for postoperative outcomes but there is still significant subjectivity between evaluators. Materials and Methods: A hypospadias image database with 1169 anonymized images (837 distal and 332 proximal) was used. Images were standardized (ventral aspect of the penis including the glans, shaft, and scrotum) and classified into distal or proximal and uploaded for training with TensorFlow. Data from the training were outputted to TensorBoard, to assess for the loss function. The model was then run on a set of 29 “Test” images randomly selected. Same set of images were distributed among expert clinicians in pediatric urology. Inter- and intrarater analyses were performed using Fleiss Kappa statistical analysis using the same 29 images shown to the algorithm. Results: After training with 627 images, detection accuracy was 60%. With1169 images, accuracy increased to 90%. Inter-rater analysis among expert pediatric urologists was k= 0.86 and intrarater 0.74. Image recognition model emulates the almost perfect inter-rater agreement between experts. Conclusion: Our model emulates expert human classification of patients with distal/proximal hypospadias. Future applicability will be on standardizing the use of these technologies and their clinical applicability. The ability of using variables different than only anatomical will feed deep learning algorithms and possibly better assessments and predictions for surgical outcomes.Q3Q2Neonatos con Hipospadiashttps://orcid.org/0000-0002-9675-5963https://orcid.org/0000-0002-2231-4321Revista Internacional - IndexadaA1NoPDFapplication/pdfengArticleArtificial IntelligenceAutomated Pattern RecognitionChild UrologyClinical OutcomeClinicianData BaseDiagnostic AccuracyDisease ClassificationFunctional AssessmentFunctional DiseaseHumanHypospadiasImage AnalysisLearning AlDigital pattern recognition for the identification and classification of hypospadias using artificial intelligence vs experienced pediatric urologistArtículo de revistahttp://purl.org/coar/resource_type/c_6501264269Urology147ORIGINALa1240.pdfapplication/pdf764090http://repository.javeriana.edu.co/bitstream/10554/60051/1/a1240.pdf9da9814c99b8c4b29150c620d49c3631MD51open accessTHUMBNAILa1240.pdf.jpga1240.pdf.jpgIM Thumbnailimage/jpeg10803http://repository.javeriana.edu.co/bitstream/10554/60051/2/a1240.pdf.jpgc326ae12fb772078d1d653c6234cd311MD52open access10554/60051oai:repository.javeriana.edu.co:10554/600512023-05-08 13:53:39.683Repositorio Institucional - Pontificia Universidad Javerianarepositorio@javeriana.edu.co
dc.title.none.fl_str_mv Digital pattern recognition for the identification and classification of hypospadias using artificial intelligence vs experienced pediatric urologist
title Digital pattern recognition for the identification and classification of hypospadias using artificial intelligence vs experienced pediatric urologist
spellingShingle Digital pattern recognition for the identification and classification of hypospadias using artificial intelligence vs experienced pediatric urologist
Article
Artificial Intelligence
Automated Pattern Recognition
Child Urology
Clinical Outcome
Clinician
Data Base
Diagnostic Accuracy
Disease Classification
Functional Assessment
Functional Disease
Human
Hypospadias
Image Analysis
Learning Al
title_short Digital pattern recognition for the identification and classification of hypospadias using artificial intelligence vs experienced pediatric urologist
title_full Digital pattern recognition for the identification and classification of hypospadias using artificial intelligence vs experienced pediatric urologist
title_fullStr Digital pattern recognition for the identification and classification of hypospadias using artificial intelligence vs experienced pediatric urologist
title_full_unstemmed Digital pattern recognition for the identification and classification of hypospadias using artificial intelligence vs experienced pediatric urologist
title_sort Digital pattern recognition for the identification and classification of hypospadias using artificial intelligence vs experienced pediatric urologist
dc.creator.fl_str_mv Fernandez, Nicolas
Lorenzo, Armando J.
Rickard, Mandy
Chua, Michael
Pippi-Salle, Joao L.
Perez Niño, Jaime
Braga, Luis H.
Matava, Clyde
dc.contributor.author.none.fl_str_mv Fernandez, Nicolas
Lorenzo, Armando J.
Rickard, Mandy
Chua, Michael
Pippi-Salle, Joao L.
Perez Niño, Jaime
Braga, Luis H.
Matava, Clyde
dc.contributor.corporatename.spa.fl_str_mv Pontificia Universidad Javeriana. Facultad de Medicina. Departamento de Cirugía y Especialidades. Urología
Pontificia Universidad Javeriana. Facultad de Medicina. Hospital Universitario San Ignacio
dc.contributor.javerianateacher.none.fl_str_mv Perez Niño, Jaime
dc.subject.spa.fl_str_mv Article
Artificial Intelligence
Automated Pattern Recognition
Child Urology
Clinical Outcome
Clinician
Data Base
Diagnostic Accuracy
Disease Classification
Functional Assessment
Functional Disease
Human
Hypospadias
Image Analysis
Learning Al
topic Article
Artificial Intelligence
Automated Pattern Recognition
Child Urology
Clinical Outcome
Clinician
Data Base
Diagnostic Accuracy
Disease Classification
Functional Assessment
Functional Disease
Human
Hypospadias
Image Analysis
Learning Al
description Objective: To improve hypospadias classification system, we hereby, show the use of machine learning/image recognition to increase objectivity of hypospadias recognition and classification. Hypospadias anatomical variables such as meatal location, quality of urethral plate, glans size, and ventral curvature have been identified as predictors for postoperative outcomes but there is still significant subjectivity between evaluators. Materials and Methods: A hypospadias image database with 1169 anonymized images (837 distal and 332 proximal) was used. Images were standardized (ventral aspect of the penis including the glans, shaft, and scrotum) and classified into distal or proximal and uploaded for training with TensorFlow. Data from the training were outputted to TensorBoard, to assess for the loss function. The model was then run on a set of 29 “Test” images randomly selected. Same set of images were distributed among expert clinicians in pediatric urology. Inter- and intrarater analyses were performed using Fleiss Kappa statistical analysis using the same 29 images shown to the algorithm. Results: After training with 627 images, detection accuracy was 60%. With1169 images, accuracy increased to 90%. Inter-rater analysis among expert pediatric urologists was k= 0.86 and intrarater 0.74. Image recognition model emulates the almost perfect inter-rater agreement between experts. Conclusion: Our model emulates expert human classification of patients with distal/proximal hypospadias. Future applicability will be on standardizing the use of these technologies and their clinical applicability. The ability of using variables different than only anatomical will feed deep learning algorithms and possibly better assessments and predictions for surgical outcomes.
publishDate 2020
dc.date.created.none.fl_str_mv 2020-09-25
dc.date.accessioned.none.fl_str_mv 2022-05-31T17:11:31Z
dc.date.available.none.fl_str_mv 2022-05-31T17:11:31Z
dc.type.local.spa.fl_str_mv Artículo de revista
dc.type.coar.spa.fl_str_mv http://purl.org/coar/resource_type/c_6501
format http://purl.org/coar/resource_type/c_6501
dc.identifier.spa.fl_str_mv https://www.goldjournal.net/article/S0090-4295(20)31129-8/fulltext
dc.identifier.issn.spa.fl_str_mv 0090-4295 / 1527-9995 (Electrónico)
dc.identifier.uri.none.fl_str_mv http://hdl.handle.net/10554/60051
dc.identifier.doi.spa.fl_str_mv https://doi.org/10.1016/j.urology.2020.09.019
dc.identifier.instname.spa.fl_str_mv instname:Pontificia Universidad Javeriana
dc.identifier.reponame.spa.fl_str_mv reponame:Repositorio Institucional - Pontificia Universidad Javeriana
dc.identifier.repourl.spa.fl_str_mv repourl:https://repository.javeriana.edu.co
url https://www.goldjournal.net/article/S0090-4295(20)31129-8/fulltext
http://hdl.handle.net/10554/60051
https://doi.org/10.1016/j.urology.2020.09.019
identifier_str_mv 0090-4295 / 1527-9995 (Electrónico)
instname:Pontificia Universidad Javeriana
reponame:Repositorio Institucional - Pontificia Universidad Javeriana
repourl:https://repository.javeriana.edu.co
dc.language.iso.spa.fl_str_mv eng
language eng
dc.relation.citationstartpage.spa.fl_str_mv 264
dc.relation.citationendpage.spa.fl_str_mv 269
dc.relation.ispartofjournal.spa.fl_str_mv Urology
dc.relation.citationvolume.spa.fl_str_mv 147
dc.rights.licence.*.fl_str_mv Atribución-NoComercial 4.0 Internacional
dc.rights.uri.*.fl_str_mv http://creativecommons.org/licenses/by-nc/4.0/
dc.rights.coar.spa.fl_str_mv http://purl.org/coar/access_right/c_abf2
rights_invalid_str_mv Atribución-NoComercial 4.0 Internacional
http://creativecommons.org/licenses/by-nc/4.0/
http://purl.org/coar/access_right/c_abf2
dc.format.spa.fl_str_mv PDF
dc.format.mimetype.spa.fl_str_mv application/pdf
institution Pontificia Universidad Javeriana
bitstream.url.fl_str_mv http://repository.javeriana.edu.co/bitstream/10554/60051/1/a1240.pdf
http://repository.javeriana.edu.co/bitstream/10554/60051/2/a1240.pdf.jpg
bitstream.checksum.fl_str_mv 9da9814c99b8c4b29150c620d49c3631
c326ae12fb772078d1d653c6234cd311
bitstream.checksumAlgorithm.fl_str_mv MD5
MD5
repository.name.fl_str_mv Repositorio Institucional - Pontificia Universidad Javeriana
repository.mail.fl_str_mv repositorio@javeriana.edu.co
_version_ 1811671331665608704