Show simple item record

dc.contributor.authorGarcía-Mejido, José Antonio
dc.contributor.authorGalán Paez, Juan
dc.contributor.authorSolís Martín, David
dc.contributor.authorMartín Morán, Marina
dc.contributor.authorBorrero-Gonzalez, Carlota
dc.contributor.authorFernández-Gómez, Alfonso
dc.contributor.authorFernández Palacín, Fernando 
dc.contributor.authorSainz Bueno, José Antonio
dc.contributor.otherEstadística e Investigación Operativaes_ES
dc.date.accessioned2025-11-12T08:59:45Z
dc.date.available2025-11-12T08:59:45Z
dc.date.issued2025-04-25
dc.identifier.issn1097-0096
dc.identifier.issn0091-2751
dc.identifier.urihttp://hdl.handle.net/10498/37871
dc.description.abstractPurpose To create and validate a machine learning(ML) model that allows for identifying the correct capture of the midsagittal plane in a dynamic ultrasound study, as well as establishing its concordance with a senior explorer and a junior explorer. Methods Observational and prospective study with 90 patients without pelvic floor pathology. Each patient was given an ultrasound video where the midsagittal plane of the pelvic floor was recorded at rest and during the Valsalva maneuver. A segmentation model was used that was trained on a previously published article, generating the segmentations of the 90 new videos to create the model. The algorithm selected to build the model in this project was XGBoost(Gradient Boosting). To obtain a tabular dataset on which to train the model, feature engineering was carried out on the raw segmentation data. The concordance of the model, of a junior examiner and a senior examiner, with the expert examiner was studied using the kappa index. Results The first 60 videos were used to train the model and the last 30 videos were reserved for the test set. The model presented a kappa index 0.930(p < 0.001) with very good agreement for detection of the correct midsagittal plane. The junior explorer presented a very good agreement (kappa index = 0.930(p < 0.001)). The senior explorer presented a kappa index 0.789(p < 0.001) (good agreement) for detection of the correct midsagittal plane. Conclusion We have developed a model that allows determining the correct midsagittal plane captured through dynamic transperineal ultrasound with a level of agreement comparable to or greater than that of a junior or senior examiner, using expert examiner assessment as the gold standard.es_ES
dc.formatapplication/pdfes_ES
dc.language.isoenges_ES
dc.publisherWileyes_ES
dc.rightsAtribución 4.0 Internacional*
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/*
dc.sourceJournal of Clinical Ultrasound, Vol. 53, Núm. 7, 2025, pp. 1470-1478es_ES
dc.subjectartificial intelligencees_ES
dc.subjectgradient boostinges_ES
dc.subjectlevator ani musclees_ES
dc.subjectmachine learninges_ES
dc.subjectpelvic floores_ES
dc.subjectultrasonographyes_ES
dc.subjectXGBoostes_ES
dc.titleArtificial Intelligence to Determine Correct Midsagittal Plane in Dynamic Transperineal Ultrasoundes_ES
dc.typejournal articlees_ES
dc.rights.accessRightsopen accesses_ES
dc.identifier.doi10.1002/JCU.24050
dc.relation.projectIDMICIU/AEI/10.13 039/501100011033es_ES
dc.type.hasVersionVoRes_ES


Files in this item

This item appears in the following Collection(s)

Show simple item record

Atribución 4.0 Internacional
This work is under a Creative Commons License Atribución 4.0 Internacional