EUVIMEDEUVIMED entdecken
BeobachtungsstudieOpen Access · CC BY 4.0

Artificial Intelligence to Determine Correct Midsagittal Plane in Dynamic Transperineal Ultrasound

José Antonio García-Mejido iD, Juan Galán-Paez iD, David Solis-Martín iD, Marina Martín-Morán, Carlota Borrero-Gonzalez, Alfonso Fernández-Gomez, Fernando Fernández-Palacín iD, José Antonio Sainz-Bueno iD

Journal of Clinical Ultrasound · 2025

DOI: 10.1002/jcu.24050 ↗

Kurz gefasst

Beobachtungsstudie in der Zeitschrift Journal of Clinical Ultrasound, 2025. Verfasst von José Antonio García-Mejido und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Surgery, Faculty of Medicine, University of Seville, Seville, Spain. Hauptthemen laut MEDLINE: Artificial Intelligence, Pelvic Floor, Machine Learning. Die Arbeit nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: MICIU/AEI/10.13 039/501100011033 (Agencia Estatal de Investigación), FEDER, Agencia Estatal de Investigación.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Purpose

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.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Artificial IntelligencePelvic FloorMachine LearningHumansProspective StudiesUltrasonographyFemaleAdultMaleMiddle AgedReproducibility of ResultsPerineumAgedValsalva ManeuverYoung Adult

Stichwörter der Autor:innen

XGBoostartificial intelligencegradient boostinglevator ani musclemachine learningpelvic floorultrasonography

Autor:innen und Institutionen

  • Department of Surgery, Faculty of Medicine, University of Seville, Seville, Spain.
  • Department of Computer Science and Artificial Intelligence, Faculty of Mathematics, University of Seville, Seville, Spain.
  • Department of Statistics and Operational Research, University of Cadiz, Cadiz, Spain.

ORCID-Profile: José Antonio García-Mejido, Juan Galán-Paez, David Solis-Martín, Fernando Fernández-Palacín, José Antonio Sainz-Bueno

Förderung

  • MICIU/AEI/10.13 039/501100011033 (Agencia Estatal de Investigación)
  • FEDER
  • Agencia Estatal de Investigación

Zitieren

APA

García-Mejido, J. A., Galán-Paez, J., Solis-Martín, D., Martín-Morán, M., Borrero-Gonzalez, C., Fernández-Gomez, A., Fernández-Palacín, F., & Sainz-Bueno, J. A. (2025). Artificial Intelligence to Determine Correct Midsagittal Plane in Dynamic Transperineal Ultrasound. Journal of Clinical Ultrasound. https://doi.org/10.1002/jcu.24050

Vancouver

García-Mejido JA, Galán-Paez J, Solis-Martín D, Martín-Morán M, Borrero-Gonzalez C, Fernández-Gomez A, et al. Artificial Intelligence to Determine Correct Midsagittal Plane in Dynamic Transperineal Ultrasound. Journal of Clinical Ultrasound. 2025. doi:10.1002/jcu.24050

BibTeX
@article{GarcaMejido2025,
  author = {García-Mejido, José Antonio and Galán-Paez, Juan and Solis-Martín, David and Martín-Morán, Marina and Borrero-Gonzalez, Carlota and Fernández-Gomez, Alfonso and Fernández-Palacín, Fernando and Sainz-Bueno, José Antonio},
  title = {Artificial Intelligence to Determine Correct Midsagittal Plane in Dynamic Transperineal Ultrasound},
  journal = {Journal of Clinical Ultrasound},
  year = {2025},
  doi = {10.1002/jcu.24050}
}
Kostenlos starten →