Desempeño de la segmentación automática de líquido libre abdominal en tomografía con redes neuronales.
Saved in:
| Title: | Desempeño de la segmentación automática de líquido libre abdominal en tomografía con redes neuronales. |
|---|---|
| Alternate Title: | Performance of automatic segmentation of abdominal free fluid in tomography using neural networks. |
| Authors: | Acevedo-Ruiz-Esparza, Blanca A.1 azul8223@gmail.com, Sánchez-Cruz, Hermilo2, Murillo-Ortiz, Blanca O.3, Muñoz-Zavala, Ángel E.2, Hernández-Trinidad, Arón4, Guzmán-Cabrera, Rafael4, Córdova-Fraga, Teodoro4, Campos-Escoto, María G.5 |
| Source: | Anales de Radiologia, Mexico. ene-mar2025, Vol. 24 Issue 1, p10-24. 15p. |
| Subjects: | ASCITIC fluids, DEEP learning, COMPUTED tomography, PROGNOSTIC tests, ARTIFICIAL intelligence |
| Abstract (English): | Objective: To create a fully automated and fast-segmentation tool for peritoneal free fluid using deep learning. Method: Dataset of CT images of 30 patients with peritoneal free fluid were assembled. Ground truth segmentation of peritoneal free fluid was performed manually. Automatic segmentation was achieved with 3D U-Net. Results: Our neural network achieves a dice coefficient of 0.79. Conclusions: The proposed neural network helps to segment the peritoneal free fluid accurately, providing information about patientspecific density fluid and volume. With results showing a mean difference of 226 ml, with the help of 3D U-Net fully automatic segmentation of peritoneal free fluid on CT scans can be performed in milliseconds. A fully automatic segmentation system makes peritoneal free fluid segmentation a valuable tool for treatment and prognostic planning. [ABSTRACT FROM AUTHOR] |
| Abstract (Spanish): | Objetivo: Crear una herramienta automatizada, de segmentación rápida para líquido libre peritoneal usando aprendizaje profundo. Método: Se recopiló un conjunto de datos de imágenes de tomografía computarizada de 30 pacientes con líquido libre peritoneal. La segmentación de referencia se realizó manualmente y la automática con 3D U-Net. Resultados: Nuestra red tiene un coeficiente de Dice de 0.79 e IoU de 0.68. Conclusiones: La red neuronal propuesta es una herramienta útil para la segmentación del líquido libre peritoneal, proporcionando información específica sobre la densidad y volumen del líquido en los pacientes, con una diferencia media de 226 ml, con la arquitectura 3D U-Net, la segmentación automática del líquido libre peritoneal se puede realizar en cuestión de milisegundos. Este esquema de segmentación completamente automática convierte el proceso en una herramienta valiosa para la planificación del tratamiento y el pronóstico de diversas enfermedades. [ABSTRACT FROM AUTHOR] |
| Copyright of Anales de Radiologia, Mexico is the property of Sociedad Mexicana de Radiologia e Imagen A.C. and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | MedicLatina |
| FullText | Links: – Type: pdflink Text: Availability: 0 |
|---|---|
| Header | DbId: lth DbLabel: MedicLatina An: 185145722 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: Desempeño de la segmentación automática de líquido libre abdominal en tomografía con redes neuronales. – Name: TitleAlt Label: Alternate Title Group: TiAlt Data: Performance of automatic segmentation of abdominal free fluid in tomography using neural networks. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Acevedo-Ruiz-Esparza%2C+Blanca+A%2E%22">Acevedo-Ruiz-Esparza, Blanca A.</searchLink><relatesTo>1</relatesTo><i> azul8223@gmail.com</i><br /><searchLink fieldCode="AR" term="%22Sánchez-Cruz%2C+Hermilo%22">Sánchez-Cruz, Hermilo</searchLink><relatesTo>2</relatesTo><br /><searchLink fieldCode="AR" term="%22Murillo-Ortiz%2C+Blanca+O%2E%22">Murillo-Ortiz, Blanca O.</searchLink><relatesTo>3</relatesTo><br /><searchLink fieldCode="AR" term="%22Muñoz-Zavala%2C+Ángel+E%2E%22">Muñoz-Zavala, Ángel E.</searchLink><relatesTo>2</relatesTo><br /><searchLink fieldCode="AR" term="%22Hernández-Trinidad%2C+Arón%22">Hernández-Trinidad, Arón</searchLink><relatesTo>4</relatesTo><br /><searchLink fieldCode="AR" term="%22Guzmán-Cabrera%2C+Rafael%22">Guzmán-Cabrera, Rafael</searchLink><relatesTo>4</relatesTo><br /><searchLink fieldCode="AR" term="%22Córdova-Fraga%2C+Teodoro%22">Córdova-Fraga, Teodoro</searchLink><relatesTo>4</relatesTo><br /><searchLink fieldCode="AR" term="%22Campos-Escoto%2C+María+G%2E%22">Campos-Escoto, María G.</searchLink><relatesTo>5</relatesTo> – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22Anales+de+Radiologia%2C+Mexico%22">Anales de Radiologia, Mexico</searchLink>. ene-mar2025, Vol. 24 Issue 1, p10-24. 15p. – Name: Subject Label: Subjects Group: Su Data: <searchLink fieldCode="DE" term="%22ASCITIC+fluids%22">ASCITIC fluids</searchLink><br /><searchLink fieldCode="DE" term="%22DEEP+learning%22">DEEP learning</searchLink><br /><searchLink fieldCode="DE" term="%22COMPUTED+tomography%22">COMPUTED tomography</searchLink><br /><searchLink fieldCode="DE" term="%22PROGNOSTIC+tests%22">PROGNOSTIC tests</searchLink><br /><searchLink fieldCode="DE" term="%22ARTIFICIAL+intelligence%22">ARTIFICIAL intelligence</searchLink> – Name: Abstract Label: Abstract (English) Group: Ab Data: Objective: To create a fully automated and fast-segmentation tool for peritoneal free fluid using deep learning. Method: Dataset of CT images of 30 patients with peritoneal free fluid were assembled. Ground truth segmentation of peritoneal free fluid was performed manually. Automatic segmentation was achieved with 3D U-Net. Results: Our neural network achieves a dice coefficient of 0.79. Conclusions: The proposed neural network helps to segment the peritoneal free fluid accurately, providing information about patientspecific density fluid and volume. With results showing a mean difference of 226 ml, with the help of 3D U-Net fully automatic segmentation of peritoneal free fluid on CT scans can be performed in milliseconds. A fully automatic segmentation system makes peritoneal free fluid segmentation a valuable tool for treatment and prognostic planning. [ABSTRACT FROM AUTHOR] – Name: Abstract Label: Abstract (Spanish) Group: Ab Data: Objetivo: Crear una herramienta automatizada, de segmentación rápida para líquido libre peritoneal usando aprendizaje profundo. Método: Se recopiló un conjunto de datos de imágenes de tomografía computarizada de 30 pacientes con líquido libre peritoneal. La segmentación de referencia se realizó manualmente y la automática con 3D U-Net. Resultados: Nuestra red tiene un coeficiente de Dice de 0.79 e IoU de 0.68. Conclusiones: La red neuronal propuesta es una herramienta útil para la segmentación del líquido libre peritoneal, proporcionando información específica sobre la densidad y volumen del líquido en los pacientes, con una diferencia media de 226 ml, con la arquitectura 3D U-Net, la segmentación automática del líquido libre peritoneal se puede realizar en cuestión de milisegundos. Este esquema de segmentación completamente automática convierte el proceso en una herramienta valiosa para la planificación del tratamiento y el pronóstico de diversas enfermedades. [ABSTRACT FROM AUTHOR] – Name: AbstractSuppliedCopyright Label: Group: Ab Data: <i>Copyright of Anales de Radiologia, Mexico is the property of Sociedad Mexicana de Radiologia e Imagen A.C. and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.) |
| PLink | https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=lth&AN=185145722 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.24875/ARM.240000551 Languages: – Code: spa Text: Spanish PhysicalDescription: Pagination: PageCount: 15 StartPage: 10 Subjects: – SubjectFull: ASCITIC fluids Type: general – SubjectFull: DEEP learning Type: general – SubjectFull: COMPUTED tomography Type: general – SubjectFull: PROGNOSTIC tests Type: general – SubjectFull: ARTIFICIAL intelligence Type: general Titles: – TitleFull: Desempeño de la segmentación automática de líquido libre abdominal en tomografía con redes neuronales. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Acevedo-Ruiz-Esparza, Blanca A. – PersonEntity: Name: NameFull: Sánchez-Cruz, Hermilo – PersonEntity: Name: NameFull: Murillo-Ortiz, Blanca O. – PersonEntity: Name: NameFull: Muñoz-Zavala, Ángel E. – PersonEntity: Name: NameFull: Hernández-Trinidad, Arón – PersonEntity: Name: NameFull: Guzmán-Cabrera, Rafael – PersonEntity: Name: NameFull: Córdova-Fraga, Teodoro – PersonEntity: Name: NameFull: Campos-Escoto, María G. IsPartOfRelationships: – BibEntity: Dates: – D: 01 M: 01 Text: ene-mar2025 Type: published Y: 2025 Identifiers: – Type: issn-print Value: 16652118 Numbering: – Type: volume Value: 24 – Type: issue Value: 1 Titles: – TitleFull: Anales de Radiologia, Mexico Type: main |
| ResultId | 1 |
