3D statistical shape models for automatic segmentation of the fetal cerebellum in ultrasound images


Por: Velásquez-Rodríguez, GAR, Fanti-Gutiérrez, Z, Torres, F, Medina-Bañuelos, V, Escalante-Ramírez, B, Marín, LC, Huerta, MG, Cosío, FA

Publicada: 1 ene 2025
Resumen:
The cerebellum is an important structure to determine fetal development because its volume has a high correlation with gestational age. Manual annotation of the cerebellum in 3D ultrasound images (to measure the cerebellar volume) requires highly trained experts to perform a time-consuming task. To assist in this task, we developed a totally automatic system for the 3D segmentation of the cerebellum in ultrasound images of the fetal brain, using a 3D Point Distribution Model (PDM) obtained from another statistical shape model based on a spherical harmonics (SPHARMs) representation, which provides a very efficient basis for the construction of statistical shape models of 3D organs with a spherical topology. Our PDM of the fetal cerebellum was automatically adjusted with the optimization of an objective function based on gray level voxel profiles, using a genetic algorithm. An automatic initialization and plane selection scheme was also developed, based on the detection of the cerebellum on each plane by a convolutional neural network (YOLO v2). Our results of the 3D segmentation of 18 ultrasound volumes of the fetal brain are: Dice coefficient of 0.83 +/- 0.10 and Hausdorff distance of 3.61 +/- 0.83 mm. The methods reported show potential to successfully assist the experts in the assessment of fetal growth in ultrasound volumes.

Filiaciones:
Velásquez-Rodríguez, GAR:
 Univ Nacl Autonoma Mexico, Postgrad Program Elect Engn, Ciudad Univ, Mexico City 04510, Mexico

Fanti-Gutiérrez, Z:
 Univ Nacl Autonoma Mexico, Inst Invest Matemat Aplicadas & Sistemas, Ciudad Univ, Mexico City 04510, Mexico

Torres, F:
 Univ Nacl Autonoma Mexico, Inst Fis, Ciudad Univ, Mexico City 04510, Mexico

Medina-Bañuelos, V:
 Univ Autonoma Metropolitana Iztapalapa, Div Ciencias Basicas & Ingn, Mexico City 09340, Mexico

Escalante-Ramírez, B:
 Univ Nacl Autonoma Mexico, Fac Ingn, Ciudad Univ, Mexico City 04510, Mexico

Marín, LC:
 Natl Inst Perinatol, Dept Translat Med, Mexico City 11000, Mexico

Huerta, MG:
 Natl Inst Perinatol, Dept Translat Med, Mexico City 11000, Mexico

Cosío, FA:
 Univ Nacl Autonoma Mexico, Unidad Acad IIMAS Yucatan, Inst Invest Matemat Aplicadas & Sistemas IIMAS, Merida 97205, Yucatan, Mexico
ISSN: 18631703
Editorial
SPRINGER LONDON LTD, 236 GRAYS INN RD, 6TH FLOOR, LONDON WC1X 8HL, ENGLAND, Reino Unido
Tipo de documento: Article
Volumen: 19 Número: 1
Páginas:
WOS Id: 001371385500006