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

• Published in: Signal, image and video processing image and video processing, 2025, Vol.19 (1), Article 81
• Main Authors: Velásquez-Rodríguez, Gustavo A.R., Fanti-Gutiérrez, Zian, Torres, Fabián, Medina-Bañuelos, Verónica, Escalante-Ramírez, Boris, Camargo Marín, Lisbeth, Guzmán Huerta, Mario, Arámbula Cosío, Fernando
• Format: Article
• Language: English
• Subjects: Annotations; Artificial neural networks; Brain; Cerebellum; Computer Imaging; Computer Science; Genetic algorithms; Image Processing and Computer Vision; Image segmentation; Metric space; Multimedia Information Systems; Original Paper; Pattern Recognition and Graphics; Signal,Image and Speech Processing; Spherical harmonics; Topology optimization; Ultrasonic imaging; Vision
• ISSN: 1863-1703; 1863-1711
• DOI: 10.1007/s11760-024-03615-1

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.