Automatic segmentation of the fetal cerebellum on 3D ultrasound
نویسندگان
چکیده
In this study we present the development of a 3D statistical shape model (Point Distribution Model PDM), for automatic segmentation, of the fetal cerebellum based on 3D US. This model is adjusted to a fetal 3D ultrasound, using an optimization algorithm which optimizes a model fitting function. A mean Dice Similarity Coefficient of 0.78 was obtained between manual annotations and automatic segmentations of the fetal cerebellum, which is comparable to the Dice Similarity Coefficient obtained between experts. Our results show that this technique is able to automatically segment the cerebellum on 3D ultrasounds of fetal brains with adequate accuracy.
منابع مشابه
Automatic Segmentation of the Cerebellum in Ultrasound Volumes of the Fetal Brain
The size of the cerebellum in ultrasound volumes of the fetal brain has shown a high correlation with gestational age, which makes it a valuable feature to detect fetal growth restrictions. Manual annotation of the 3D surface of the cerebellum in an ultrasound volume is a time consuming task, which needs to be performed by a highly trained expert. In order to assist the experts in the evaluatio...
متن کاملBiological Effect of Modern Fetal Ultrasound Techniques on Human Dermal Fibroblast Cells
Background: Diagnostic ultrasound has been used to detect human disease especially fetus abnormalities in recent decades. Although the harmful effects of diagnostic ultrasound on human have not been established so far, several researchers showed it has had bioeffects in cell lines and in experimental animals. Three-dimensional (3D), four-dimensional (4D), and color Doppler sonography are new te...
متن کاملA hierarchical Convolutional Neural Network for Segmentation of Stroke Lesion in 3D Brain MRI
Introduction: Brain tumors such as glioma are among the most aggressive lesions, which result in a very short life expectancy in patients. Image segmentation is highly essential in medical image analysis with applications, particularly in clinical practices to treat brain tumors. Accurate segmentation of magnetic resonance data is crucial for diagnostic purposes, planning surgical treatments, a...
متن کاملA hierarchical Convolutional Neural Network for Segmentation of Stroke Lesion in 3D Brain MRI
Introduction: Brain tumors such as glioma are among the most aggressive lesions, which result in a very short life expectancy in patients. Image segmentation is highly essential in medical image analysis with applications, particularly in clinical practices to treat brain tumors. Accurate segmentation of magnetic resonance data is crucial for diagnostic purposes, planning surgical treatments, a...
متن کاملSegmentation of embryonic and fetal 3D ultrasound images based on pixel intensity distributions and shape priors
This paper presents a novel variational segmentation framework combining shape priors and parametric intensity distribution modeling for extracting the fetal envelope on 3D obstetric ultrasound images. To overcome issues related to poor image quality and missing boundaries, we inject three types of information in the segmentation process: tissue-specific parametric modeling of pixel intensities...
متن کامل