Abstract-Ultrasound images segmentation is a difficult problem due to speckle noise, low contrast and local changes of intensity. Intensity based methods do not perform particularly well on ultrasound images. However, it has been previously shown that these images respond well to local phase-based methods which are theoretically intensity-invariant. Here, we use level set propagation to capture the left ventricle boundaries. This uses a new speed term based on local phase and local orientation derived from the monogenic signal, which makes the algorithm robust to attenuation artefact. Furthermore, we use Cauchy kernels, instead of the commonly used log-Gabor, as pair of quadrature filters for the feature extraction. Preliminary results show that the proposed method can robustly handle noise, and captures well the low contrast boundaries.
Abstract-Ultrasound images segmentation is a difficult problem due to speckle noise, low contrast and local changes of intensity. Intensity based methods do not perform particularly well on ultrasound images. However, it has been previously shown that these images respond well to local phase-based methods which are theoretically intensity-invariant. Here, we use level set propagation to capture the left ventricle boundaries. This uses a new speed term based on local phase and local orientation derived from the monogenic signal, which makes the algorithm robust to attenuation artefact. Furthermore, we use Cauchy kernels, instead of the commonly used log-Gabor, as pair of quadrature filters for the feature extraction. Preliminary results show that the proposed method can robustly handle noise, and captures well the low contrast boundaries.
This paper presents a new method in a variational level set framework for ultrasound images segmentation. The conventional intensity gradient based methods have had limited success on ultrasound images. Phase based methods, which are theoretically intensity-invariant, offer a good alternative. The proposed approach uses a speed term based on local phase derived from the monogenic signal. In order to confront more the speckle noise and local changes of intensity, the proposed phase based geodesic active contours term is combined with a new local maximum likelihood region term. A Rayleigh probability distribution is considered to model the B-mode ultrasound images intensities. Preliminary results show that the proposed model is robust to attenuation and captures well the low contrast boundaries.
Today, researchers are increasingly using manual, semi-automatic, and automatic segmentation techniques to delimit or extract organs from medical images. Deep learning algorithms are increasingly being used in the area of medical imaging analysis. In comparison to traditional methods, these algorithms are more efficient to obtain compact information, which considerably enhances the quality of medical image analysis system. In this paper, we present a new method to fully automatic segmentation of the sphenoid sinus using a 3D (convolutional neural network). The scarcity of medical data initially forced us through this study to use a 3D CNN model learned on a small data set. To make our method fully automatic, preprocessing and post processing are automated with extraction techniques and mathematical morphologies. The proposed tool is compared to a semi-automatic method and manual deductions performed by a specialist. Preliminary results from CT volumes appear very promising.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.