Abstract. This paper describes a comprehensive multi-step algorithm for vascular structure segmentation in CT scan data, from raw slice images to a 3D object, with an emphasis on improving segmentation quality and assessing computational complexity. To estimate initial image quality and to evaluate denoising in the absence of the noise-free image, we propose a semi-global contrast-to-noise quality metric. We show that total variation-based filtering in the metric results in the best denoising when compared to widely used nonlocal means or anisotropic diffusion denoising. To address higher computational complexity of our denoising algorithm, we created two high performance implementations, using Intel MIC and NVIDIA CUDA and compared results. In combination with proposed nearly real-time incremental segmentation technique, it provides fast and framework with controlled quality.
Abstract. Anatomical structure segmentation on computed tomography (CT) is the key stage in medical visualization and computer diagnosis. Tumors are one of types of internal structures, for which the problem of automatic segmentation today has no solution fully satisfying by quality. The reason is high variance of tumor's density and inability of using a priori anatomical information about shape. In this paper we propose automatic method of liver tumors segmentation based on convolution neural nets (CNN). Studying and validation have been performed on set of CT with liver and tumors segmentation ground truth. Average error (VOE) by cross-validation is 17.3%. Also there were considered algorithms of pre-and post-processing which increase accuracy and performance of segmentation procedure. Particularly the acceleration of the segmentation procedure with negligible decrease of quality has been reached 6 times.
Anatomical structure segmentation on computed tomography (CT) is the key stage in medical visualization and computer diagnosis. Tumors are one of types of internal structures, for which the problem of automatic segmentation today has no solution fully satisfying by quality. The reason is high variance of tumor’s density and inability of using a priori anatomical information about shape. In this paper we propose automatic method of liver tumors segmentation based on convolution neural nets (CNN). Studying and validation have been performed on set of CT with liver and tumors segmentation ground truth. Average error (VOE) by cross-validation is 17.3%. Also there were considered algorithms of pre- and post-processing which increase accuracy and performance of segmentation procedure. Particularly the acceleration of the segmentation procedure with negligible decrease of quality has been reached 6 times.
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.