Segmentation of abdominal organs in computed tomography using a generalized statistical shape model. (December 2019)

• Record Type: Journal Article
• Authors: Krasoń, Agata; Woloshuk, Andre; Spinczyk, Dominik
• Is Part Of: Computerized medical imaging and graphics. Volume 78(2019)
• Publication Date: 2019-12
• Subjects: Generalized statistical shape model -- Abdominal anatomy segmentation; Diagnostic imaging -- Periodicals; Imaging systems in medicine -- Periodicals; Diagnosis, Radioscopic -- Data processing -- Periodicals; Diagnostic Imaging -- Periodicals; Imagerie pour le diagnostic -- Périodiques; Diagnostic imaging; Periodicals; Electronic journals; Electronic journals; 616.0754
• DOI: 10.1016/j.compmedimag.2019.101672
• Languages: English
• ISSNs: 0895-6111

Abstract

Highlights: The general segmentation method has been presented, not requiring the selection of specific parameter. The usability the generalized statistical shape model for segmentation of abdominal anatomical structures was presented. The method has obtained better results for a diverse group of parenchymal organs. Abstract: Segmentation of anatomical structures in computed tomography images remains an important stage in computer-aided diagnostics and therapy. Due to the complexity of anatomical structures in the abdominal cavity, the occurrence of anatomical variants and pathological changes of organs in computed tomography images, segmentation is still treated as a current research problem. The paper presents the segmentation method based on the generalized statistical shape model. The method was tested in the application to segmentation based on 40 cases of computed tomography with contrast: 20 cases were included in training set and 20 in the testing set. For each case, expert outlines were made for the following organs: spleen, kidney, liver, pancreas, and duodenum. The following average results of the DICE coefficient were obtained: 0.96, 093, 0.88, 0.86, 0.81. The obtained results on the developed method can be treated as a step towards a universal method of segmentation in normalized scaled images, because the method does not require the selection of new parameter values when applied to the segmentation of a diverse group of parenchymal anatomical organs.