3D Segmentation Algorithms for Computerized Tomographic Imaging: a Systematic Literature Review

Abstract

This paper presents a systematic literature review concerning 3D segmentation algorithms for computerized tomographic imaging. This analysis covers articles published in the range 2006-March 2018 found in four scientific databases (Science Direct, IEEEXplore, ACM, and PubMed), using the methodology for systematic review proposed by Kitchenham. We present the analyzed segmentation methods categorized according to its application, algorithmic strategy, validation, and use of prior knowledge, as well as its general conceptual description. Additionally, we present a general overview, discussions, and further prospects for the 3D segmentation methods applied for tomographic images.

Analysis of Surface Extraction Methods Based on Gradient Operators for Computed Tomography in Metrology Applications

“…This process is mainly affected by the methodology used to locate the surface and by the algorithm used in the process of forming it. The location of the surface for metrological applications is generally based on the definition of a gray value as a characteristic of similarity to define the regions of interest [6]. This gray value threshold is mainly dependent on the properties of the material, the thickness of the piece, and the radiation intensity that is used in the CT data acquisition; therefore, a standard value cannot be determined as it is done in medical applications.…”

Multi-Resolution Texture-Based 3D Level Set Segmentation

“…The resulting quality and runtime performance was compared with the WELS and IGAC algorithms, since both of those methods are used for medical image segmentation. Although the accuracy of the outcomes is the ultimate goal for medical applications [40], [41], the complexity and time performance of the algorithms is also an important factor, especially considering the size of 3D imaging data [3].…”

Multi-modal image analysis for semi-automatic segmentation of the total liver and liver arterial perfusion territories for radioembolization

“…Image registration accuracy has been investigated for CT to CT liver registration for contrast-enhanced diagnostic CTs [38]. Over the past decade, numerous semi-automatic and automatic approaches for liver segmentation [39,40] on CT that rely on histogrambased methods [41,42], graph cut [43][44][45], region growing [45][46][47], geometric deformable model and level set [48][49][50], probabilistic atlas [51,52], statistical shape models [53][54][55], and recently neural network [56][57][58][59] have been proposed. Despite these efforts, image registration and segmentation remains a challenging task for SIRT application for several reasons: (1) liver is a soft tissue and liver shape is heavily dependent on patient positioning (e.g., the position of the arms); (2) the liver shape in SIRT patients differs from the normal shape, because of preceding treatments (liver resection, liver ablation, chemotherapy) and tumor growth which makes it challenging to use liver segmentation techniques which are dependent on the liver shape for these patients; (3) liver is a soft tissue and its Hounsfield units are similar to those of adjacent organs like the heart, spleen, stomach, and kidney, which makes liver segmentation on non-contrast-enhanced CTs (e.g., CT from MAA study) hard, even for experts; (4) CT from MAA study is not a dedicated diagnostic CT, this low-dose CT usually suffers from streak artifacts; and (5) the interval between the MAA study and the diagnostic high-dose, contrast-enhanced CT from from fluorine-18 fluorodeoxyglucose ( 18 F-FDG) PET/CT study can be up to weeks to even 1 or 2 months and the liver can deform dramatically over time for several reasons, e.g., tumor change.…”