Comparison of 3D Segmentation Algorithms for Medical Imaging

2007 ◽  
Author(s):  
Hakan Bulu ◽  
Adil Alpkocak
Keyword(s):  
Medical Imaging ◽  
3D Segmentation ◽  
Segmentation Algorithms

Accelerating compute intensive medical imaging segmentation algorithms using hybrid CPU-GPU implementations

2016 ◽  
Vol 76 (3) ◽  
pp. 3537-3555 ◽  
Author(s):  
Mohammad A. Alsmirat ◽  
Yaser Jararweh ◽  
Mahmoud Al-Ayyoub ◽  
Mohammed A. Shehab ◽  
Brij B. Gupta
Keyword(s):  
Medical Imaging ◽  
Segmentation Algorithms

A Hybrid Approach for Automatic Aorta Segmentation in Abdominal 3D CT Scan Images

2021 ◽  
Vol 11 (3) ◽  
pp. 712-719
Author(s):  
Iftikhar Ahmad ◽  
Sami ur Rehman ◽  
Imran Ullah Khan ◽  
Arfa Ali ◽  
Hussain Rahman ◽  
...  
Keyword(s):  
Medical Imaging ◽  
Ct Scan ◽  
Hybrid Approach ◽  
Computational Cost ◽  
Iterative Algorithms ◽  
Fast Algorithms ◽  
Human Anatomy ◽  
3D Ct Scan ◽  
Segmentation Accuracy ◽  
Segmentation Algorithms

Due to rapid advancement in medical imaging, human anatomy is now observable in finer details bringing new dimensions to diagnosis and treatment. One such area which benefitted from advancement in medical imaging is aorta segmentation. Aorta segmentation is achieved by using anatomical features (shape and position of aorta) using specialized segmentation algorithms. These segmentation algorithms are broadly classified into two categories. The first type comprises of fast algorithms which exploits spatial and intensity properties of images. The second type are iterative algorithms which use optimization of a cost function to track aorta boundaries. Fast algorithms offer lower computation cost, whereas iterative algorithms offer better segmentation accuracy. Therefore, there is a tradeoff between segmentation accuracy and computational cost. In this work, a hybrid approach for aorta segmentation in 3D Computed Tomography (CT) scan images is proposed. The proposed approach produces high segmentation accuracy of intensity based (fast) approaches at reduced computational cost. The proposed technique is evaluated using real world 3D abdominal CT scan images. The proposed approach can either be used as a fast-standalone segmentation procedure, or as a pre-segmentation procedure for iterative and more accurate approaches.

Deep Learning for Medical Image Segmentation

2021 ◽  
pp. 40-77
Author(s):  
Kanchan Sarkar ◽  
Bohang Li
Keyword(s):  
Image Segmentation ◽  
Deep Learning ◽  
Medical Imaging ◽  
Medical Image ◽  
Disease Diagnosis ◽  
Medical Image Segmentation ◽  
Kidney Tumour ◽  
Tumour Segmentation ◽  
Recent Innovation ◽  
Segmentation Algorithms

Pixel accurate 2-D, 3-D medical image segmentation to identify abnormalities for further analysis is on high demand for computer-aided medical imaging applications. Various segmentation algorithms have been studied and applied in medical imaging for many years, but the problem remains challenging due to growing a large number of variety of applications starting from lung disease diagnosis based on x-ray images, nucleus detection, and segmentation based on microscopic pictures to kidney tumour segmentation. The recent innovation in deep learning brought revolutionary advances in computer vision. Image segmentation is one such area where deep learning shows its capacity and improves the performance by a larger margin than its successor. This chapter overviews the most popular deep learning-based image segmentation techniques and discusses their capabilities and basic advantages and limitations in the domain of medical imaging.

scholarly journals Geodesic Distance Algorithm for Extracting the Ascending Aorta from 3D CT Images

2016 ◽  
Vol 2016 ◽  
pp. 1-7 ◽  
Author(s):  
Yeonggul Jang ◽  
Ho Yub Jung ◽  
Youngtaek Hong ◽  
Iksung Cho ◽  
Hackjoon Shim ◽  
...  
Keyword(s):  
Geodesic Distance ◽  
Ascending Aorta ◽  
Dice Similarity Coefficient ◽  
3D Segmentation ◽  
Medical Expert ◽  
Distance Transformation ◽  
Segmentation Algorithms ◽  
Initial Seed ◽  
Seed Points ◽  
Axial Slice

This paper presents a method for the automatic 3D segmentation of the ascending aorta from coronary computed tomography angiography (CCTA). The segmentation is performed in three steps. First, the initial seed points are selected by minimizing a newly proposed energy function across the Hough circles. Second, the ascending aorta is segmented by geodesic distance transformation. Third, the seed points are effectively transferred through the next axial slice by a novel transfer function. Experiments are performed using a database composed of 10 patients’ CCTA images. For the experiment, the ground truths are annotated manually on the axial image slices by a medical expert. A comparative evaluation with state-of-the-art commercial aorta segmentation algorithms shows that our approach is computationally more efficient and accurate under the DSC (Dice Similarity Coefficient) measurements.

Sign in / Sign up

Export Citation Format

Share Document