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.

Building Extraction from High-Resolution Remote Sensing Images Based on GrabCut with Automatic Selection of Foreground and Background Samples

2020 ◽  
Vol 86 (4) ◽  
pp. 235-245 ◽  
Author(s):  
Ka Zhang ◽  
Hui Chen ◽  
Wen Xiao ◽  
Yehua Sheng ◽  
Dong Su ◽  
...  
Keyword(s):  
Remote Sensing ◽  
High Resolution ◽  
Geodesic Distance ◽  
Extraction Methods ◽  
Building Extraction ◽  
Remote Sensing Images ◽  
Canny Operator ◽  
Contour Lines ◽  
Average Accuracy ◽  
Seed Points

This article proposes a new building extraction method from high-resolution remote sensing images, based on GrabCut, which can automatically select foreground and background samples under the constraints of building elevation contour lines. First the image is rotated according to the direction of pixel displacement calculated by the rational function Model. Second, the Canny operator, combined with morphology and the Hough transform, is used to extract the building's elevation contour lines. Third, seed points and interesting points of the building are selected under the constraint of the contour line and the geodesic distance. Then foreground and background samples are obtained according to these points. Fourth, GrabCut and geometric features are used to carry out image segmentation and extract buildings. Finally, WorldView satellite images are used to verify the proposed method. Experimental results show that the average accuracy can reach 86.34%, which is 15.12% higher than other building extraction methods.

scholarly journals Automatic Segmentation of Ulna and Radius in Forearm Radiographs

2019 ◽  
Vol 2019 ◽  
pp. 1-9 ◽  
Author(s):  
Xiaofang Gou ◽  
Yuming Rao ◽  
Xiuxia Feng ◽  
Zhaoqiang Yun ◽  
Wei Yang
Keyword(s):  
Automatic Segmentation ◽  
Density Measurement ◽  
Minimum Cost ◽  
Dice Similarity Coefficient ◽  
Mineral Density ◽  
Robust Segmentation ◽  
Low Exposure ◽  
Cost Paths ◽  
Seed Points ◽  
Imaging Conditions

Automatic segmentation of ulna and radius (UR) in forearm radiographs is a necessary step for single X-ray absorptiometry bone mineral density measurement and diagnosis of osteoporosis. Accurate and robust segmentation of UR is difficult, given the variation in forearms between patients and the nonuniformity intensity in forearm radiographs. In this work, we proposed a practical automatic UR segmentation method through the dynamic programming (DP) algorithm to trace UR contours. Four seed points along four UR diaphysis edges are automatically located in the preprocessed radiographs. Then, the minimum cost paths in a cost map are traced from the seed points through the DP algorithm as UR edges and are merged as the UR contours. The proposed method is quantitatively evaluated using 37 forearm radiographs with manual segmentation results, including 22 normal-exposure and 15 low-exposure radiographs. The average Dice similarity coefficient of our method reached 0.945. The average mean absolute distance between the contours extracted by our method and a radiologist is only 5.04 pixels. The segmentation performance of our method between the normal- and low-exposure radiographs was insignificantly different. Our method was also validated on 105 forearm radiographs acquired under various imaging conditions from several hospitals. The results demonstrated that our method was fairly robust for forearm radiographs of various qualities.

scholarly journals Model-based Automatic Segmentation of Ascending Aorta from Multimodality Medical Data

2016 ◽  
Vol 6 (6) ◽  
pp. 3161
Author(s):  
Noha Seada ◽  
Safwat Hamad ◽  
Mostafa G. M. Mostafa
Keyword(s):  
Automatic Segmentation ◽  
Model Fitting ◽  
Region Of Interest ◽  
Region Growing ◽  
Magnetic Resonance Images ◽  
Ascending Aorta ◽  
Imaging Modalities ◽  
Dice Similarity Coefficient ◽  
Seeded Region Growing ◽  
Novel Approach

<p>Automatic Ascending Aorta Segmentation is one of the important steps towards automatic segmentation of the whole cardiac tree. This paper presents a novel approach for the automatic segmentation of the ascending aorta from two imaging modalities: CTA (Computed Tomography Angiography) and PC-MRI (Phase-Contrast Magnetic Resonance Images). The novel approach is an algorithm that works without the need for setting manual seed points or applying preprocessing steps or setting a region of interest. Instead, the proposed algorithm automatically detects and segments the ascending aorta using an ascending aorta model built from its anatomical features. The proposed segmentation algorithm begins with aorta detection through features model fitting augmented with Hough transform, where the ascending aorta is identified from the descending aorta and any other circular structures based on the proposed model. After detection, the whole ascending aorta is segmented up from the aortic arch down to the ostia points using a novel automatic seeded region growing algorithm. The proposed algorithm is fully automatic, works in real-time and robust as parameters used are the same for all the tested datasets. The detection and segmentation of the ascending aorta succeeded in all test cases acquired from the two imaging modalities; proving the robustness of the proposed ascending aorta model and algorithm for the automatic segmentation process even on data from different modalities and different scanner types. The accuracy of the segmentation has a mean Dice Similarity Coefficient (DSC) of 94.72% for CTA datasets and 97.13% for PC-MRI datasets.</p>

Detection of Pulmonary Nodules in CT Scanned Images Based on Region Growing with Optimization Parameters

2012 ◽  
Vol 532-533 ◽  
pp. 854-858
Author(s):  
Yong Li ◽  
Zhuang Miao ◽  
Bo Chen
Keyword(s):  
Pulmonary Nodules ◽  
Principal Component ◽  
Region Growing ◽  
Three Dimension ◽  
Distance Map ◽  
Optimization Parameters ◽  
Scanned Images ◽  
Initial Seed ◽  
Seed Points ◽  
Aided Diagnosis

We present a more efficient computer-aided diagnosis algorithm to detect pulmonary nodules automatically in CT (Computerized Tomography) scanned images based on region growing with optimization parameters: initial seed points and constraint condition. The former are chosen by 3D (three-dimension) PCA (principal component analysis), and the later is designed by distance map and watershed algorithms. The technique was tested against more than 200 CT images of 10 typical cases from Jilin Tumor Hospital. The results confirm the validity of technique as well as enhanced performance.

Model-based Automatic Segmentation of Ascending Aorta from Multimodality Medical Data

2016 ◽  
Vol 6 (6) ◽  
pp. 3161
Author(s):  
Noha Seada ◽  
Safwat Hamad ◽  
Mostafa G. M. Mostafa
Keyword(s):  
Automatic Segmentation ◽  
Model Fitting ◽  
Region Of Interest ◽  
Region Growing ◽  
Magnetic Resonance Images ◽  
Ascending Aorta ◽  
Imaging Modalities ◽  
Dice Similarity Coefficient ◽  
Seeded Region Growing ◽  
Novel Approach

<p>Automatic Ascending Aorta Segmentation is one of the important steps towards automatic segmentation of the whole cardiac tree. This paper presents a novel approach for the automatic segmentation of the ascending aorta from two imaging modalities: CTA (Computed Tomography Angiography) and PC-MRI (Phase-Contrast Magnetic Resonance Images). The novel approach is an algorithm that works without the need for setting manual seed points or applying preprocessing steps or setting a region of interest. Instead, the proposed algorithm automatically detects and segments the ascending aorta using an ascending aorta model built from its anatomical features. The proposed segmentation algorithm begins with aorta detection through features model fitting augmented with Hough transform, where the ascending aorta is identified from the descending aorta and any other circular structures based on the proposed model. After detection, the whole ascending aorta is segmented up from the aortic arch down to the ostia points using a novel automatic seeded region growing algorithm. The proposed algorithm is fully automatic, works in real-time and robust as parameters used are the same for all the tested datasets. The detection and segmentation of the ascending aorta succeeded in all test cases acquired from the two imaging modalities; proving the robustness of the proposed ascending aorta model and algorithm for the automatic segmentation process even on data from different modalities and different scanner types. The accuracy of the segmentation has a mean Dice Similarity Coefficient (DSC) of 94.72% for CTA datasets and 97.13% for PC-MRI datasets.</p>

Sign in / Sign up

Export Citation Format

Share Document