Automatic Segmentation and Diagnosis Based on Multi-Scale Two-Stage Region Growing and Skeleton Extraction for Vessel Stenosis in Coronary Angiography

2020 ◽  
Vol 10 (2) ◽  
pp. 446-451
Author(s):  
Wu Deng ◽  
Kai Luo ◽  
Qinke Shi ◽  
Yi Yang ◽  
Ning Ning
Keyword(s):  
Coronary Angiography ◽  
Hessian Matrix ◽  
Region Growing ◽  
Vessel Segmentation ◽  
Good Effect ◽  
Skeleton Extraction ◽  
Seed Point ◽  
Automatic Diagnosis ◽  
Small Vessels ◽  
Vessel Stenosis

Although great progress has been made in vessel segmentation, the existing methods still can not accurately segment small vessels. A novel vessel segmentation and automatic diagnosis in coronary angiography image was proposed. During vessel segmentation, a new vessel function based on Hessian matrix was put forward. Then the vessel contour was extracted by the dual-stage region growing with automatic selection of seed point. Next, the automatic diagnosis was realized by vessel skeleton extraction, skeleton point search and diameter measurement. The experimental results demonstrate that our proposed vessel segmentation can extract the main branch contour accurately and have a good effect on the enhancement and segmentation of small vessels. The automatic diagnosis of vessel stenosis is fast. With a relatively accurate diagnosis result, it can provide a good reference and quantitative basis for the final judgment of the doctor.

scholarly journals Retinal Vessel Segmentation by Deep Residual Learning with Wide Activation

2020 ◽  
Vol 2020 ◽  
pp. 1-11
Author(s):  
Yuliang Ma ◽  
Xue Li ◽  
Xiaopeng Duan ◽  
Yun Peng ◽  
Yingchun Zhang
Keyword(s):  
Blood Vessel ◽  
Blood Vessels ◽  
Area Under The Curve ◽  
Retinal Vessel ◽  
Vessel Segmentation ◽  
Superior Performance ◽  
Retinal Blood Vessel ◽  
Low Contrast ◽  
Blood Vessel Segmentation ◽  
Small Vessels

Purpose. Retinal blood vessel image segmentation is an important step in ophthalmological analysis. However, it is difficult to segment small vessels accurately because of low contrast and complex feature information of blood vessels. The objective of this study is to develop an improved retinal blood vessel segmentation structure (WA-Net) to overcome these challenges. Methods. This paper mainly focuses on the width of deep learning. The channels of the ResNet block were broadened to propagate more low-level features, and the identity mapping pathway was slimmed to maintain parameter complexity. A residual atrous spatial pyramid module was used to capture the retinal vessels at various scales. We applied weight normalization to eliminate the impacts of the mini-batch and improve segmentation accuracy. The experiments were performed on the DRIVE and STARE datasets. To show the generalizability of WA-Net, we performed cross-training between datasets. Results. The global accuracy and specificity within datasets were 95.66% and 96.45% and 98.13% and 98.71%, respectively. The accuracy and area under the curve of the interdataset diverged only by 1%∼2% compared with the performance of the corresponding intradataset. Conclusion. All the results show that WA-Net extracts more detailed blood vessels and shows superior performance on retinal blood vessel segmentation tasks.

scholarly journals A smoke image segmentation algorithm based on rough set and region growing

2019 ◽  
Vol 65 (No. 8) ◽  
pp. 321-329
Author(s):  
Haitao Wang ◽  
Yanli Chen
Keyword(s):  
Image Segmentation ◽  
Rough Set ◽  
Region Growing ◽  
Recall Rate ◽  
Segmentation Algorithm ◽  
Colour Space ◽  
Seed Point ◽  
Black Smoke ◽  
Growth Method ◽  
Image Segmentation Algorithm

Because the image fire smoke segmentation algorithm can not extract white, gray and black smoke at the same time, a smoke image segmentation algorithm is proposed by combining rough set and region growth method. The R component of the image is extracted in the RGB colour space, the roughness histogram is constructed according to the statistical histogram of the R component, and the appropriate valley value in the roughness histogram is selected as the segmentation threshold, the image is roughly segmented. Relative to the background image, the smoke belongs to the motion information, and the motion region is extracted by the interframe difference method to eliminate static interference. Smoke has a unique colour feature, a smoke colour model is created in the RGB colour space, the motion disturbances of similar colour are removed and the suspected smoke areas are obtained. The seed point is selected in the region, and the region is grown on the result of rough segmentation, the smoke region is extracted. The experimental results show that the algorithm can segment white, gray and black smoke at the same time, and the irregular information of smoke edges is relatively complete. Compared with the existing algorithms, the average segmentation accuracy, recall rate and F-value are increased by 19%, 21.5% and 20%, respectively.<br /><br />

scholarly journals Automatic liver vessel segmentation using 3D region growing and hybrid active contour model

2018 ◽  
Vol 97 ◽  
pp. 63-73 ◽  
Author(s):  
Ye-zhan Zeng ◽  
Sheng-hui Liao ◽  
Ping Tang ◽  
Yu-qian Zhao ◽  
Miao Liao ◽  
...  
Keyword(s):  
Active Contour ◽  
Active Contour Model ◽  
Region Growing ◽  
Vessel Segmentation ◽  
Contour Model ◽  
3D Region Growing

scholarly journals A Region Growing Vessel Segmentation Algorithm Based on Spectrum Information

2013 ◽  
Vol 2013 ◽  
pp. 1-9 ◽  
Author(s):  
Huiyan Jiang ◽  
Baochun He ◽  
Di Fang ◽  
Zhiyuan Ma ◽  
Benqiang Yang ◽  
...  
Keyword(s):  
Region Of Interest ◽  
Region Growing ◽  
Vessel Segmentation ◽  
Growth Strategy ◽  
Segmentation Algorithm ◽  
Edge Information ◽  
Manual Intervention ◽  
Vascular Structures ◽  
Region Growing Segmentation ◽  
Seed Points

We propose a region growing vessel segmentation algorithm based on spectrum information. First, the algorithm does Fourier transform on the region of interest containing vascular structures to obtain its spectrum information, according to which its primary feature direction will be extracted. Then combined edge information with primary feature direction computes the vascular structure’s center points as the seed points of region growing segmentation. At last, the improved region growing method with branch-based growth strategy is used to segment the vessels. To prove the effectiveness of our algorithm, we use the retinal and abdomen liver vascular CT images to do experiments. The results show that the proposed vessel segmentation algorithm can not only extract the high quality target vessel region, but also can effectively reduce the manual intervention.

scholarly journals Reliability of Segmenting Brain Tumor and Finding Optimal Volume Estimator for MR Images of Patients with Glioma’s

2019 ◽  
Vol 8 (9) ◽  
pp. 1647-1652
Keyword(s):  
Brain Tumor ◽  
Tumor Volume ◽  
Region Growing ◽  
Threshold Value ◽  
Volume Estimation ◽  
Clinical Aspects ◽  
Tumor Segmentation ◽  
Low Grade ◽  
Seed Point ◽  
Glioma Tumor

Tumor volume estimation is a significant prognostic part of the Glioma tumor detection. Reliable assessment of Glioma tumor segmentation and volume estimation is a common problem in clinical aspects. We aim to propose a tumor segmentation method by suggesting suitable estimator for MR brain tumor volume construction. Run length algorithm is used to automatic initialize the seed point to the region growing algorithm. Region growing algorithm works with a threshold value using 8 × 8 patches. In this experiment includes thirty BraTS2013 high-grade and low-grade Glioma datasets. Proposed method yield 80.12% of Dice similarity with 6.8% of deviation and 84% of accuracy with 10% of deviation. The proposed work uses six state-of-the-art volume detectors to estimate the size of tumor volume. From the results, Cavalieri’s estimator gives more accurate results with less deviation

scholarly journals Triple vessel coronary artery disease in a rural Nigerian: A reflection of poor diagnostic infrastructure or rarity in prevalence? A call for action

2019 ◽  
Vol 5 (3) ◽  
pp. 109-111
Author(s):  
Akintunde Adeseye A ◽  
◽  
Olafiranye Oladipupo ◽  
◽  
Keyword(s):  
Coronary Artery Disease ◽  
Coronary Artery ◽  
Coronary Angiography ◽  
Good Effect ◽  
Vessel Disease ◽  
Diagnostic Facility ◽  
Triple Vessel Disease ◽  
Artery Disease ◽  
Angioplasty And Stenting ◽  
Vessel Coronary Artery

The need for provision of more diagnostic facility for coronary angiography to diagnose coronary artery disease among Africans cannot be overemphasized as there is the possibility that coronary artery disease may not be as uncommon as it is presently estimated but may be manifesting with different phenotypic presentations compared to the Caucasians. We present an otherwise stable adult rural Nigerian with hypertension and diabetes who was diagnosed with a triple vessel disease and subsequently had coronary angioplasty and stenting with good effect.

scholarly journals Analysis of Glomerular Filtration Rate in Ischemic Cerebrovascular Diseases under the Magnetic Resonance Angiography Image Segmentation Algorithm

2021 ◽  
Vol 2021 ◽  
pp. 1-10
Author(s):  
Yong Ding ◽  
Yuebin Liu ◽  
Cong Peng ◽  
Huanmei Wang ◽  
Yuqin Xu ◽  
...  
Keyword(s):  
Blood Vessel ◽  
Fuzzy Clustering ◽  
Clustering Algorithm ◽  
Vessel Segmentation ◽  
Segmentation Algorithm ◽  
Arterial Stenosis ◽  
Blood Vessel Segmentation ◽  
Fuzzy Clustering Algorithm ◽  
Vessel Stenosis ◽  
Cv Model

In order to discuss the segmentation effect of the magnetic resonance angiography (MRA) image segmentation algorithm based on the fuzzy clustering algorithm and DR-CV model and the prognostic value of glomerular filtration rate (GFR) in the ischemic cerebrovascular disease (ICVD), a total of 178 patients who were admitted to the hospital and received MRA due to ICVD were selected as the research objects of this study. Blood vessel segmentation was performed on the MRA image by fuzzy clustering algorithm and DR-CV model, and all patients were divided into a control group (group A), a single-vessel stenosis group (group B), a two-vessel stenosis group (group C), and a multiple-vessel stenosis group (group D). The GFR was estimated by using the dietary modification equation for kidney disease, and the correlation between GFR and the severity of arterial stenosis in patients with ICVD was analyzed. It was found that the results of the Dice similarity index (DSI) of the MRA image blood vessel segmentation algorithm based on the fuzzy clustering algorithm and the integrated model of boundary and regional information (DR-CV model) were all above 85%. The age and GFR values of the four groups of patients were significantly different ( P  < 0.05). The proportions of patients in groups C and D in the group with low DFR were significantly different from those in groups A and B ( P  < 0.01); the proportions of patients in groups A and B in the high-level GFR group had extremely significant differences compared with group D ( P  < 0.01). Age, GFR, total cholesterol (TC), and high-density lipoprotein-C (HDL-C) were correlated with the degree of arterial stenosis ( P  < 0.05). It showed that the segmentation effect of MRA image blood vessel segmentation algorithm based on the fuzzy clustering algorithm and DR-CV model was better, and the GFR level can be used as an independent risk factor for the ICVD.

Sign in / Sign up

Export Citation Format

Share Document