scholarly journals Concrete Image Segmentation Based on Multiscale Mathematic Morphology Operators and Otsu Method

2015 ◽  
Vol 2015 ◽  
pp. 1-11 ◽  
Author(s):  
Sheng-Bo Zhou ◽  
Ai-Qin Shen ◽  
Geng-Fei Li
Keyword(s):  
Computed Tomography ◽  
Image Segmentation ◽  
Noise Suppression ◽  
Segmentation Method ◽  
Low Contrast ◽  
Otsu Method ◽  
Edge Detectors ◽  
Mathematic Morphology ◽  
Threshold Algorithms ◽  
Concrete Image

The aim of the current study lies in the development of a reformative technique of image segmentation for Computed Tomography (CT) concrete images with the strength grades of C30 and C40. The results, through the comparison of the traditional threshold algorithms, indicate that three threshold algorithms and five edge detectors fail to meet the demand of segmentation for Computed Tomography concrete images. The paper proposes a new segmentation method, by combining multiscale noise suppression morphology edge detector with Otsu method, which is more appropriate for the segmentation of Computed Tomography concrete images with low contrast. This method cannot only locate the boundaries between objects and background with high accuracy, but also obtain a complete edge and eliminate noise.

scholarly journals Analysis of the Clinical Characteristics of Tuberculosis Patients based on Multi-Constrained Computed Tomography (CT) Image Segmentation Algorithm

2021 ◽  
Vol 37 (6-WIT) ◽  
Author(s):  
Feng Zhu ◽  
Bo Zhang
Keyword(s):  
Computed Tomography ◽  
Lung Cancer ◽  
Image Segmentation ◽  
Pulmonary Tuberculosis ◽  
Clinical Characteristics ◽  
Ct Image ◽  
Segmentation Method ◽  
Tuberculosis Patients ◽  
Cancer Group ◽  
Image Segmentation Algorithm

Objective: We used U-shaped convolutional neural network (U_Net) multi-constraint image segmentation method to compare the diagnosis and imaging characteristics of tuberculosis and tuberculosis with lung cancer patients with Computed Tomography (CT). Methods: We selected 160 patients with tuberculosis from the severity scoring (SVR) task is provided by Image CLEF Tuberculosis 2019. According to the type of diagnosed disease, they were divided into tuberculosis combined with lung cancer group and others group, all patients were given chest CT scan, and the clinical manifestations, CT characteristics, and initial suspected diagnosis and missed diagnosis of different tumor diameters were observed and compared between the two groups. Results: There were more patients with hemoptysis and hoarseness in pulmonary tuberculosis combined with lung cancer group than in the pulmonary others group (P<0.05), and the other symptoms were not significantly different (P>0.05). Tuberculosis combined with lung cancer group had fewer signs of calcification, streak shadow, speckle shadow, and cavitation than others group; however, tuberculosis combined with lung cancer group had more patients with mass shadow, lobular sign, spines sign, burr sign and vacuole sign than others group. Conclusion: The symptoms of hemoptysis and hoarseness in pulmonary tuberculosis patients need to consider whether the disease has progressed and the possibility of lung cancer lesions. CT imaging of pulmonary tuberculosis patients with lung cancer usually shows mass shadows, lobular signs, spines signs, burr signs, and vacuoles signs. It can be used as the basis for its diagnosis. Simultaneously, the U-Net-based segmentation method can effectively segment the lung parenchymal region, and the algorithm is better than traditional algorithms. doi: https://doi.org/10.12669/pjms.37.6-WIT.4795 How to cite this:Zhu F, Zhang B. Analysis of the Clinical Characteristics of Tuberculosis Patients based on Multi-Constrained Computed Tomography (CT) Image Segmentation Algorithm. Pak J Med Sci. 2021;37(6):1705-1709. doi: https://doi.org/10.12669/pjms.37.6-WIT.4795 This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/3.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

A Robust Deep Learning Segmentation Method for Hematoma Volumetric Detection in Intracerebral Hemorrhage

Stroke ◽  
2021 ◽  
Author(s):  
Nannan Yu ◽  
He Yu ◽  
Haonan Li ◽  
Nannan Ma ◽  
Chunai Hu ◽  
...  
Keyword(s):  
Computed Tomography ◽  
Image Segmentation ◽  
Deep Learning ◽  
Intracerebral Hemorrhage ◽  
Epidural Hematoma ◽  
Contour Method ◽  
Data Sets ◽  
Segmentation Method ◽  
Data Set ◽  
Testing Data

Background and Purpose: Hematoma volume (HV) is a significant diagnosis for determining the clinical stage and therapeutic approach for intracerebral hemorrhage (ICH). The aim of this study is to develop a robust deep learning segmentation method for the fast and accurate HV analysis using computed tomography. Methods: A novel dimension reduction UNet (DR-UNet) model was developed for computed tomography image segmentation and HV measurement. Two data sets, 512 ICH patients with 12 568 computed tomography slices in the retrospective data set and 50 ICH patients with 1257 slices in the prospective data set, were used for network training, validation, and internal and external testing. Moreover, 13 irregular hematoma cases, 11 subdural and epidural hematoma cases, and 50 different HV cases into 3 groups (<30, 30–60, and >60 mL) were selected to further evaluate the robustness of DR-UNet. The image segmentation performance of DR-UNet was compared with those of UNet, the fuzzy clustering method, and the active contour method. The HV measurement performance was compared using DR-UNet, UNet, and the Coniglobus formula method. Results: Using DR-UNet, the segmentation model achieved a performance similar to that of expert clinicians in 2 independent test data sets containing internal testing data (Dice of 0.861±0.139) and external testing data (Dice of 0.874±0.130). The HV measurement derived from DR-UNet was strongly correlated with that from manual segmentation (R 2 =0.9979; P <0.0001). In the irregularly shaped hematoma group and the subdural and epidural hematoma group, DR-UNet was more robust than UNet in both hematoma segmentation and HV measurement. There is no statistical significance in segmentation accuracy among 3 different HV groups. Conclusions: DR-UNet can segment hematomas from the computed tomography scans of ICH patients and quantify the HV with better accuracy and greater efficiency than the main existing methods and with similar performance to expert clinicians. Due to robust performance and stable segmentation on different ICHs, DR-UNet could facilitate the development of deep learning systems for a variety of clinical applications.

Vein Image Segmentation Based on One-Dimentional Gray and Filter Erosion Method

2014 ◽  
Vol 635-637 ◽  
pp. 1049-1055 ◽  
Author(s):  
Xun Zhang ◽  
Yong Hong Guo ◽  
Gang Li ◽  
Jin Long He
Keyword(s):  
Image Segmentation ◽  
Test Results ◽  
Segmentation Method ◽  
Low Contrast ◽  
One Dimensional ◽  
Hand Vein ◽  
Binary Morphology

For the low contrast and serious noises, a fast image segmentation method based on one-dimensional gray segmentation, binary morphology erosion and area elimination is proposed. Since veins are thin and long, the vein image can be easily distinguished from background by judging the gray difference from nearby pixels when they are vertically or horizontally scanned. Then the processed image is diposed with erosion and area elimination to filter the noise. According to test results on the hand vein images which got from the equipment constructed by ourselves, it is proved that the method is more suitable for hand vein image segmentation than others and clear vein images can be botained quickly.

An Effective X-Ray Image Segmentation Method for the Pharmaceutical Industry via Surface Fitting

2013 ◽  
Vol 333-335 ◽  
pp. 839-844
Author(s):  
Kai Hong Shi ◽  
Zong Qing Lu ◽  
Qing Min Liao
Keyword(s):  
Image Segmentation ◽  
Pharmaceutical Industry ◽  
Active Contour Model ◽  
Three Dimensional ◽  
Surface Fitting ◽  
Segmentation Method ◽  
Image Subtraction ◽  
Low Contrast ◽  
X Ray ◽  
Fixed Condition

Image segmentation techniques currently used for X-ray inspection in pharmaceutical industry suffer from some limitations. The object in an image is close to the background and its contours are weak or blurred because of the X-ray imaging characteristic. Based on our research of X-ray inspection, a simple and efficient image segmentation method is proposed in this paper. It is implemented by treating the image and desired contours as three dimensional surface and holes respectively in order to simplify the model of segmentation, and making use of surface fitting and image subtraction to extract the target region efficiently. The novelty of this approach is that we need less selection of parameters to extract contours with low contrast by surface fitting. Experiments on real X-ray images demonstrate the advantages of the proposed method over active contour model (ACM) and Chan_Vese model (CV model) in terms of both accuracy and efficiency on fixed condition.

Creeping Contours: A Multilabel Image Segmentation Method for Extracting Boundary Surfaces of Parts in Volumetric Images

2011 ◽  
Vol 11 (1) ◽  
Author(s):  
Haitham Shammaa ◽  
Hiromasa Suzuki ◽  
Yutaka Ohtake
Keyword(s):  
Computed Tomography ◽  
Image Segmentation ◽  
Initial Contour ◽  
Segmentation Method ◽  
Mechanical Parts ◽  
Computed Tomography Images ◽  
Volumetric Images ◽  
Speed Function ◽  
Boundary Surfaces ◽  
Grayscale Images

In this work, we introduce a method named creeping contours for image segmentation into component parts for the purpose of extracting the boundary surfaces of these parts. Creeping contours are contours that expand following a speed function defined by the gradient and curvature at contour points, starting from an initial contour position defined either manually or automatically. Contours in the image creep simultaneously at different speeds, while labels are assigned to contour pixels by the defined creeping condition. We also demonstrate the effectiveness of the proposed method by segmenting 2D grayscale images and 3D volumetric computed tomography images of mechanical parts into multiple segments and generating the boundary surfaces of these parts.

The Optimal Thresholding Technique for Image Segmentaion Using Fuzzy Otsu Method

2015 ◽  
Vol 4 (3) ◽  
pp. 81
Author(s):  
P. Rambabu ◽  
C. Naga Raju
Keyword(s):  
Image Segmentation ◽  
Threshold Value ◽  
Mean Value ◽  
Low Contrast ◽  
Innovative Method ◽  
Otsu Method ◽  
Tone Color ◽  
S Curve ◽  
Selection Of

<p>Image Segmentation plays a very important role in image processing. The single-mindedness of image segmentation is to partition the image into a set of disconnected regions with the homogeneous and uniform attributes like intensity, tone, color and texture. There are various methods for image segmentation but no method is suitable for low contrast images. In this paper, we are presenting an efficient and optimal thresholding image segmentation technique that can be used to separate the object and background pixels of the image to improve the quality of low contrast images. This innovative method consists of two steps. Firstly fuzzy logics are used to find optimum mean value using S-curve with automatic selection of controlled parameters to avoid the fuzziness in the image. Secondly, the fuzzy logic’s optimal threshold value used in Otsu method to improve the contrast of the image. This method, gives better results than traditional Otsu and Fuzzy logic techniques. The graphs and tables of values show that the proposed method is superior to traditional methods.</p>

Wear Particles Image Segmentation Method Based on Multiscale Mathematical Morphology

2010 ◽  
Vol 44-47 ◽  
pp. 3169-3173
Author(s):  
Guo De Wang ◽  
Pei Lin Zhang ◽  
Bing Li ◽  
Chao Xu ◽  
An Cheng Zhang
Keyword(s):  
Image Segmentation ◽  
Mathematical Morphology ◽  
Large Scale ◽  
Noise Suppression ◽  
Weighted Average ◽  
Small Scale ◽  
Wear Particles ◽  
Segmentation Method ◽  
Structuring Element ◽  
Single Scale

Image segmentation plays an important role in wear particles analysis. A new segmentation method based on multiscale mathematical morphology is proposed for wear particles image segmentation. The newly introduced method employs different scale structuring elements to detect the image edge, the final edge is calculated by the weighted average method. Edge details can be remained by small scale structuring element (SE) and noise can be depressed effectively by large scale SE, therefore, the new method has great effect in edge accuracy, strong and weak edge extraction and noise suppression. The efficiency of the method is evaluated by a set of wear particles images. The comparison with the single scale SE and other traditional methods demonstrates the improvement of the new algorithm.

Sign in / Sign up

Export Citation Format

Share Document