scholarly journals Precise Segmentation of COVID-19 Infected Lung from CT Images Based on Adaptive First-Order Appearance Model with Morphological/Anatomical Constraints

Sensors ◽  
2021 ◽  
Vol 21 (16) ◽  
pp. 5482
Author(s):  
Ahmed Sharafeldeen ◽  
Mohamed Elsharkawy ◽  
Norah Saleh Alghamdi ◽  
Ahmed Soliman Soliman ◽  
Ayman El-Baz
Keyword(s):  
Ct Images ◽  
Appearance Model ◽  
Dice Similarity Coefficient ◽  
Lung Region ◽  
Current State ◽  
Segmentation Quality ◽  
Initial Segmentation ◽  
Clustering Approach ◽  
Ct Data ◽  
Volume Difference

A new segmentation technique is introduced for delineating the lung region in 3D computed tomography (CT) images. To accurately model the distribution of Hounsfield scale values within both chest and lung regions, a new probabilistic model is developed that depends on a linear combination of Gaussian (LCG). Moreover, we modified the conventional expectation-maximization (EM) algorithm to be run in a sequential way to estimate both the dominant Gaussian components (one for the lung region and one for the chest region) and the subdominant Gaussian components, which are used to refine the final estimated joint density. To estimate the marginal density from the mixed density, a modified k-means clustering approach is employed to classify the Gaussian subdominant components to determine which components belong properly to a lung and which components belong to a chest. The initial segmentation, based on the LCG-model, is then refined by the imposition of 3D morphological constraints based on a 3D Markov–Gibbs random field (MGRF) with analytically estimated potentials. The proposed approach was tested on CT data from 32 coronavirus disease 2019 (COVID-19) patients. Segmentation quality was quantitatively evaluated using four metrics: Dice similarity coefficient (DSC), overlap coefficient, 95th-percentile bidirectional Hausdorff distance (BHD), and absolute lung volume difference (ALVD), and it achieved 95.67±1.83%, 91.76±3.29%, 4.86±5.01, and 2.93±2.39, respectively. The reported results showed the capability of the proposed approach to accurately segment healthy lung tissues in addition to pathological lung tissues caused by COVID-19, outperforming four current, state-of-the-art deep learning-based lung segmentation approaches.

scholarly journals Detection and Severity Classification of COVID-19 in CT Images Using Deep Learning

Diagnostics ◽  
2021 ◽  
Vol 11 (5) ◽  
pp. 893
Author(s):  
Yazan Qiblawey ◽  
Anas Tahir ◽  
Muhammad E. H. Chowdhury ◽  
Amith Khandakar ◽  
Serkan Kiranyaz ◽  
...  
Keyword(s):  
Computed Tomography ◽  
Neural Networks ◽  
Early Stage ◽  
Similarity Coefficient ◽  
Dice Similarity Coefficient ◽  
Lung Region ◽  
Computed Tomography Images ◽  
Feature Pyramid ◽  
Severity Levels

Detecting COVID-19 at an early stage is essential to reduce the mortality risk of the patients. In this study, a cascaded system is proposed to segment the lung, detect, localize, and quantify COVID-19 infections from computed tomography images. An extensive set of experiments were performed using Encoder–Decoder Convolutional Neural Networks (ED-CNNs), UNet, and Feature Pyramid Network (FPN), with different backbone (encoder) structures using the variants of DenseNet and ResNet. The conducted experiments for lung region segmentation showed a Dice Similarity Coefficient (DSC) of 97.19% and Intersection over Union (IoU) of 95.10% using U-Net model with the DenseNet 161 encoder. Furthermore, the proposed system achieved an elegant performance for COVID-19 infection segmentation with a DSC of 94.13% and IoU of 91.85% using the FPN with DenseNet201 encoder. The proposed system can reliably localize infections of various shapes and sizes, especially small infection regions, which are rarely considered in recent studies. Moreover, the proposed system achieved high COVID-19 detection performance with 99.64% sensitivity and 98.72% specificity. Finally, the system was able to discriminate between different severity levels of COVID-19 infection over a dataset of 1110 subjects with sensitivity values of 98.3%, 71.2%, 77.8%, and 100% for mild, moderate, severe, and critical, respectively.

GROUND-GLASS OPACITY DETECTION BY USING CORRELATION BETWEEN SUCCESSIVE SLICE IMAGES

2007 ◽  
Vol 16 (04) ◽  
pp. 583-592 ◽  
Author(s):  
HYOUNGSEOP KIM ◽  
MASAKI MAEKADO ◽  
JOO KOOI TAN ◽  
SEIJI ISHIKAWA ◽  
MASAAKI TSUKUDA
Keyword(s):  
Soft Tissues ◽  
Automatic Segmentation ◽  
Ground Glass Opacity ◽  
Processing Technique ◽  
Ct Images ◽  
Image Processing Technique ◽  
Ground Glass ◽  
Lung Region ◽  
Mdct Image ◽  
Thorax Ct

Medical imaging systems such as computed tomography, magnetic resonance imaging provided a high resolution image for powerful diagnostic tool in visual inspection fields by physician. Especially MDCT image can be used to obtain detailed images of the pulmonary anatomy, including pulmonary diseases such as the pulmonary nodules, the pulmonary vein, etc. In the medical image processing technique, segmentation is a difficult task because surrounding soft tissues and organs have similar CT values and sometimes contact with each other. We propose a new technique for automatic segmentation of lung regions and its classification for ground-glass opacity from the extracted lung regions by computer based on a set of the thorax CT images. In this paper, we segment the lung region for extraction of the region of interest employing binarization and labeling process from the inputted each slices images. The region having the largest area is regarded as the tentative lung regions. Furthermore, the ground-glass opacity is classified by correlation distribution on the slice to slice from the extracted lung region with respect to the thorax CT images. Experiment is performed employing twenty six thorax CT image sets and 96% of recognition rates were achieved. Obtained results are shown along with a discussion.

Quantitative Comparisons of Deep-learning-based and Atlas-based Auto-segmentation of the Intermediate Risk Clinical Target Volume for Nasopharyngeal Carcinoma

2021 ◽  
Vol 17 ◽  
Author(s):  
Yisong He ◽  
Shengyuan Zhang ◽  
Yong Luo ◽  
Hang Yu ◽  
Yuchuan Fu ◽  
...  
Keyword(s):  
Deep Learning ◽  
Clinical Target Volume ◽  
Target Volume ◽  
Similarity Coefficient ◽  
Relative Volume ◽  
Dice Similarity Coefficient ◽  
Intermediate Risk ◽  
Segmentation Methods ◽  
Accuracy And Stability ◽  
Volume Difference

Background: Manual segment target volumes were time-consuming and inter-observer variability couldn’t be avoided. With the development of computer science, auto-segmentation had the potential to solve this problem. Objective: To evaluate the accuracy and stability of Atlas-based and deep-learning-based auto-segmentation of the intermediate risk clinical target volume, composed of CTV2 and CTVnd, for nasopharyngeal carcinoma quantitatively. Methods and Materials: A cascade-deep-residual neural network was constructed to automatically segment CTV2 and CTVnd by deep learning method. Meanwhile, a commercially available software was used to automatically segment the same regions by Atlas-based method. The datasets included contrast computed tomography scans from 102 patients. For each patient, the two regions were manually delineated by one experienced physician. The similarity between the two auto-segmentation methods was quantitatively evaluated by Dice similarity coefficient, the 95th Hausdorff distance, volume overlap error and relative volume difference, respectively. Statistical analyses were performed using the ranked Wilcoxon test. Results: The average Dice similarity coefficient (±standard deviation) given by the deep-learning-based and Atlas-based auto-segmentation were 0.84(±0.03) and 0.74(±0.04) for CTV2, 0.79(±0.02) and 0.68(±0.03) for CTVnd, respectively. For the 95th Hausdorff distance, the corresponding values were 6.30±3.55mm and 9.34±3.39mm for CTV2, 7.09±2.27mm and 14.33±3.98mm for CTVnd. Besides, volume overlap error and relative volume difference could also predict the same situations. Statistical analyses showed significant difference between the two auto-segmentation methods (p<0.01). Conclusions: Compared with the Atlas-based segmentation approach, the deep-learning-based segmentation method performed better both in accuracy and stability for meaningful anatomical areas other than organs at risk.

scholarly journals AUTOMATIC LUNG NODULE DETECTION BASED ON STATISTICAL REGION MERGING AND SUPPORT VECTOR MACHINES

2017 ◽  
Vol 36 (2) ◽  
pp. 65 ◽  
Author(s):  
Elaheh Aghabalaei Khordehchi ◽  
Ahmad Ayatollahi ◽  
Mohammad Reza Daliri
Keyword(s):  
Lung Nodule ◽  
Three Dimensional ◽  
Pulmonary Nodules ◽  
Ct Images ◽  
Support Vector ◽  
Svm Classifier ◽  
Region Merging ◽  
Three Dimensional Objects ◽  
Ct Data ◽  
Statistical Region Merging

Lung cancer is one of the most common diseases in the world that can be treated if the lung nodules are detected in their early stages of growth. This study develops a new framework for computer-aided detection of pulmonary nodules thorough a fully-automatic analysis of Computed Tomography (CT) images. In the present work, the multi-layer CT data is fed into a pre-processing step that exploits an adaptive diffusion-based smoothing algorithm in which the parameters are automatically tuned using an adaptation technique. After multiple levels of morphological filtering, the Regions of Interest (ROIs) are extracted from the smoothed images. The Statistical Region Merging (SRM) algorithm is applied to the ROIs in order to segment each layer of the CT data. Extracted segments in consecutive layers are then analyzed in such a way that if they intersect at more than a predefined number of pixels, they are labeled with a similar index. The boundaries of the segments in adjacent layers which have the same indices are then connected together to form three-dimensional objects as the nodule candidates. After extracting four spectral, one morphological, and one textural feature from all candidates, they are finally classified into nodules and non-nodules using the Support Vector Machine (SVM) classifier. The proposed framework has been applied to two sets of lung CT images and its performance has been compared to that of nine other competing state-of-the-art methods. The considerable efficiency of the proposed approach has been proved quantitatively and validated by clinical experts as well.

scholarly journals Common and Uncommon Imaging Appearances of COVID-19 Pneumonia in Young and Middle-Aged Group and Elderly Group

2021 ◽  
Author(s):  
Alireza Mahmoudabadi ◽  
Hamed Masoumi ◽  
Mohammad Keshtkar ◽  
Arash Azhideh ◽  
Hamidreza Haghighatkhah
Keyword(s):  
Pleural Effusion ◽  
Ground Glass Opacity ◽  
The Elderly ◽  
Ct Images ◽  
Elderly Group ◽  
Wall Thickening ◽  
Lung Region ◽  
Middle Aged ◽  
Aged Group ◽  
Lower Lung

Purpose: In this study, we retrospectively evaluated chest Computed Tomography (CT) imaging manifestations of the patients with Coronavirus Disease 2019 (COVID-19) to simplify prompt early diagnosis of disease and speed up needed actions for infected patients. Materials and Methods: Totally, 75 patients who laboratory confirmed COVID-19 pneumonia were enrolled in this study. CT images, demographic and some clinical data of all patients were collected and analyzed retrospectively. Furthermore, for comparison, the patients were divided into two groups as follows: the young and middle-aged group (< 60 years old) and the elderly group (≥ 60 years old). Results: Based on the evaluation of CT images, 33 patients (44%) showed Ground-Glass Opacity (GGO), 15 patients (20%) showed consolidation, 24 patients (32%) showed mixed GGO and consolidation, 2 patients (2.6%) had bronchial wall thickening, 10 patients (13.3%) had a crazy paving sign, 35 patients (46.6%) had air bronchogram and, 7 patients (9.3%) had cavitation and 2 patients (2.6%) had a tree in the bud. CT images of 3 patients (4%) were normal. In terms of out of lung changes, lymphadenopathy was observed in one patient (1.3%), pleural effusion in 12 patients (16%), and pericardial effusion in 2 patients (2.6%). Lesions were found predominantly in the peripheral (57.3%) and the lower lung region (60%). Conclusion: CT images of the COVID-19 patients showed various aspects, mainly GGO, consolidation, mixed GGO and consolidation, and air bronchogram. Lesion distribution was predominantly in lower lung region, bilateral and peripheral. Pleural effusion and multiple lobe involvement were significantly higher in the elderly group than that of the young and middle-aged group.

Evolution of Meso-Structure of Intact Loess during Wetting

2012 ◽  
Vol 204-208 ◽  
pp. 188-191
Author(s):  
Xiang Wei Fang ◽  
Chun Ni Shen ◽  
Pei Jiang Cheng ◽  
Long Wang
Keyword(s):  
Volumetric Strain ◽  
Ct Images ◽  
Deviatoric Stress ◽  
Cell Stress ◽  
Degree Of Saturation ◽  
Triaxial Apparatus ◽  
Evolution Of Structure ◽  
Ct Data ◽  
Intact Loess

To study the evolution of meso-structure of unsaturated intact loess during wetting, a series of CT-triaxial-collapse tests were conducted using CT-multi-function triaxial apparatus. The distinct CT images and detailed CT data were attained nondestructively during wetting. A parameter and an evolution variable which characterized evolution of meso-structure were defined based CT data. An equation describing the evolution of structure during wetting was proposed. The equation reflected the influences of net cell stress, deviatoric stress and suction on the evolution of meso-structure. In the equation, volumetric strain, deviatoric strain and incremental degree of saturation are included.

A Hybrid Approach for 3D Lung Segmentation in CT Images Using Active Contour and Morphological Operation

2020 ◽  
pp. 163-175
Author(s):  
Satya Praksh Sahu ◽  
Bhawna Kamble
Keyword(s):  
Active Contour ◽  
Hybrid Approach ◽  
Similarity Index ◽  
Ct Images ◽  
Dice Similarity Coefficient ◽  
Morphological Operations ◽  
Lung Segmentation ◽  
Cad System ◽  
Detection And Diagnosis ◽  
Index Value

Lung segmentation is the initial step for detection and diagnosis for lung-related abnormalities and disease. In CAD system for lung cancer, this step traces the boundary for the pulmonary region from thorax in CT images. It decreases the overhead for a further step in CAD system by reducing the space for finding the ROIs. The major issue and challenging task for the segmentation is the inclusion of juxtapleural nodules in the segmented lungs. The chapter attempts 3D lung segmentation of CT images using active contour and morphological operations. The major steps in the proposed approach contain: preprocessing through various techniques, Otsu's thresholding for the binarizing the image; morphological operations are applied for elimination of undesired region and, finally, active contour for the segmentation of the lungs in 3D. For experiment, 10 subjects are taken from the public dataset of LIDC-IDRI. The proposed method achieved accuracies 0.979 Jaccard's similarity index value, 0.989 Dice similarity coefficient, and 0.073 volume overlap error when compared to ground truth.

CT Images Segmentation Based on Dynamic Relative Fuzzy Region Growing Algorithm

2014 ◽  
Vol 644-650 ◽  
pp. 4233-4236
Author(s):  
Zhen You Zhang ◽  
Guo Huan Lou
Keyword(s):  
Confidence Interval ◽  
Region Growing ◽  
Ct Images ◽  
Segmentation Algorithm ◽  
Experimental Results ◽  
Segmentation Result ◽  
Ct Image ◽  
Initial Segmentation ◽  
Fuzzy Region

Segmentation algorithm of CT Image is discussed in this paper. Dynamic relative fuzzy region growing algorithm is used for CT. At the beginning of the segmentation, the confidence interval region growing algorithm is used. The overlapping parts in the initial segmentation result is segmented again with the improved fuzzy connected, and then determine which region the overlapping parts belong to. Thus, the final segmentation result can be obtained. Since the algorithm contains the advantages of region growing algorithm, fuzzy connected algorithm and the region competition, the runtime of segmentation is greatly reduced and better experimental results are obtained.

Architecture Concrete Mesostructure Analysis Based on CT Image Fracture Process

2011 ◽  
Vol 368-373 ◽  
pp. 2638-2641
Author(s):  
Liang Zhao ◽  
Chang Hua Li ◽  
Fa Ning Dang ◽  
Deng Feng Chen
Keyword(s):  
Spatial Distribution ◽  
Volume Expansion ◽  
Fracture Process ◽  
Ct Images ◽  
Spatial Distributions ◽  
Ct Image ◽  
Destruction Process ◽  
Ct Data ◽  
The Relationship ◽  
Variation Process

Scanning observation on meso evolution of fracture in concrete is carried out by means of computerized tomography (CT) on uniaxial compressive condition. The cracks in the mortar expansion, in particular, the bond of mortar and aggregate which is key regions of concrete damaged, are drawn out through CT image and CT data, and the destruction process of the concrete can be divided into four stakes, compression, enlargement, the expansion of the CT crack,and destruction. According to the character of CT image，MMD is used to analyze the CT images of the concrete specimens in 4 stages of deformation. The components of the CT images are classified and the spatial distributions of crack or cavity, mortar and aggregate are obtained. The variation process of the relationship between distributions of crack or cavity magnitude and stress are obtained from classification maps. The specimens experienced the process of condensed, volume expansion, crack propagation, coalescence and failure. The method can not only reflect the spatial distribution of the materials but also simplify the following analyses that follow.

scholarly journals U-Net combined with multi-scale attention mechanism for liver segmentation in CT images

2021 ◽  
Vol 21 (1) ◽  
Author(s):  
Jiawei Wu ◽  
Shengqiang Zhou ◽  
Songlin Zuo ◽  
Yiyin Chen ◽  
Weiqin Sun ◽  
...  
Keyword(s):  
Work Experience ◽  
Spatial Location ◽  
Ct Images ◽  
Attention Mechanism ◽  
Dice Similarity Coefficient ◽  
Liver Segmentation ◽  
Multi Scale ◽  
Segmentation Methods ◽  
Spatial Location Information ◽  
Liver Region

Abstract Background The liver is an important organ that undertakes the metabolic function of the human body. Liver cancer has become one of the cancers with the highest mortality. In clinic, it is an important work to extract the liver region accurately before the diagnosis and treatment of liver lesions. However, manual liver segmentation is a time-consuming and boring process. Not only that, but the segmentation results usually varies from person to person due to different work experience. In order to assist in clinical automatic liver segmentation, this paper proposes a U-shaped network with multi-scale attention mechanism for liver organ segmentation in CT images, which is called MSA-UNet. Our method makes a new design of U-Net encoder, decoder, skip connection, and context transition structure. These structures greatly enhance the feature extraction ability of encoder and the efficiency of decoder to recover spatial location information. We have designed many experiments on publicly available datasets to show the effectiveness of MSA-UNet. Compared with some other advanced segmentation methods, MSA-UNet finally achieved the best segmentation effect, reaching 98.00% dice similarity coefficient (DSC) and 96.08% intersection over union (IOU).

Sign in / Sign up

Export Citation Format

Share Document