scholarly journals SD-UNet: A Novel Segmentation Framework for CT Images of Lung Infections

Electronics ◽  
2022 ◽  
Vol 11 (1) ◽  
pp. 130
Author(s):  
Shuangcai Yin ◽  
Hongmin Deng ◽  
Zelin Xu ◽  
Qilin Zhu ◽  
Junfeng Cheng
Keyword(s):  
Texture Features ◽  
Ground Truth ◽  
Lung Infection ◽  
Ct Images ◽  
Dice Similarity Coefficient ◽  
Health Crisis ◽  
Low Contrast ◽  
Global Context ◽  
Multi Scale ◽  
Lung Infections

Due to the outbreak of lung infections caused by the coronavirus disease (COVID-19), humans have to face an unprecedented and devastating global health crisis. Since chest computed tomography (CT) images of COVID-19 patients contain abundant pathological features closely related to this disease, rapid detection and diagnosis based on CT images is of great significance for the treatment of patients and blocking the spread of the disease. In particular, the segmentation of the COVID-19 CT lung-infected area can quantify and evaluate the severity of the disease. However, due to the blurred boundaries and low contrast between the infected and the non-infected areas in COVID-19 CT images, the manual segmentation of the COVID-19 lesion is laborious and places high demands on the operator. Quick and accurate segmentation of COVID-19 lesions from CT images based on deep learning has drawn increasing attention. To effectively improve the segmentation effect of COVID-19 lung infection, a modified UNet network that combines the squeeze-and-attention (SA) and dense atrous spatial pyramid pooling (Dense ASPP) modules) (SD-UNet) is proposed, fusing global context and multi-scale information. Specifically, the SA module is introduced to strengthen the attention of pixel grouping and fully exploit the global context information, allowing the network to better mine the differences and connections between pixels. The Dense ASPP module is utilized to capture multi-scale information of COVID-19 lesions. Moreover, to eliminate the interference of background noise outside the lungs and highlight the texture features of the lung lesion area, we extract in advance the lung area from the CT images in the pre-processing stage. Finally, we evaluate our method using the binary-class and multi-class COVID-19 lung infection segmentation datasets. The experimental results show that the metrics of Sensitivity, Dice Similarity Coefficient, Accuracy, Specificity, and Jaccard Similarity are 0.8988 (0.6169), 0.8696 (0.5936), 0.9906 (0.9821), 0.9932 (0.9907), and 0.7702 (0.4788), respectively, for the binary-class (multi-class) segmentation task in the proposed SD-UNet. The result of the COVID-19 lung infection area segmented by SD-UNet is closer to the ground truth compared to several existing models such as CE-Net, DeepLab v3+, UNet++, and other models, which further proves that a more accurate segmentation effect can be achieved by our method. It has the potential to assist doctors in making more accurate and rapid diagnosis and quantitative assessment of COVID-19.

scholarly journals Computing infection distributions and longitudinal evolution patterns in lung CT images

2021 ◽  
Vol 21 (1) ◽  
Author(s):  
Dongdong Gu ◽  
Liyun Chen ◽  
Fei Shan ◽  
Liming Xia ◽  
Jun Liu ◽  
...  
Keyword(s):  
Time Course ◽  
Lower Lobe ◽  
Ground Truth ◽  
Distribution Patterns ◽  
Lung Infection ◽  
Ct Images ◽  
Community Acquired Pneumonia ◽  
Disease Course ◽  
Distribution Maps ◽  
Significant Difference

Abstract Background Spatial and temporal lung infection distributions of coronavirus disease 2019 (COVID-19) and their changes could reveal important patterns to better understand the disease and its time course. This paper presents a pipeline to analyze statistically these patterns by automatically segmenting the infection regions and registering them onto a common template. Methods A VB-Net is designed to automatically segment infection regions in CT images. After training and validating the model, we segmented all the CT images in the study. The segmentation results are then warped onto a pre-defined template CT image using deformable registration based on lung fields. Then, the spatial distributions of infection regions and those during the course of the disease are calculated at the voxel level. Visualization and quantitative comparison can be performed between different groups. We compared the distribution maps between COVID-19 and community acquired pneumonia (CAP), between severe and critical COVID-19, and across the time course of the disease. Results For the performance of infection segmentation, comparing the segmentation results with manually annotated ground-truth, the average Dice is 91.6% ± 10.0%, which is close to the inter-rater difference between two radiologists (the Dice is 96.1% ± 3.5%). The distribution map of infection regions shows that high probability regions are in the peripheral subpleural (up to 35.1% in probability). COVID-19 GGO lesions are more widely spread than consolidations, and the latter are located more peripherally. Onset images of severe COVID-19 (inpatients) show similar lesion distributions but with smaller areas of significant difference in the right lower lobe compared to critical COVID-19 (intensive care unit patients). About the disease course, critical COVID-19 patients showed four subsequent patterns (progression, absorption, enlargement, and further absorption) in our collected dataset, with remarkable concurrent HU patterns for GGO and consolidations. Conclusions By segmenting the infection regions with a VB-Net and registering all the CT images and the segmentation results onto a template, spatial distribution patterns of infections can be computed automatically. The algorithm provides an effective tool to visualize and quantify the spatial patterns of lung infection diseases and their changes during the disease course. Our results demonstrate different patterns between COVID-19 and CAP, between severe and critical COVID-19, as well as four subsequent disease course patterns of the severe COVID-19 patients studied, with remarkable concurrent HU patterns for GGO and consolidations.

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).

AUTOMATIC MULTI-SCALE SEGMENTATION OF INTRAHEPATIC VESSEL IN CT IMAGES FOR LIVER SURGERY PLANNING

2013 ◽  
Vol 27 (01) ◽  
pp. 1357001 ◽  
Author(s):  
YI WANG ◽  
BIN FANG ◽  
JINGRUI PI ◽  
LEI WU ◽  
PATRICK S. P. WANG ◽  
...  
Keyword(s):  
Distribution Function ◽  
Blood Vessels ◽  
Medical Image ◽  
Automatic Segmentation ◽  
Hessian Matrix ◽  
Ct Images ◽  
Vascular Pattern ◽  
Low Contrast ◽  
Multi Scale ◽  
Normal Scale

The processing of blood vessels is an indispensable part in complicated surgeries of livers and hearts as the development of medical image technologies, which requires an automatic segmentation system over CT images of organs. However, the vascular pattern of livers in CT images suffers from low contrast to background so that the existing segmentation technologies are not able to extract the blood vessels completely. In the paper, we propose a new algorithm to extract the blood vessels of livers based on the adaptive multi-scale segmentation. First, we prove that the background histogram of normal scale blood vessels obeys the Gaussian distribution in CT images, and obtain the vascular distribution function from the vascular signal segmented from the background with a local optimal threshold. Second, Hessian matrix is employed to enhance the thin blood vessels before the extraction, and a complete and clear segmentation system for blood vessels is constructed by combining the major and thin blood vessels via filtering. Experimental results show the effectiveness of the proposed method, which is able to extract more complete blood vessels for 3D system, and assist the clinical liver surgeries efficiently.

scholarly journals Health Vigilance for Medical Imaging Diagnostic Optimization: Automated segmentation of COVID-19 lung infection from CT images

2021 ◽  
Vol 319 ◽  
pp. 01089
Author(s):  
Chala Mohamed ◽  
Benayad Nsiri ◽  
Soulaymani Abdelmajid ◽  
Mokhtari Abdelghani ◽  
Benaji Brahim
Keyword(s):  
Medical Imaging ◽  
Imaging Techniques ◽  
Lung Infection ◽  
Ct Images ◽  
Health Crisis ◽  
Proposed Model ◽  
Clinical Purpose ◽  
Model Training ◽  
Ct Segmentation ◽  
Set Up

Covid-19 disease has confronted the world with an unprecedented health crisis, faced with its quick spread, the health system is called upon to increase its vigilance. So, it is essential to set up a quick and automated diagnosis that can alleviate pressure on health systems. Many techniques used to diagnose the covid-19 disease, including imaging techniques, like computed tomography (CT). In this paper, we present an automatic method for COVID-19 Lung Infection Segmentation from CT Images, that can be integrated into a decision support system for the diagnosis of covid-19 disease. To achieve this goal, we focused to new techniques based on artificial intelligent concept, in particular the uses of deep convolutional neural network, and we are interested in our study to the most popular architecture used in the medical imaging community based on encoder-decoder models. We use an open access data collection for Artificial Intelligence COVID-19 CT segmentation or classification as dataset, the proposed model implemented on keras framework in python. A short description of model, training, validation and predictions is given, at the end we compare the result with an existing labeled data. We tested our trained model on new images, we obtained for Area under the ROC Curve the value 0.884 from the prediction result compared with manual expert segmentation. Finally, an overview is given for future works, and use of the proposed model into homogeneous framework in a medical imaging context for clinical purpose.

Modified Rolling-Ball Method for Pulmonary Parenchyma Segmentation

2020 ◽  
Vol 10 (2) ◽  
pp. 364-369
Author(s):  
Qi Mao ◽  
Shuguang Zhao
Keyword(s):  
Lung Cancer ◽  
Relative Survival ◽  
Lung Parenchyma ◽  
Ct Images ◽  
Dice Similarity Coefficient ◽  
Rolling Ball ◽  
Lung Cancer Patients ◽  
Multi Scale ◽  
Pulmonary Parenchyma ◽  
Novel Method

Background: Computer-aided detection/diagnosis (CAD) of lung nodules is a practical approach to improve the relative survival of lung cancer patients. Pulmonary parenchyma segmentation is an essential part of the CAD systems for detecting lung cancer. Methods: To solve the problems of improper segmentation and incomplete repair with the traditional rolling-ball method (RBM), we proposed a novel method with a multi-scale rolling-ball for pulmonary parenchyma segmentation. The traditional RBM suffers from the problem that there is often a mismatch between the rolling-ball radius and the size of the boundary defect. Additionally, the shapes of the rolling-ball and lung parenchyma are mismatched, which results in incomplete restoration of the boundary of lung parenchyma. Therefore, to address these issues, a novel multi-scale elliptic RBM (ME-RBM) is proposed for pulmonary parenchyma segmentation in this work. Results: The proposed approach was used to segment the lung parenchyma in 60 computed tomography (CT) images. The results revealed an area overlap measure (AOM) of 96.34%, dice similarity coefficient (DSC) of 97.83% and sensitivity (Sens) of 98.93%. Conclusion: A novel modified rolling-ball method was proposed and developed in this work for pulmonary parenchyma segmentation on chest CT images. The experimental results showed that the proposed approach was accurate and reliable.

scholarly journals A Method for Extracting Suspected Parotid Lesions in CT Images using Feature-based Segmentation and Active Contours based on Stationary Wavelet Transform

2013 ◽  
Vol 13 (5) ◽  
pp. 237-247 ◽  
Author(s):  
T. Y. Wu ◽  
S. F. Lin
Keyword(s):  
Wavelet Transform ◽  
Active Contours ◽  
Initial Conditions ◽  
Texture Features ◽  
Ct Images ◽  
Stationary Wavelet Transform ◽  
Low Contrast ◽  
Feature Based ◽  
Ct Data ◽  
Suspected Lesion

Abstract Automatic suspected lesion extraction is an important application in computer-aided diagnosis (CAD). In this paper, we propose a method to automatically extract the suspected parotid regions for clinical evaluation in head and neck CT images. The suspected lesion tissues in low contrast tissue regions can be localized with feature-based segmentation (FBS) based on local texture features, and can be delineated with accuracy by modified active contour models (ACM). At first, stationary wavelet transform (SWT) is introduced. The derived wavelet coefficients are applied to derive the local features for FBS, and to generate enhanced energy maps for ACM computation. Geometric shape features (GSFs) are proposed to analyze each soft tissue region segmented by FBS; the regions with higher similarity GSFs with the lesions are extracted and the information is also applied as the initial conditions for fine delineation computation. Consequently, the suspected lesions can be automatically localized and accurately delineated for aiding clinical diagnosis. The performance of the proposed method is evaluated by comparing with the results outlined by clinical experts. The experiments on 20 pathological CT data sets show that the true-positive (TP) rate on recognizing parotid lesions is about 94%, and the dimension accuracy of delineation results can also approach over 93%.

scholarly journals Low-Grade Glioma Segmentation Based on CNN with Fully Connected CRF

2017 ◽  
Vol 2017 ◽  
pp. 1-12 ◽  
Author(s):  
Zeju Li ◽  
Yuanyuan Wang ◽  
Jinhua Yu ◽  
Zhifeng Shi ◽  
Yi Guo ◽  
...  
Keyword(s):  
Conditional Random Field ◽  
Three Dimensional ◽  
Ground Truth ◽  
Low Grade Glioma ◽  
Dice Similarity Coefficient ◽  
Low Grade ◽  
Low Contrast ◽  
Magnetic Resonance Imaging Mri ◽  
3D Information ◽  
Fully Connected

This work proposed a novel automatic three-dimensional (3D) magnetic resonance imaging (MRI) segmentation method which would be widely used in the clinical diagnosis of the most common and aggressive brain tumor, namely, glioma. The method combined a multipathway convolutional neural network (CNN) and fully connected conditional random field (CRF). Firstly, 3D information was introduced into the CNN which makes more accurate recognition of glioma with low contrast. Then, fully connected CRF was added as a postprocessing step which purposed more delicate delineation of glioma boundary. The method was applied to T2flair MRI images of 160 low-grade glioma patients. With 59 cases of data training and manual segmentation as the ground truth, the Dice similarity coefficient (DSC) of our method was 0.85 for the test set of 101 MRI images. The results of our method were better than those of another state-of-the-art CNN method, which gained the DSC of 0.76 for the same dataset. It proved that our method could produce better results for the segmentation of low-grade gliomas.

scholarly journals Computing Infection Distributions and Longitudinal Evolution Patterns in Lung CT Images

2020 ◽  
Author(s):  
Dongdong Gu ◽  
Liyun Chen ◽  
Fei Shan ◽  
Liming Xia ◽  
Jun Liu ◽  
...  
Keyword(s):  
Time Course ◽  
Lower Lobe ◽  
Ground Truth ◽  
Distribution Patterns ◽  
Lung Infection ◽  
Ct Images ◽  
Community Acquired Pneumonia ◽  
Disease Course ◽  
Distribution Maps ◽  
Significant Difference

Abstract Background: Spatial and temporal lung infection distributions of coronavirus disease 2019 (COVID-19) and their changes could reveal important patterns to better understand the disease and its time course. This paper presents a pipeline to analyze statistically these patterns by automatically segmenting the infection regions and registering them onto a common template. Methods: A VB-Net is designed to automatically segment infection regions in CT images. After training and validating the model, we segmented all the CT images in the study. The segmentation results are then warped onto a pre-defined template CT image using deformable registration based on registering CT images within the lung fields. Then, the spatial distributions of infection regions and those during the course of the disease are calculated at the voxel level. Visualization and quantitative comparison can be performed between different groups. As a result, we compared the distribution maps between COVID-19 and community acquired pneumonia (CAP), between severe and critical COVID-19, and across different course of the disease. Results: For the performance of infection segmentation, comparing the segmentation results with manually annotated ground truth, the average Dice is 91.6%±10.0%, which is close to the inter-rater difference between two radiologists (the Dice is 96.1%±3.5%). The distribution map of infection regions shows that high probability regions are in the peripheral subpleural (up to 35.1% in probability). COVID-19 GGO lesions are more widely spread than consolidations, and the latter are located more peripherally. Onset images of severe COVID-19 (inpatients) show similar lesion distributions but with smaller areas of significant difference in the right lower lobe compared to critical COVID-19 (intensive care unit patients). About the disease course, critical COVID-19 patients showed four distinct patterns (progression, absorption, enlargement, and further absorption) with remarkable concurrent HU patterns for GGO and consolidations.Conclusions: By segmenting the infection regions with a VB-Net and registering all the CT images and the segmentation results onto a template, spatial distribution patterns of infections can be computed automatically. The algorithm provides an effective tool to visualize and quantify the spatial patterns of lung infection diseases and their changes during the disease course. Our results demonstrate different patterns between COVID-19 and CAP, between severe and critical COVID-19, as well as four distinct disease course patterns of the severe COVID-19 patients studied, with remarkable concurrent HU patterns for GGO and consolidations.

Sign in / Sign up

Export Citation Format

Share Document