Lung Parenchyma Segmentation Research Articles

Cascaded 3D UNet architecture for segmenting the COVID-19 infection from lung CT volume

World Health Organization (WHO) declared COVID-19 (COronaVIrus Disease 2019) as pandemic on March 11, 2020. Ever since then, the virus is undergoing different mutations, with a high rate of dissemination. The diagnosis and prognosis of COVID-19 are critical in bringing the situation under control. COVID-19 virus replicates in the lungs after entering the upper respiratory system, causing pneumonia and mortality. Deep learning has a significant role in detecting infections from the Computed Tomography (CT). With the help of basic image processing techniques and deep learning, we have developed a two stage cascaded 3D UNet to segment the contaminated area from the lungs. The first 3D UNet extracts the lung parenchyma from the CT volume input after preprocessing and augmentation. Since the CT volume is small, we apply appropriate post-processing to the lung parenchyma and input these volumes into the second 3D UNet. The second 3D UNet extracts the infected 3D volumes. With this method, clinicians can input the complete CT volume of the patient and analyze the contaminated area without having to label the lung parenchyma for each new patient. For lung parenchyma segmentation, the proposed method obtained a sensitivity of 93.47%, specificity of 98.64%, an accuracy of 98.07%, and a dice score of 92.46%. We have achieved a sensitivity of 83.33%, a specificity of 99.84%, an accuracy of 99.20%, and a dice score of 82% for lung infection segmentation.

COVID-19 CT Scan Lung Segmentation: How We Do It.

The National Health Systems have been severely stressed out by the COVID-19 pandemic because 14% of patients require hospitalization and oxygen support, and 5% require admission to an Intensive Care Unit (ICU). Relationship between COVID-19 prognosis and the extent of alterations on chest CT obtained by both visual and software-based quantification that expresses objective evaluations of the percentage of ventilated lung parenchyma compared to the affected one has been proven. While commercial applications for automatic medical image computing and visualization are expensive and limited in their spread, the open-source systems are characterized by not enough standardization and time-consuming troubles. We analyzed chest CT exams on 246 patients suspected of COVID-19 performed in the Emergency Department CT room. The lung parenchyma segmentation was obtained by a threshold-based method using the open-source 3D Slicer software and software tools called “Segment Editor” and “Segment Quantification.” For the three main characteristics analyzed on lungs affected by COVID-19 pneumonia, a specifical densitometry value range was defined: from − 950 to − 700 HU for well-aerated parenchyma; from − 700 to − 250 HU for interstitial lung disease; from − 250 to 250 HU for parenchymal consolidation. For the well-aerated parenchyma and the interstitial alterations, the procedure was semi-automatic with low time consumption, whereas consolidations’ analysis needed manual interventions by the operator. After the chest CT, 13% of the sample was admitted to intensive care, while 34% of them to the sub-intensive care. In patients moved to intensive care, the parenchyma analysis reported a higher crazy paving presentation. The quantitative analysis of the alterations affecting the lung parenchyma of patients with COVID-19 pneumonia can be performed by threshold method segmentation on 3D Slicer. The segmentation could have an important role in the quantification in different COVID-19 pneumonia presentations, allowing to help the clinician in the correct management of patients.

Segmentation of lung parenchyma based on new U-NET network

As the risk of lung disease increases in people's daily lives and COVID-19 spreads around the world, lung screening has become critical. Owing to the unique lung tissue, traditional image segmentation methods are difficult to achieve accurate segmentation of lung tissues. In view of the complexity of lung tissue structure, it was found in the experiment that the segmentation accuracy of upper lung and lower lung parenchyma tissue was low. Aiming at this phenomenon, a new network model, new U-NET, was proposed based on the improvement and optimisation of U-NET network model. Experimental data show that the proposed new U-NET network model solves the problem of low segmentation accuracy of the original U-NET network segmentation model at both ends of lung, improves the segmentation accuracy of lung parenchyma on the whole, and verifies that the new U-NET network model is more suitable for parenchyma segmentation.

Automatic lung parenchyma segmentation using a deep convolutional neural network from chest X-rays

To detect and diagnosis the lungs related diseases, a Chest X-Ray (CXR) is the major tool used by the physician. Automated organ segmentation contributes to a crucial part of computer-aided detection (CAD) and diagnosis of diseases from CXRs as they enhance the accuracy in detecting, and also help in reducing the burden raised due to manual diagnosis from radiologists and medical practitioners. In this paper, an efficient automatic CAD system is proposed to detect the boundaries using a deep convolutional neural network (DCNN) model. The DCNN is trained in an end-to-end setting to facilitate fully automatic lung segmentation from anteroposterior or posteroanterior view CXRs. It learns to predict binary masks for a given CXR, by learning to discriminate regions of organ parenchyma from regions of no organ parenchyma. The proposed model’s architecture makes use of residual connections in all the concurrent up-sampling paths from each encoder block at every level, thus facilitating collective learning within blocks through inter-sharing of all high-dimensional feature maps. To generalize the proposed model to CXRs from all data distributions, image preprocessing techniques such as Top-Hat Bottom-Hat Transform and Contrast Limited Adaptive Histogram Equalization are employed. The proposed model is trained and tested using the JSRT, NLM-MC and Shenzhen Hospital datasets. The proposed method achieved a Dice Similarity Coefficient of 0.982 ± 0.018 and a Jaccard Similarity Coefficient of 0.967 ± 0.015. The implementation results demonstrated that the proposed method has surpassed the existing methods and our model is relatively lightweight and can be easily implemented on standard GPUs.

A Pulmonary Vascular Extraction Algorithm from Chest CT/CTA Images.

Segmentation of pulmonary vessels in CT/CTA images can help physicians better determine the patient's condition and treatment. However, due to the complexity of CT images, existing methods have limitations in the segmentation of pulmonary vessels. In this paper, a method based on the separation of pulmonary vessels in CT/CTA images is investigated. The method is divided into two steps: in the first step, the lung parenchyma is extracted using the Unet++ algorithm, which can effectively reduce the oversegmentation rate; in the second step, the pulmonary vessels in the lung parenchyma are extracted using nnUnet. According to the obtained lung parenchyma segmentation results, the “AND” operation is performed on the original image and the lung parenchyma segmentation results, and only the blood vessels within the lung parenchyma are segmented, which reduces the interference of external tissues and improves the segmentation accuracy. The experimental data source used CT/CTA images acquired from the partner hospital. After the experiments were performed on a total of 67 sets of images, the accuracy of CT and CTA images reached 85.1% and 87.7%, respectively. The comparison of whether to segment the lung parenchyma and with other conventional methods was also performed, and the experimental results showed that the algorithm in this paper has high accuracy.

Analysis of segmentation of lung parenchyma based on deep learning methods

Precise segmentation of lung parenchyma is essential for effective analysis of the lung. Due to the obvious contrast and large regional area compared to other tissues in the chest, lung tissue is less difficult to segment. Special attention to details of lung segmentation is also needed. To improve the quality and speed of segmentation of lung parenchyma based on computed tomography (CT) or computed tomography angiography (CTA) images, the 4th International Symposium on Image Computing and Digital Medicine (ISICDM 2020) provides interesting and valuable research ideas and approaches. For the work of lung parenchyma segmentation, 9 of the 12 participating teams used the U-Net network or its modified forms, and others used the methods to improve the segmentation accuracy include attention mechanism, multi-scale feature information fusion. Among them, U-Net achieves the best results including that the final dice coefficient of CT segmentation is 0.991 and the final dice coefficient of CTA segmentation is 0.984. In addition, attention U-Net and nnU-Net network also performs well. In this paper, the methods chosen by 12 teams from different research groups are evaluated and their segmentation results are analyzed for the study and references to those involved.

Effects of Lung Injury on Regional Aeration and Expiratory Time Constants: Insights From Four-Dimensional Computed Tomography Image Registration.

Rationale: Intratidal changes in regional lung aeration, as assessed with dynamic four-dimensional computed tomography (CT; 4DCT), may indicate the processes of recruitment and derecruitment, thus portending atelectrauma during mechanical ventilation. In this study, we characterized the time constants associated with deaeration during the expiratory phase of pressure-controlled ventilation in pigs before and after acute lung injury using respiratory-gated 4DCT and image registration.Methods: Eleven pigs were mechanically ventilated in pressure-controlled mode under baseline conditions and following an oleic acid model of acute lung injury. Dynamic 4DCT scans were acquired without interrupting ventilation. Automated segmentation of lung parenchyma was obtained by a convolutional neural network. Respiratory structures were aligned using 4D image registration. Exponential regression was performed on the time-varying CT density in each aligned voxel during exhalation, resulting in regional estimates of intratidal aeration change and deaeration time constants. Regressions were also performed for regional and total exhaled gas volume changes.Results: Normally and poorly aerated lung regions demonstrated the largest median intratidal aeration changes during exhalation, compared to minimal changes within hyper- and non-aerated regions. Following lung injury, median time constants throughout normally aerated regions within each subject were greater than respective values for poorly aerated regions. However, parametric response mapping revealed an association between larger intratidal aeration changes and slower time constants. Lower aeration and faster time constants were observed for the dependent lung regions in the supine position. Regional gas volume changes exhibited faster time constants compared to regional density time constants, as well as better correspondence to total exhaled volume time constants.Conclusion: Mechanical time constants based on exhaled gas volume underestimate regional aeration time constants. After lung injury, poorly aerated regions experience larger intratidal changes in aeration over shorter time scales compared to normally aerated regions. However, the largest intratidal aeration changes occur over the longest time scales within poorly aerated regions. These dynamic 4DCT imaging data provide supporting evidence for the susceptibility of poorly aerated regions to ventilator-induced lung injury, and for the functional benefits of short exhalation times during mechanical ventilation of injured lungs.

Research progress in lung parenchyma segmentation based on computed tomography

Lung diseases such as lung cancer and COVID-19 seriously endanger human health and life safety, so early screening and diagnosis are particularly important. computed tomography (CT) technology is one of the important ways to screen lung diseases, among which lung parenchyma segmentation based on CT images is the key step in screening lung diseases, and high-quality lung parenchyma segmentation can effectively improve the level of early diagnosis and treatment of lung diseases. Automatic, fast and accurate segmentation of lung parenchyma based on CT images can effectively compensate for the shortcomings of low efficiency and strong subjectivity of manual segmentation, and has become one of the research hotspots in this field. In this paper, the research progress in lung parenchyma segmentation is reviewed based on the related literatures published at domestic and abroad in recent years. The traditional machine learning methods and deep learning methods are compared and analyzed, and the research progress of improving the network structure of deep learning model is emphatically introduced. Some unsolved problems in lung parenchyma segmentation were discussed, and the development prospect was prospected, providing reference for researchers in related fields.

An Automatic Segmentation of Lung Structure Using Active Contour Model and Fuzzy Clustering Algorithm

The aim of this paper was to develop an active contour model based on a region and a Fuzzy C-Means (FCM) technique for lung nodule segmentation. In the end, the mortality rate is increased by detection and assisted diagnosis of nodules at an earlier stage. Computed tomography (CT) is the most sought after among many imaging modalities because of its image sensitivity, high resolution and isotropic acquisition. The suggested technique focuses on CT image acquisition, lung parenchyma reconstruction and segmentation of lung nodules. Using selective binary and Gaussian filtering with a new signed pressure force function (SBGF-new SPF) and clustering methods for nodule segmentation, parenchyma reconstruction can be used. The benefits of the proposed approach in terms of reduced error rate and improved measure of similarity are demonstrated by comparative experiments. CT, FCM, SPF, SBGF, SVM, ANN

Segmentation of Pulmonary Parenchyma from Pulmonary CT Based on ResU-Net++ Model

Pulmonary parenchyma segmentation is an important basic step in CT detection, which requires high accuracy and speed. According to the characteristics of lung structure, we present a method for segmenting CT images of lung parenchyma based on the ResU-net++ neural network model. The model preserves the deep feature parameters extracted from the residual blocks while paying attention to preserving the feature parameters obtained by transferring the shallow convolution blocks. The experimental results show that compared with U-net and U-net++ models, the lung parenchyma segmentation results using this method are more accurate, the accuracy of lung parenchyma edge identification is significantly improved, and it is more suitable for the diverse structures at both ends of the lung.

Integrating Lung Parenchyma Segmentation and Nodule Detection With Deep Multi-Task Learning.

Lung parenchyma segmentation is valuable for improving the performance of lung nodule detection in computed tomography (CT) images. Traditionally, the two tasks are performed separately. This paper proposes a deep multi-task learning (MTL) approach to integrate these tasks for better lung nodule detection. Three new ideas lead to our proposed approach. First, lung parenchyma segmentation is used as the attention module and is combined with nodule detection in a single deep network. Second, lung nodule detection is performed in an anchor-free manner by dividing it into two subtasks, nodule center identification and nodule size regression. Third, a novel pyramid dilated convolution block (PDCB) is proposed to utilize the advantage of dilated convolution and tackle its gridding problem for better lung parenchyma segmentation. Based on these ideas, we design our end-to-end deep network architecture and corresponding MTL method to achieve lung parenchyma segmentation and nodule detection simultaneously. We evaluate the proposed approach on the commonly used Lung Nodule Analysis 2016 (LUNA16) dataset. The experimental results show the value of our contributions and demonstrate that our approach can yield significant improvements compared with state-of-the-art counterparts.

Internal pressure driven finite element model of a single pulmonary acinus

A computer simulated, poroelastic, hyperelastic model was developed to replicate the pressure-volume response of a single pulmonary acinus (15th branch of the respiratory tree and daughter branches) with air flow at its core. An internal pressure driven approach was taken upon a small spherical geometry (99.2 mm3 in volume) representing this small segment of lung parenchyma. A reference porcine tracheal pressure at tidal breathing was adjusted from 1471 Pa to 998 Pa to accommodate for pressure drop, and the pressure of 998 Pa was applied to the model for parametric analysis of its pressure-volume characteristics. In targeting a proportional tidal volume change of approximately 15% while also inducing a pressure-volume hysteresis, material parameters of Young’s modulus of 4 kPa, Poisson’s ratio of 0.4, and a permeability of 5×10-5 cm3s-1cm-2 were identified as suitable. The energy loss over a single pressure-volume cycle for a pulmonary acinus was found to be 6.3×10-6 J. This model was qualitatively compared to the pressure-volume relationship of the original porcine data source, and then with experimental findings of the material parameters for lung parenchyma in medical literature, demonstrating same-order agreement.

3D Densely Connected Convolution Neural Networks for Pulmonary Parenchyma Segmentation from CT Images

Lung cancer is one of the deadliest diseases in the world today. It kills many people every year. For the diagnosis and treatment of lung cancer, accurate segmentation of lung tissue from CT images is an important process. It is necessary to design a fast and accurate segmentation method to accomplish this task. In the traditional computer-aided diagnosis system, the segmentation of Lung parenchyma is very complex, and the segmentation result depends on the performance of the parameters set in the previous stage. In order to solve these problems, we propose a 3D densely connected convolution neural network which based on deep learning. It has three densely connected blocks and three deconvolution layers. The experimental data set was taken from the public LIDC-IDRI database. A total of 888 samples with slice thickness less than 2.5 mm were selected in the experiments. And the number of samples of training set, test set and validation set is 708, 90 and 90 respectively. In addition, the experimental results show that our method is more accurate than 3D-Unet, but it requires less training parameters.

Automatic Lung Segmentation in CT Images Using Dilated Convolution Based Weighted Fully Convolutional Network

Lung cancer is one of the primary lung malignant tumour with the fastest increasing morbidity and mortality and the greatest threat to people’s health and life. Early detection of lung cancer can significantly increase patients’ chance of survival. Lung parenchymal segmentation is an essential pre-processing step for analysing thoracic computed tomography(CT) images. Conventional methods for lung segmentation rely on user generated features, and do not segment lung parenchymal with juxta-pleural nodules accurately. Deep learning has outperformed other methods in image classification and target recognition tasks. In this study, a new dilated convolutional based weighted fully convolutional network (FCN) has been proposed for the segmentation of lung parenchyma to minimize the juxta-pleural nodule issue. The effectiveness of this method was verified by experiments on 173,694 diagnosis CT images of lungs and their corresponding segmentation maps. The Dice similarity coefficient and pixel accuracy achieved are 0.9702 and 0.9833 respectively. The experiment results show that the proposed method can provide more accurate and robust results than traditional FCN.

Lung Parenchyma Segmentation Based on Improved Unet Network

Segmentation of lung parenchyma is an essential link in the diagnosis of lung diseases and also the premise of disease analysis. The accuracy of lung parenchyma segmentation affects the diagnosis and treatment of lung diseases. The size of input data will be reduced by using the traditional Unet network. In this paper, an improved Unet network structure is proposed to segment lung parenchyma automatically. In the process of convolution, the size of input data is kept constant by padding same and dropout layer is introduced into the network. We use cross entropy loss function to train the model for the first time. After the model converges, we use custom Dice loss function to fine tune to improve the accuracy. By calculating Jaccard coefficient and DSC coefficient, our lung parenchyma segmentation method has a very high accuracy, which is better than the earlier researchers’ segmentation algorithm. The significance of this study is to provide pretreatment for the diagnosis and treatment of lung diseases.

A Lung Dense Deep Convolution Neural Network for Robust Lung Parenchyma Segmentation

Lung parenchyma segmentation is the prerequisite for an automatic diagnosis system to analyze lung CT (computed tomography) images. However, traditional lung segmentation algorithms have poor adaptability and are not effectively robust regarding lung databases with blood vessels and small voids which can interfere the segmentation. The main work of this paper is as follows: Firstly, a lung dense deep convolutional neural network (LDDNet) is proposed, which adopts some popular optimizer methods, such as dense block, batch normalization (BN) and dropout. The performance of LDDNet is tested on the public lung database LIDC-IDRI which contains many cases of interference for segmentation. Secondly, the labeled with blood vessels and small voids are not contained by the public ground-truth masks of the LIDC-IDRI database, therefore these regions are labeled by us with LabelMe software. Thirdly, for the aim of exploring the effect of image preprocessing on segmenting lung CT images with deep neural network, contrast enhancing, median filtering and Laplacian filtering are used to preprocess the image as comparative experiments. Finally, dataset is classified into four classes by the geometrical shapes to test the performance of LDDNet. The accuracy of the segmentation experiment reaches over 99% and the four classes can all reach over 95%. Additionally, blood vessels and small voids are segmented out from the lung parenchyma which is not achieved by other methods. Experimental results confirm that the proposed LDDNet can segment the lung parenchymal area more accurately and has better robustness in comparison with other neural networks and most of the traditional methods.

An Efficient Segmentation Method for Juxtapleural Parenchyma with Modified Fractal Geometry-Based Pulmonary Boundary Detection

Lung cancer seems to be the world has ever known the most leading cause of death from cancer. Early diagnosis of lung cancer will help patients significantly. The exactness of tumour form, location, and volume detection wants to play an important role to play in effective tumour treatment. Artefacts can severely deteriorate the performance or even clinically obsolete of computed tomographic (CT) images. An automatic approach to incorporate the adaptive threshold iteration technique with the segmentation of images of the lungs. The implementation involves an enhanced convex hull repair to undertake a precise lung parenchyma segmentation. The results of the analysis say with certainty that the current approach can precisely segment juxtapleural parenchymal images and that the algorithm has been put into practice and evaluated in Matlab on Windows. The investigation results indicate that the modified convex hull calculation uses only a very small number of points. The study has also shown that the algorithm proposed improves the complexity of time compared to several other algorithms.

Research on Different Classifiers for Early Detection of Lung Nodules

Lung cancer is one of the most common deadliest disease which has highest death rate as per the recent medical research. However, research indicates that early detection of lung cancer improves chances of survival. The disease is identified using nodules attached to lung walls and lung parenchyma. Nodules plays significant role in identifying cancer in lungs. The proposed approach to determine lung nodules has three stages preprocessing, feature extraction and classification. Segmentation is the preprocessing technique involves two phases namely lung parenchyma segmentation and lung nodules segmentation. Then, texture features and geometric features are extracted using feature extraction algorithms. Lastly, using classification techniques the nodules are classified as benign or malign. TCIA dataset was used for validation of the proposed approach. Form the dataset, CT images were used which have high density resolution and adequate information which helps to find every small detail easily. The proposed method helps in improving accuracy to find number of the lung nodules in lung region and also helps is differentiating benign and malign nodules using CNN architecture. Different classifiers such as SVM, MLP and CNN classifiers are used in comparison analysis. As the result, we conclude that the approach of feature extraction with CNN decreases the false positive rate significantly compared to the existing classification approaches.

Automated Segmentation of Lung Parenchyma Using Colour Based Fuzzy C-Means Clustering

In this article, a combination of fuzzy logic and color features-based fuzzy C means (FCM) clustering approach is proposed for segmenting the parenchyma of the computed tomography (CT) lung images. In this approach, the lung parenchyma is considered as the region of interest (ROI). This method is carried out in five steps. First step is the pre-processing of CT lung images to remove the noise and artefacts present in it. The border detection process is carried out as a second step where all the regions including the tissue and lung parenchyma is separated. Third step is the color formation process in which the image along with its border is formed in magenta color. Fourth step is the color features extraction from the obtained image border. In this process, the obtained features are given as input towards the FCM clustering method to produce a segmented foreground image from the background. This method is tested over 150 CT scans for finding the efficiency. From the experimental results, it can be observed that the proposed approach gives an overall accuracy of 96.31% for segmenting lung parenchyma.

Pulmonary Nodule Detection in CT Images Using Optimal Multilevel Thresholds and Rule-based Filtering

Lung cancer is the most common cancer causing the highest mortality rate as per the analysis of previous and recent year worldwide statistics. The main reason behind the high mortality is late detection of its fatal stage. Early detection of lung nodules offers challenging tasks due to nodules’ types, size, unfavorable locations, and attachment with the vessels. In this paper, we propose a method of early detection of lung nodules in computed tomography images, which can assist radiologists to locate the suspected nodules. The method consists of three major sections, i.e. the extraction and segmentation of lung parenchyma through clustering algorithm, extraction and highlighting the region of interests through optimal multilevel thresholding using particle swarm optimization, selection and application of 2D features to detect the initial nodule candidates and further iteratively false positive reduction by the analysis of 3D features. We used 84 CT scans with 301 nodules taken from publically available Lung Image Database Consortium – Image Database Resource Initiative (LIDC-IDRI) data set for experiment. In general for all types of nodules, the proposed method achieved an overall sensitivity of 84.05% with a reduced false positive rate of 1.93 per CT scan. Our results have been compared with the methods from literature which show improved false positive rate along with comparable sensitivity.