Automated lung segmentation in X-ray computed tomography: development and evaluation of a heuristic threshold-based scheme1

doi:10.1016/S1076-6332(03)00380-5

Academic Radiology

Volume 10, Issue 11, November 2003, Pages 1224-1236

https://doi.org/10.1016/S1076-6332(03)00380-5 Get rights and content

Abstract

Rationale and Objectives. To develop and evaluate a reliable, fully-automated lung segmentation scheme for application in X-ray computed tomography.

Materials and Methods. The automated scheme was heuristically developed using a slice-based, pixel-value threshold and two sets of classification rules. Features used in the rules include size, circularity, and location. The segmentation scheme operates slice-by-slice and performs three key operations: (1) image preprocessing to remove background pixels, (2) computation and application of a pixel-value threshold to identify lung tissue, and (3) refinement of the initial segmented regions to prune incorrectly detected airways and separate fused right and left lungs.

Results. The performance of the automated segmentation scheme was evaluated using 101 computed tomography cases (91 thick slice, 10 thin slice scans). The 91 thick cases were pre- and post-surgery from 50 patients and were not independent. The automated scheme successfully segmented 94.0% of the 2,969 thick slice images and 97.6% of the 1,161 thin slice images. The mean difference of the total lung volumes calculated by the automated scheme and functional residual capacity plus 60% inspiratory capacity was −24.7 ± 508.1 mL. The mean differences of the total lung volumes calculated by the automated scheme and an established, commonly used semi-automated scheme were 95.2 ± 52.5 mL and −27.7 ± 66.9 mL for the thick and thin slice cases, respectively.

Conclusion. This simple, fully-automated lung segmentation scheme provides an objective tool to facilitate lung segmentation from computed tomography scans.

Section snippets

Materials and methods

The fully-automated lung segmentation scheme was heuristically developed to process all image slices contained in axial, thoracic CT examination without manual intervention. The scheme performs a series of image processing tasks sequentially, slice-by-slice through the CT examination, including images in which lung tissue may be absent. Several preprocessing tasks precede pixel-value thresholding of the image to segment the lungs, and several refinement tasks succeed the threshold segmentation

Results

The automated scheme successfully segmented 2,792 (94.0%) of the 2,969 images in cases 1–91 (thick slice scans averaging 33 slices per examination) and 1,133 (97.6%) of the 1,161 images in cases 92–101 (thin slice scans averaging 116 slices per examination). The scheme failed to prune large airways, incorrectly included bowel or other air cavities, failed to separate fused lungs, excluded lung tissue, and included non-lung tissue in 123 (4.1%), 31 (1.0%), 15 (0.5%), 3 (0.1%), and 5 (0.2%) image

Discussion

The heuristically developed, fully-automated lung segmentation scheme accurately and reliably segmented the lungs in thick and thin slice CT scans with reasonably short computational time. The total lung volumes calculated from the CT scans (TLV_CT) using the automated scheme were comparable to an “established” semi-automated scheme, and both schemes were in strong agreement with PFT values calculated using body plethysmography. The automated and semi-automated schemes are dependent on a

Acknowledgements

The authors thank Drs Harvey O. Coxson and Kenneth P. Whittall, University of British Columbia McDonald Research Laboratory, St Paul’s Hospital, Vancouver, Canada, for their helpful guidance regarding the semi-automated segmentation scheme. The authors also thank Paul Thompson and Glenn Maitz from the University of Pittsburgh, Pittsburgh PA, for their dedicated assistance with data analysis and management.

References (33)

N.L. Muller et al.
“Density mask.” An objective method to quantitate emphysema using computed tomography
Chest
(1988)
R.S. Crausman et al.
Quantitative CT predicts the severity of physiologic dysfunction in patients with lymphangioleiomyomatosis
Chest
(1996)
M. Kinsella et al.
Quantification of emphysema by computed tomography using a density mask program and correlation with pulmonary function tests
Chest
(1990)
R.M. Rogers et al.
Preoperative severity of emphysema predictive of improvement after lung volume reduction surgeryuse of CT morphometry
Chest
(2000)
R.M. Summers et al.
CT virtual bronchoscopy of the central airways in patients with Wegener’s granulomatosis
Chest
(2002)
H. Adams et al.
An appraisal of CT pulmonary density mapping in normal subjects
Clin Radiol
(1991)
W.A. Kalender et al.
Semiautomatic evaluation procedures for quantitative CT of the lung
J Comput Assist Tomogr
(1991)
R. Zagers et al.
Quantitative analysis of computed tomography scans of the lungs for the diagnosis of pulmonary emphysemaa validation study of a semiautomated contour detection technique
Invest Radiol
(1995)
M.F. McNitt-Gray et al.
Development and testing of image-processing methods for the quantitative assessment of airway hyperresponsiveness from high-resolution CT images
J Comput Assist Tomogr
(1997)
D.C. Archer et al.
Automated in vivo quantification of emphysema
Radiology
(1993)

K.T. Bae et al.

Patients with emphysemaquantitative CT analysis before and after lung volume reduction surgery

Radiology

(1997)

Y. Nakano et al.

Core to rind distribution of severe emphysema predicts outcome of lung volume reduction surgery

Am J Respir Crit Care Med

(2001)

P. Wonkyu et al.

Segmentation of intrathoracic airway treesa fuzzy logic approach

IEEE Trans Med Imaging

(1998)

J. Remy et al.

Multiplanar and three-dimensional reconstruction techniques in CTimpact on chest diseases

Eur Radiol

(1998)

M.L. Giger et al.

Computerized detection of pulmonary nodules in computed tomography images

Invest Radiol

(1994)

S.G. Armato et al.

Automated detection of lung nodules in CT scanspreliminary results

Med Phys

(2001)

Cited by (146)

Quantitative analysis of fast non-local means algorithm smoothing factor impact on lung segmentation accuracy in computed tomography images
2024, Radiation Physics and Chemistry
In computed tomography (CT), noise inevitably occurs during image acquisition and degrades segmentation accuracy. Thus, in this study, we compared and evaluated quantitative factors to derive the optimized smoothing factor of the fast non-local means (FNLM) algorithm, which can improve the accuracy of lung segmentation. Gaussian noise with a standard deviation of 0.05 was added to the lung phantom image and clinically acquired lung image, respectively, and the smoothing factor of the FNLM algorithm was modeled and applied from 0.03 to 0.02 in 0.01 intervals. The segmentation algorithm is modeled based on a region-growing approach. For evaluating segmentation performance, the root mean square error (RMSE), peak signal-to-noise ratio (PSNR) and dice score (DSC) were used. The quantitative evaluation demonstrated that the RMSE, PSNR and DSC exhibited the greatest improvement when the smoothing factor was set as 0.10 for both the phantom and clinically acquired lung images. In the lung phantom images, the RMSE, PSNR, and DSC displayed improvements of 8.40, 1.33, and 1.33 times compared to the noisy images. In the clinically acquired lung images, the RMSE, PSNR, and DSC exhibited enhancements of 9.74, 1.35, 1.37 times respectively, compared to the noisy images. We confirmed that lung segmentation performance was most effectively improved when the smoothing factor of the FNLM algorithm was set to 0.10. Moreover, we demonstrated that adjusting the appropriate smoothing factor in CT images can improve lung segmentation performance.
Pulmonary nodules detection assistant platform: An effective computer aided system for early pulmonary nodules detection in physical examination
2022, Computer Methods and Programs in Biomedicine
Background and Objective: Early detection of the pulmonary nodule from physical examination low-dose computer tomography (LDCT) images is an effective measure to reduce the mortality rate of lung cancer. Although there are many computer aided diagnosis (CAD) methods used for detecting pulmonary nodules, there are few CAD systems for small pulmonary nodule detection with a large amount of physical examination LDCT images.
Methods: In this work, we designed a CAD system called Pulmonary Nodules Detection Assistant Platform for early pulmonary nodules detection and classification based on the physical examination LDCT images. Based on the preprocessed physical examination CT images, the three-dimensional (3D) CNN-based model is presented to detect candidate pulmonary nodules and output detection results with quantitative parameters, the 3D ResNet is used to classify the detected nodules into intrapulmonary nodules and pleural nodules to reduce the physician workloads, and the Fully Connected Neural Network (FCNN) is used to classify ground-glass opacity (GGO) nodules and non-GGO nodules to help doctor pay more attention to those suspected early lung cancer nodules.
Results: Experiments are performed on our 1000 samples of physical examinations (LNPE1000) with an average diameter of 5.3 mm and LUNA16 dataset with an average diameter of 8.31 mm, which show that the designed CAD system is automatic and efficient for detecting smaller and larger nodules from different datasets, especially for the detection of smaller nodules with diameter between 3 mm and 6 mm in physical examinations. The accuracy of pulmonary nodule detection reaches 0.879 with an average of 1 false positive per CT in LNPE1000 dataset, which is comparable to the experienced physicians. The classification accuracy reaches 0.911 between intrapulmonary and pleural nodules, and 0.950 between GGO and non-GGO nodules, respectively.
Conclusion: Experimental results show that the proposed pulmonary nodule detection model is robust for different datasets, which can successfully detect smaller and larger nodules in CT images obtained by physical examination. The interactive platform of the designed CAD system has been on trial in a hospital by combining with manual reading, which helps doctors analyze clinical data dynamically and improves the nodule detection efficiency in physical examination applications.
Deep Residual Separable Convolutional Neural Network for lung tumor segmentation
2022, Computers in Biology and Medicine
Lung cancer is one of the deadliest types of cancers. Computed Tomography (CT) is a widely used technique to detect tumors present inside the lungs. Delineation of such tumors is particularly essential for analysis and treatment purposes. With the advancement in hardware technologies, Machine Learning and Deep Learning methods are outperforming the traditional methods in the field of medical imaging. In order to delineate lung cancer tumors, we have proposed a deep learning-based methodology which includes a maximum intensity projection based pre-processing method, two novel deep learning networks and an ensemble strategy. The two proposed networks named Deep Residual Separable Convolutional Neural Network 1 and 2 (DRS-CNN1 and DRS-CNN2) achieved better performance over the state-of-the-art U-net network and other segmentation networks. For fair comparison, we have evaluated the performances of all networks on Medical Segmentation Decathlon (MSD) and StructSeg 2019 datasets. The DRS-CNN2 achieved a mean Dice Similarity Coefficient (DSC) of 0.649, mean 95 Hausdorff Distance (HD95) of 18.26, mean Sensitivity 0.737 and a mean Precision of 0.765 on independent test sets.
Transfer learning techniques for medical image analysis: A review
2022, Biocybernetics and Biomedical Engineering
Medical imaging is a useful tool for disease detection and diagnostic imaging technology has enabled early diagnosis of medical conditions. Manual image analysis methods are labor-intense and they are susceptible to intra as well as inter-observer variability. Automated medical image analysis techniques can overcome these limitations. In this review, we investigated Transfer Learning (TL) architectures for automated medical image analysis. We discovered that TL has been applied to a wide range of medical imaging tasks, such as segmentation, object identification, disease categorization, severity grading, to name a few. We could establish that TL provides high quality decision support and requires less training data when compared to traditional deep learning methods. These advantageous properties arise from the fact that TL models have already been trained on large generic datasets and a task specific dataset is only used to customize the model. This eliminates the need to train the models from scratch. Our review shows that AlexNet, ResNet, VGGNet, and GoogleNet are the most widely used TL models for medical image analysis. We found that these models can understand medical images, and the customization refines the ability, making these TL models useful tools for medical image analysis.
LungSeg-Net: Lung field segmentation using generative adversarial network
2021, Biomedical Signal Processing and Control
Citation Excerpt :
In normal lung CT scan, it is easy to discriminate between lung and non-lung region because of the large difference in attenuation [8]. Thus, initial approaches [9–14] for lung segmentation followed simple grey-level thresholding based approach for segmentation of the lungs from non-lung region. Sun et al. [11] segmented the lung region using region growing algorithm based on grey value, region homogeneity, and gradient magnitude followed by the morphological closing operation to fill the inside cavities.
Automatic lung segmentation is an essential step towards the Computer-Aided Diagnosis of the lung CT scan. However, in presence of dense abnormalities, existing methods fail in accurate lung segmentation. In this paper, a generative adversarial networks-based approach is proposed for improving the accuracy of lung segmentation. The proposed network effectively segments the lung region from the surrounding chest region hence, named as LungSeg-Net. In the proposed LungSeg-Net, the input lung CT slices are processed through the trail of encoders which encode these slices into a set of feature maps. Further, a multi-scale dense-feature extraction (MSDFE) module is designed for extraction of multi-scale features from the set of encoded feature maps. Finally, the decoders are employed to obtain the lung segmentation map from the multi-scale features. The MSDFE makes the network to learn the relevant features of dense abnormalities whereas the iterative down-sampling followed by the up-sampling makes it invariant to the size of the dense abnormality. The publicly available benchmark ILD dataset is used for the experimental analysis. The qualitative and quantitative analysis has been carried out to compare the performance of the proposed network with the existing state-of-the-art methods for lung segmentation. The experimental analysis show that the performance of the proposed LungSeg-Net is invariant to the presence of dense abnormalities in lung CT scan.
Fully automatic deep learning-based lung parenchyma segmentation and boundary correction in thoracic CT scans
2024, International Journal of Computer Assisted Radiology and Surgery

View all citing articles on Scopus

^☆: Supported in part by the George H. Love Foundation.

View full text

Original investigationAutomated lung segmentation in X-ray computed tomography: development and evaluation of a heuristic threshold-based scheme1☆

Abstract

Section snippets

Materials and methods

Results

Discussion

Acknowledgements

Chest

Chest

Chest

Chest

Chest

Clin Radiol

Semiautomatic evaluation procedures for quantitative CT of the lung

J Comput Assist Tomogr

Quantitative analysis of computed tomography scans of the lungs for the diagnosis of pulmonary emphysemaa validation study of a semiautomated contour detection technique

Invest Radiol

Development and testing of image-processing methods for the quantitative assessment of airway hyperresponsiveness from high-resolution CT images

J Comput Assist Tomogr

Automated in vivo quantification of emphysema

Radiology

Patients with emphysemaquantitative CT analysis before and after lung volume reduction surgery

Radiology

Core to rind distribution of severe emphysema predicts outcome of lung volume reduction surgery

Am J Respir Crit Care Med

Segmentation of intrathoracic airway treesa fuzzy logic approach

IEEE Trans Med Imaging

Multiplanar and three-dimensional reconstruction techniques in CTimpact on chest diseases

Eur Radiol

Computerized detection of pulmonary nodules in computed tomography images

Invest Radiol

Automated detection of lung nodules in CT scanspreliminary results

Med Phys

Original investigation
Automated lung segmentation in X-ray computed tomography: development and evaluation of a heuristic threshold-based scheme¹☆