Automated lung segmentation and smoothing techniques for inclusion of juxtapleural nodules and pulmonary vessels on chest CT images

Zhou, Shanshan; Cheng, Yuanzhi; Tamura, Shinichi

doi:10.1016/j.bspc.2014.03.010

Cited by 48 publications

(26 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It can be seen from Figure 9 that the segmented lung images are very similar, and the difference between the segmented lung image with our method and that with the graph-cut based method presented in [5] and also that with the method proposed in [11] are too tiny to observe.…”

Section: Discussionmentioning

confidence: 86%

Many Is Better Than One: An Integration of Multiple Simple Strategies for Accurate Lung Segmentation in CT Images

Shi

Zhao

et al. 2016

BioMed Research International

View full text Add to dashboard Cite

Accurate lung segmentation is an essential step in developing a computer-aided lung disease diagnosis system. However, because of the high variability of computerized tomography (CT) images, it remains a difficult task to accurately segment lung tissue in CT slices using a simple strategy. Motived by the aforementioned, a novel CT lung segmentation method based on the integration of multiple strategies was proposed in this paper. Firstly, in order to avoid noise, the input CT slice was smoothed using the guided filter. Then, the smoothed slice was transformed into a binary image using an optimized threshold. Next, a region growing strategy was employed to extract thorax regions. Then, lung regions were segmented from the thorax regions using a seed-based random walk algorithm. The segmented lung contour was then smoothed and corrected with a curvature-based correction method on each axis slice. Finally, with the lung masks, the lung region was automatically segmented from a CT slice. The proposed method was validated on a CT database consisting of 23 scans, including a number of 883 2D slices (the number of slices per scan is 38 slices), by comparing it to the commonly used lung segmentation method. Experimental results show that the proposed method accurately segmented lung regions in CT slices.

show abstract

Section: Discussionmentioning

confidence: 86%

Many Is Better Than One: An Integration of Multiple Simple Strategies for Accurate Lung Segmentation in CT Images

Shi

Zhao

et al. 2016

BioMed Research International

View full text Add to dashboard Cite

show abstract

“…However, lung segmenting is a complex task due to various densities and complex structures of lung CT images, as well as extremely varied properties of pulmonary lesions. 5 Statistics indicated that about 5 $ 17% of the lung nodules were missed in the sampled data due to inaccurate lung segmentation. 6 Researchers have presented various methods for segmenting lungs.…”

Section: Introductionmentioning

confidence: 99%

A fully automatic segmentation algorithm for CT lung images based on random forest

2019

View full text Add to dashboard Cite

Purpose Several negative factors, such as juxta‐pleural nodules, pulmonary vessels, and image noise, make accurately segmenting lungs from computed tomography (CT) images a complex task. We propose a novel hybrid automated algorithm in the paper based on random forest to deal with the issues. Our method aims to eliminate the effect of the factors and generate accurate segmentation of lungs from CT images. Methods Our algorithm consists of five main steps: image preprocessing, lung region extraction, trachea elimination, lung separation, and contour correction. A lung CT image is first preprocessed with a novel normal vector correlation‐based image denoising approach and decomposed into a group of multiscale subimages. A modified superpixel segmentation method is then performed on the first‐level subimage to generate a set of superpixels, and a random forest classifier is employed to segment the lungs by classifying the superpixels of each subimage‐based on the features extracted from them. The initial lung segmentation result is further refined through trachea elimination using an iterative thresholding approach, lung separation based on context information of image sequence, and contour correction with a corner detection technique. Results Our algorithm is tested on a set of CT images affected with interstitial lung diseases, and experiments show that the algorithm achieves high accuracy on lung segmentation with 0.9638 Jaccard’s index and 0.9867 Dice similarity coefficient, compared with ground truths. Additionally, our algorithm achieves an average 7.7% better Dice similarity coefficient than compared conventional lung segmentation methods and 1% better than Deep Learning. Conclusions Our algorithm can segment lungs from lung CT images with good performance in a fully automatic fashion, and it is of great assistance for lung disease detection in the computer‐aided detection system.

show abstract

“…The method is not robust against the noisy environment and due to that some false detection of fissures can be expected. The fast and fully automatic scheme based on iterative weighted averaging and adaptive curvature threshold is proposed in [36] to facilitate the lung segmentation accurately in order for the inclusion of juxta-pleural nodules and pulmonary vessels. This also ensures the smoothness of the lung boundary.…”

Section: Introductionmentioning

confidence: 99%

Efficient Segmentation of Lung Using FIDRM Filter and Successive Peak Quantization Transform

Firdouse¹,

Balasubramanian²

2018

IJIES

View full text Add to dashboard Cite

Abstract:Computed Tomography (CT) is the main source for analyzing the lung diseases and the preplanning of pulmonary surgeries. The accurate interpretation of chest CT scan makes a challenge to radiologists due to its complex visual nature. This paper proposes a novel method to segment the left and right lungs from the background of CT images to assist the pathologists for the easy and accurate diagnosis of pulmonary diseases. The segmentation of lung is a challenging task due to the anatomical difference of different people. This paper develops a novel algorithm namely successive peak based quantization transform (SPQT) to segment the lungs from the background. This method extracts 8 bit patterns from the input lung image and at last a BYTE data which is formed from 8 bit patterns is produced. Prior to SPQT lung segmentation, the lung image which may contain impulse noise is reduced into noise free one by using 'Fuzzy Impulse Detection and Reduction Method' (FIDRM). The novel lung image hikes the accuracy to a significant level than the existing algorithms.

show abstract

Automated lung segmentation and smoothing techniques for inclusion of juxtapleural nodules and pulmonary vessels on chest CT images

Cited by 48 publications

References 19 publications

Many Is Better Than One: An Integration of Multiple Simple Strategies for Accurate Lung Segmentation in CT Images

Many Is Better Than One: An Integration of Multiple Simple Strategies for Accurate Lung Segmentation in CT Images

A fully automatic segmentation algorithm for CT lung images based on random forest

Efficient Segmentation of Lung Using FIDRM Filter and Successive Peak Quantization Transform

Contact Info

Product

Resources

About