Automatic lung segmentation for accurate quantitation of volumetric X-ray CT images

Abstract. Several image metrics have been proposed for pulmonary assessment via thoracic high-resolution computed tomography (HRCT) for various pathologies. This paper describes a systematic analysis of the utility of such metrics for characterizing interstitial lung disease (ILD) and chronic obstructive pulmonary disease (COPD), in comparison to data from pulmonary function testing (PFT). HRCT inspiratory and expiratory images for 14 patients with ILD and 11 patients with COPD were acquired retrospectively. PFT values were also acquired retrospectively for each patient. Using a statistical feature selection scheme, our study demonstrates that the quantitative image features perform quite well in comparison with the clinically-used PFT values. In the first 25 selected features out of the total 114 mixed image metrics and PFT values, 21 are from the image metrics. The classification using mixed selected image features and PFT values outperforms using PFT values alone. Our study also shows that these image metrics are not redundant with respect to the PFT values for characterization of ILD and COPD.

show abstract

“…1) is fully automatic. First, a segmentation algorithm [14] is applied to extract lung regions and segment the trachea from CT images. Next.…”

Section: Methodsmentioning

confidence: 99%

A Comparative Study of HRCT Image Metrics and PFT Values for Characterization of ILD and COPD

et al. 2012

View full text Add to dashboard Cite

show abstract

“…The lung volume was extracted using a typical, semiautomatic lung segmentation scheme [15,17]. The lung segmentation algorithm consists of the following three steps, which are based on gray-level thresholding, 3D region growing, and morphological operations.…”

Section: Lung Extractionmentioning

confidence: 99%

“…Most lung separation methods developed thus far are based on 2-dimensional (2D) slice images and consist of three steps: junction region detection, the search for a separating line, and lung separation [12][13][14][15][16]. Leader et al [12] used a heuristic method to detect the junction region between the left and right lungs; they searched for a separating line by finding the largest pixel value in the junction region.…”

Section: Introductionmentioning

confidence: 99%

“…Brown et al [14] identified the narrow junction region by modeling an individual lung shape as a cylinder, and a separating line was then determined using a dynamic programming algorithm. Hu et al [15] found anterior and posterior junction regions more reliably by obtaining the initial separation result using 2D morphological erosion and conditional dilation and then searching for a separating line. However, this method involves increased computational complexity in cases in which an area of the connected region is relatively large, as the morphological operations must be repeated many times.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Automatic Left and Right Lung Separation Using Free-Formed Surface Fitting on Volumetric CT

et al. 2014

View full text Add to dashboard Cite

This study presents a completely automated method for separating the left and right lungs using free-formed surface fitting on volumetric computed tomography (CT). The left and right lungs are roughly divided using iterative 3-dimensional morphological operator and a Hessian matrix analysis. A point set traversing between the initial left and right lungs is then detected with a Euclidean distance transform to determine the optimal separating surface, which is then modeled from the point set using a free-formed surfacefitting algorithm. Subsequently, the left and right lung volumes are smoothly and directly separated using the separating surface. The performance of the proposed method was estimated by comparison with that of a human expert on 44 CT examinations. For all data sets, averages of the root mean square surface distance, maximum surface distance, and volumetric overlap error between the results of the automatic and the manual methods were 0.032 mm, 2.418 mm, and 0.017 %, respectively. Our study showed the feasibility of automatically separating the left and right lungs by identifying the 3D continuous separating surface on volumetric chest CT images.

show abstract

“…The lungs are identified on the 3D CT image with a simplified version of the method of Hu et al (41). In that method, lung segmentation is performed in three steps to produce separated left and right lungs with smooth boundaries.…”

Section: Lung Region Definitionmentioning

confidence: 99%

Three-Dimensional Human Airway Segmentation Methods for Clinical Virtual Bronchoscopy

et al. 2002

View full text Add to dashboard Cite

Rationale and Objectives. The segmentation of airways from CT images is a critical first step for numerous virtual bronchoscopic (VB) applications. Automatic or semiautomatic methods are necessary, since manual segmentation is prohibitively time consuming. The methods must be robust and operate within a reasonable time frame to be useful for clinical VB use. The authors developed an integrated airway segmentation system and demonstrated its effectiveness on a series of human images. Materials and Methods.The authors' airway segmentation system draws on two segmentation algorithms: (a) an adaptive region-growing algorithm and (b) a new hybrid algorithm that uses both region growing and mathematical morphology. Images from an ongoing VB study were segmented by means of both the adaptive region-growing and the new hybrid methods. The segmentation volume, branch number estimate, and segmentation quality were determined for each case.Results. The results demonstrate the need for an integrated segmentation system, since no single method is superior for all clinically relevant cases. The region-growing algorithm is the fastest and provides acceptable segmentations for most VB applications, but the hybrid method provides superior airway edge localization, making it better suited for quantitative applications. In addition, the authors show that prefiltering the image data before airway segmentation increases the robustness of both regiongrowing and hybrid methods. Conclusion.The combination of these two algorithms with the prefiltering options allowed the successful segmentation of all test images. The times required for all segmentations were acceptable, and the results were suitable for the authors' VB application needs.Key Words. Bronchi, CT; bronchoscopy; computed tomography (CT), image processing; computed tomography (CT), threedimensional; trachea, CT. © AUR, 2002New multidetector spiral CT scanners can produce threedimensional (3D) volumetric images of the human airway tree consisting of hundreds of two-dimensional (2D) sections (1,2). A typical 3D image can include 400 or more 512 ϫ 512 0.6-mm sections. Such images provide an excellent basis for virtual bronchoscopy (VB) applications (3-15) and quantitative airway analysis (8,16 -20). New VB methods also allow for live guided nodule and lymph node biopsies (13,15). A critical first step in these VB applications is the segmentation of the airway tree. Manual interactive segmentation has been applied in some cases, but routine manual analysis is impractical for the large 3D images arising from the new scanners (21,22). A variety of semiautomatic airway segmentation techniques have been proposed, but none have been conclusively proved adequate for very large, high-resolution, 3D CT chest images (4,20 -30).

show abstract

Automatic lung segmentation for accurate quantitation of volumetric X-ray CT images

Cited by 881 publications

References 17 publications

A Comparative Study of HRCT Image Metrics and PFT Values for Characterization of ILD and COPD

A Comparative Study of HRCT Image Metrics and PFT Values for Characterization of ILD and COPD

Automatic Left and Right Lung Separation Using Free-Formed Surface Fitting on Volumetric CT

Three-Dimensional Human Airway Segmentation Methods for Clinical Virtual Bronchoscopy

Contact Info

Product

Resources

About