A Novel 3D Joint MGRF Framework for Precise Lung Segmentation

Abdollahi, Behnoush; Soliman, Ahmed; Civelek, A. Cahid; Li, X.-F.; Gimel’farb, Georgy; El-Baz, Ayman

doi:10.1007/978-3-642-35428-1_11

Cited by 19 publications

(20 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These methods can be generally divided into the following four major categories: threshold method [11][12][13][14][15][16][17][18], deformable boundary models [19][20][21][22][23][24], edge-based methods [25][26][27][28], and registration-based method [29,30]. Lungs appear as dark regions in CT scans, since they are essentially bags full of air inside the body.…”

Section: Previous Workmentioning

confidence: 99%

“…The segmentation of the lung fields was iteratively refined by the iterative conditional mode (ICM) relaxation that maximizes a Markov-Gibbs random field (MGRF) energy which accounts for the first-order visual appearance model and the spatial interactions between the image voxels. Further, they enlarged their work by applying their iterative MGRF-based segmentation framework on different scale spaces [23,24].…”

Section: Previous Workmentioning

confidence: 99%

See 1 more Smart Citation

Automated Lung Segmentation from HRCT Scans with Diffuse Parenchymal Lung Diseases

Pulagam¹,

Kande²,

Ede³

et al. 2016

J Digit Imaging

View full text Add to dashboard Cite

Performing accurate and fully automated lung segmentation of high-resolution computed tomography (HRCT) images affected by dense abnormalities is a challenging problem. This paper presents a novel algorithm for automated segmentation of lungs based on modified convex hull algorithm and mathematical morphology techniques. Sixty randomly selected lung HRCT scans with different abnormalities are used to test the proposed algorithm, and experimental results show that the proposed approach can accurately segment the lungs even in the presence of disease patterns, with some limitations in the apices and bases of lungs. The algorithm demonstrates a high segmentation accuracy (dice similarity coefficient = 98.62 and shape differentiation metrics d mean = 1.39 mm, and d rms = 2.76 mm). Therefore, the developed automated lung segmentation algorithm is a good candidate for the first stage of a computer-aided diagnosis system for diffuse lung diseases.

show abstract

Section: Previous Workmentioning

confidence: 99%

Section: Previous Workmentioning

confidence: 99%

Automated Lung Segmentation from HRCT Scans with Diffuse Parenchymal Lung Diseases

Pulagam¹,

Kande²,

Ede³

et al. 2016

J Digit Imaging

View full text Add to dashboard Cite

show abstract

“…Three filtered GSS phantoms were generated from the original 3D phantom using 3D Gaussian Kernels (GKs) as described in [13,14].…”

Section: Joint Markov-gibbs Model Of Ct Lung Imagesmentioning

confidence: 99%

“…To overcome these limitations, we introduce a validation approach that generates 3D realistic phantoms to validate our developed segmentation approach [13,14]. To the best of our knowledge, we are the first authors who introduce 3D realistic synthetic phantoms that simulate both appearance and 3D geometry of a real lung in order to validate segmentation approaches.…”

Section: Introductionmentioning

confidence: 99%

Segmentation of lung region based on using parallel implementation of joint MGRF: Validation on 3D realistic lung phantoms

Soliman

Khalifa

Alansary

et al. 2013

2013 IEEE 10th International Symposium on Biomedical Imaging

Self Cite

View full text Add to dashboard Cite

The segmentation of the lung tissues in chest Computed Tomography (CT) images is an important step for developing any ComputerAided Diagnostic (CAD) system for lung cancer and other pulmonary diseases. In this paper, we introduce a new framework to generate 3D realistic synthetic phantoms to validate our developed Joint Markov-Gibbs based lung segmentation approach from CT data. Our framework is based on using a 3D generalized GaussMarkov Random Field (GGMRF) model of voxel intensities with pairwise interaction to model the 3D appearance of the lung tissues. Then, the appearance of the generated 3D phantoms is simulated based on iterative minimization of an energy function that is based on using the learned 3D-GGMRF image model. These 3D realistic phantoms can be used to evaluate the performance of any lung segmentation approach. In this paper, we used the 3D realistic phantoms to evaluate the performance of our developed lung segmentation approach based on using the Dice Similarity Coefficient (DSC) metric and the Receiver Operating Characteristics (ROC). The DSC demonstrated that our approach achieves a mean DSC value of 0.994±0.0034. Moreover, the ROC analysis for our method showed the best performance (area 0.99), while intensity showed the worst performance (area 0.92).

show abstract

“…In addition to edge detection and DM-based approaches, statistical-based methods [138][139][140][141][142][143][144][145][146][147] have been proposed for TRUS prostate segmentation, such as pixel classification and graph-cut [148] methods. In pixel classification techniques, each pixel is defined as object or non-object based on a set of extracted image fea-…”

Section: A In-vitro Prostate Cancer Diagnostic Technologiesmentioning

confidence: 99%

A novel NMF-based DWI CAD framework for prostate cancer.

McClure¹

View full text Add to dashboard Cite

A Novel 3D Joint MGRF Framework for Precise Lung Segmentation

Cited by 19 publications

References 8 publications

Automated Lung Segmentation from HRCT Scans with Diffuse Parenchymal Lung Diseases

Automated Lung Segmentation from HRCT Scans with Diffuse Parenchymal Lung Diseases

Segmentation of lung region based on using parallel implementation of joint MGRF: Validation on 3D realistic lung phantoms

A novel NMF-based DWI CAD framework for prostate cancer.

Contact Info

Product

Resources

About