Performance evaluation of an automatic MGRF-based lung segmentation approach

Soliman, Ahmed; Khalifa, Fahmi; Alansary, Amir; Gimel’farb, Georgy; El-Baz, Ayman

doi:10.1063/1.4825026

Cited by 11 publications

(6 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Four metrics of evaluation were used for evaluating accuracy and robustness of the proposed approach, 32 and comparing it with the ground truth and other approaches. [33][34][35] These metrics are listed below:…”

Section: C Evaluation Of Resultsmentioning

confidence: 99%

A novel 3D segmentation approach for extracting retinal layers from optical coherence tomography images

Sleman¹,

Soliman²,

Elsharkawy³

et al. 2021

Medical Physics

Self Cite

View full text Add to dashboard Cite

Accurate segmentation of retinal layers of the eye in 3D Optical Coherence Tomography (OCT) data provides relevant information for clinical diagnosis. This manuscript describes a 3D segmentation approach that uses an adaptive patient-specific retinal atlas, as well as an appearance model for 3D OCT data. Methods: To reconstruct the atlas of 3D retinal scan, the central area of the macula (macula midarea) where the fovea could be clearly identified, was segmented initially. Markov Gibbs Random Field (MGRF) including intensity, spatial information, and shape of 12 retinal layers were used to segment the selected area of retinal fovea. A set of coregistered OCT scans that were gathered from 200 different individuals were used to build a 2D shape prior. This shape prior was adapted subsequently to the first order appearance and second order spatial interaction MGRF model. After segmenting the center of the macula "foveal area", the labels and appearances of the layers that were segmented were utilized to segment the adjacent slices. The final step was repeated recursively until a 3D OCT scan of the patient was segmented. Results: This approach was tested in 50 patients with normal and with ocular pathological conditions. The segmentation was compared to a manually segmented ground truth. The results were verified by clinical retinal experts. Dice Similarity Coefficient (DSC), 95% bidirectional modified Hausdorff Distance (HD), Unsigned Mean Surface Position Error (MSPE), and Average Volume Difference (AVD) metrics were used to quantify the performance of the proposed approach. The proposed approach was proved to be more accurate than the current state-of-the-art 3D OCT approaches. Conclusions: The proposed approach has the advantage of segmenting all the 12 retinal layers rapidly and more accurately than current state-of-the-art 3D OCT approaches.

show abstract

Section: C Evaluation Of Resultsmentioning

confidence: 99%

A novel 3D segmentation approach for extracting retinal layers from optical coherence tomography images

Sleman¹,

Soliman²,

Elsharkawy³

et al. 2021

Medical Physics

Self Cite

View full text Add to dashboard Cite

show abstract

“…The TP represents the number of positively labeled voxels that are correct; the FP is the number of labeled voxels that are classified positively while it is incorrect; the TN is the number of negatively labeled voxels that are correct; and the FN is the number of negatively labeled voxels that are incorrect. The DC value is calculated using all these values as follow [39]:…”

Section: ) Dice Coefficient (Dc)mentioning

confidence: 99%

“…To measure the distance error between the borders of G and S, we used the bidirectional Hausdorff distance (BHD). The HD from the boarder points of G to the boarder points of S is defined as the maximum distance from the border of G to the nearest point on the border of S [39], [40]:…”

Section: ) Bidirectional Hausdorff Distance (Bhd)mentioning

confidence: 99%

Accurate Segmentation of Cerebrovasculature From TOF-MRA Images Using Appearance Descriptors

et al. 2020

Self Cite

View full text Add to dashboard Cite

Analyzing cerebrovascular changes can significantly lead to not only detecting the presence of serious diseases e.g., hypertension and dementia, but also tracking their progress. Such analysis could be better performed using Time-of-Flight Magnetic Resonance Angiography (ToF-MRA) images, but this requires accurate segmentation of the cerebral vasculature from the surroundings. To achieve this goal, we propose a fully automated cerebral vasculature segmentation approach based on extracting both prior and current appearance features that have the ability to capture the appearance of macro and micro-vessels in ToF-MRA. The appearance prior is modeled with a novel translation and rotation invariant Markov-Gibbs Random Field (MGRF) of voxel intensities with pairwise interaction analytically identified from a set of training data sets. The appearance of the cerebral vasculature is also represented with a marginal probability distribution of voxel intensities by using a Linear Combination of Discrete Gaussians (LCDG) that its parameters are estimated by using a modified Expectation-Maximization (EM) algorithm. The extracted appearance features are separable and can be classified by any classifier, as demonstrated by our segmentation results. To validate the accuracy of our algorithm, we tested the proposed approach on invivo data using 270 data sets, which were qualitatively validated by a neuroradiology expert. The results were quantitatively validated using the three commonly used metrics for segmentation evaluation: the Dice coefficient, the modified Hausdorff distance, and the absolute volume difference. The proposed approach showed a higher accuracy compared to two of the existing segmentation approaches.

show abstract

“…Imaging [384], the International Symposium on Computational Models for Life Sciences (CMLS) [385], the International Symposium on Biomedical Imaging (ISBI) [386], and the International Conference on Image Processing (ICIP) [387,388].…”

Section: E Summary and Discussionmentioning

confidence: 99%

Computational methods for the analysis of functional 4D-CT chest images.

Soliman¹

Self Cite

View full text Add to dashboard Cite

DEDICATIONThis dissertation is dedicated to my father's soul.iii ACKNOWLEDGMENTS In the name of Allah the most merciful, the most compassionate. All deepest thanks are due to Almighty Allah for the uncountable gifts given to me. Medical imaging is an important emerging technology that has been intensively used in the last few decades for disease diagnosis and monitoring as well as for the assessment of treatment effectiveness. Medical images provide a very large amount of valuable information that is too huge to be exploited by radiologists and physicians. Therefore, the design of computer-aided diagnostic (CAD) system, which can be used as an assistive tool for the medical community, is of a great importance. This dissertation deals with the development of a complete CAD system for lung cancer patients, which remains the leading cause of cancer-related death in the USA. In 2014, there were approximately 224,210 new cases of lung cancer and 159,260 related deaths. The process begins with the detection of lung cancer which is detected through the diagnosis of lung nodules (a manifestation of lung cancer). These nodules are approximately spherical regions of primarily high density tissue that are visible in computed tomography (CT) images of the lung. The treatment of these lung cancer nodules is complex, nearly 70% of lung cancer patients require radiation therapy as part of their treatment. Radiation-induced lung injury is a limiting toxicity that may decrease cure rates and increase morbidity and mortality treatment. By finding ways to accurately detect, at early stage, and hence prevent lung injury, it will have significant positive consequences for lung cancer patients.v The ultimate goal of this dissertation is to develop a clinically usable CAD system that can improve the sensitivity and specificity of early detection of radiation-induced lung injury based on the hypotheses that radiated lung tissues may get affected and suffer decrease of their functionality as a side effect of radiation therapy treatment. These hypotheses have been validated by demonstrating that automatic segmentation of the lung regions and registration of consecutive respiratory phases to estimate their elasticity, ventilation, and texture features to provide discriminatory descriptors that can be used for early detection of radiation-induced lung injury. The proposed methodologies will lead to novel indexes for distinguishing normal/healthy and injured lung tissues in clinical decisionmaking. To achieve this goal, a CAD system for accurate detection of radiation-induced lung injury that requires three basic components has been developed. These components are the lung fields segmentation, lung registration, and features extraction and tissue classification.This dissertation starts with an exploration of the available medical imaging modalities to present the importance of medical imaging in today's clinical applications. Secondly, the methodologies, challenges, and limitations of recent CAD systems for lung cancer detection are covered...

show abstract

Performance evaluation of an automatic MGRF-based lung segmentation approach

Cited by 11 publications

References 35 publications

A novel 3D segmentation approach for extracting retinal layers from optical coherence tomography images

A novel 3D segmentation approach for extracting retinal layers from optical coherence tomography images

Accurate Segmentation of Cerebrovasculature From TOF-MRA Images Using Appearance Descriptors

Computational methods for the analysis of functional 4D-CT chest images.

Contact Info

Product

Resources

About