4.7 Article

Fuzzy Object Skeletonization: Theory, Algorithms, and Applications

期刊

出版社

IEEE COMPUTER SOC
DOI: 10.1109/TVCG.2017.2738023

关键词

Skeletonization; fuzzy set; grassfire propagation; collision-impact; distance transform; digital topology and geometry

资金

  1. NIH [R01-AR054439]

向作者/读者索取更多资源

Skeletonization offers a compact representation of an object while preserving important topological and geometrical features. Literature on skeletonization of binary objects is quite mature. However, challenges involved with skeletonization of fuzzy objects are mostly unanswered. This paper presents a new theory and algorithm of skeletonization for fuzzy objects, evaluates its performance, and demonstrates its applications. A formulation of fuzzy grassfire propagation is introduced; its relationships with fuzzy distance functions, level sets, and geodesics are discussed; and several new theoretical results are presented in the continuous space. A notion of collision-impact of fire-fronts at skeletal points is introduced, and its role in filtering noisy skeletal points is demonstrated. A fuzzy object skeletonization algorithm is developed using new notions of surface-and curve-skeletal voxels, digital collision-impact, filtering of noisy skeletal voxels, and continuity of skeletal surfaces. A skeletal noise pruning algorithm is presented using branch-level significance. Accuracy and robustness of the new algorithm are examined on computer-generated phantoms and micro-and conventional CT imaging of trabecular bone specimens. An application of fuzzy object skeletonization to compute structure-width at a low image resolution is demonstrated, and its ability to predict bone strength is examined. Finally, the performance of the new fuzzy object skeletonization algorithm is compared with two binary object skeletonization methods.

作者

我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。

评论

主要评分

4.7
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

Article Computer Science, Interdisciplinary Applications

A CT-Based Automated Algorithm for Airway Segmentation Using Freeze-and-Grow Propagation and Deep Learning

Syed Ahmed Nadeem, Eric A. Hoffman, Jessica C. Sieren, Alejandro P. Comellas, Surya P. Bhatt, Igor Z. Barjaktarevic, Fereidoun Abtin, Punam K. Saha

Summary: This study introduces a novel approach for automated segmentation of pulmonary airway trees to explore COPD sub-phenotypes, assess disease progression, and intervention outcomes. Both CT intensity- and deep learning-based algorithms show high reproducibility and accuracy, with the deep learning-based FG algorithm being a promising option for large multi-site studies.

IEEE TRANSACTIONS ON MEDICAL IMAGING (2021)

Article Endocrinology & Metabolism

Bone and non-contractile soft tissue changes following open kinetic chain resistance training and testosterone treatment in spinal cord injury: an exploratory study

M. E. Holman, G. Chang, M. P. Ghatas, P. K. Saha, X. Zhang, M. R. Khan, A. P. Sima, R. A. Adler, A. S. Gorgey

Summary: The study showed that the combined intervention of TT + RT may help slow down bone loss following SCI over a longer period, suggesting it could be a valuable rehabilitation technique for individuals with spinal cord injury.

OSTEOPOROSIS INTERNATIONAL (2021)

Article Endocrinology & Metabolism

Effects of fluoride intake on cortical and trabecular bone microstructure at early adulthood using multi-row detector computed tomography (MDCT)

Punam K. Saha, Reem Reda Oweis, Xiaoliu Zhang, Elena Letuchy, Julie M. Eichenberger-Gilmore, Trudy L. Burns, John J. Warren, Kathleen F. Janz, James C. Torner, Linda G. Snetselaar, Steven M. Levy

Summary: This study aimed to investigate the effects of period-specific and cumulative fluoride intake on bone microstructural outcomes in early adulthood. The results showed that there were no significant associations between fluoride intake and bone microstructural outcomes at age 19, indicating weak or absent effects of fluoride intake on bone structures during early adulthood.
Article Critical Care Medicine

Longitudinal Association Between Muscle Loss and Mortality in Ever Smokers

Stefanie E. Mason, Rafael Moreta-Martinez, Wassim W. Labaki, Matthew J. Strand, Elizabeth A. Regan, Jessica Bon, Ruben San Jose Estepar, Richard Casaburi, Merry-Lynn McDonald, Harry B. Rossiter, Barry Make, Mark T. Dransfield, MeiLan K. Han, Kendra Young, Jeffrey L. Curtis, Kathleen Stringer, Greg Kinney, John E. Hokanson, Raul San Jose Estepar, George R. Washko

Summary: The longitudinal loss of fat-free mass (FFM) is associated with increased all-cause mortality, regardless of initial body composition metrics, including BMI or muscle mass. This finding may improve risk stratification and identify novel therapeutic targets for patients with chronic obstructive pulmonary disease.
Article Computer Science, Interdisciplinary Applications

3dSpAn: An interactive software for 3D segmentation and analysis of dendritic spines

Nirmal Das, Ewa Baczynska, Monika Bijata, Blazej Ruszczycki, Andre Zeug, Dariusz Plewczynski, Punam Kumar Saha, Evgeni Ponimaskin, Jakub Wlodarczyk, Subhadip Basu

Summary: Segmentation and analysis of dendritic spine morphology face challenges in individual spine segmentation and quantitative assessment of spine morphology. We developed 3dSpAn software based on the 3D multi-scale opening algorithm, with four modules for preprocessing, segmentation, and feature extraction. Results show usability across different observation methods, reproducibility, and accuracy, with the software freely available for non-commercial use.

NEUROINFORMATICS (2022)

Article Radiology, Nuclear Medicine & Medical Imaging

Finite element analysis of trabecular bone microstructure using CT imaging and continuum mechanical modeling

Indranil Guha, Xiaoliu Zhang, Chamith S. Rajapakse, Gregory Chang, Punam K. Saha

Summary: This study validates an application of voxel-based continuum finite element analysis (FEA) in predicting trabecular bone (Tb) modulus from clinical CT imaging. The results show that this method can accurately predict Tb modulus and has high repeatability.

MEDICAL PHYSICS (2022)

Correction Computer Science, Interdisciplinary Applications

3dSpAn: An interactive software for 3D segmentation and analysis of dendritic spines (Nov, 10.1007/s12021-021-09549-0, 2021)

Nirmal Das, Ewa Baczynska, Monika Bijata, Blazej Ruszczycki, Andre Zeug, Dariusz Plewczynski, Punam Kumar Saha, Evgeni Ponimaskin, Jakub Wlodarczyk, Subhadip Basu

NEUROINFORMATICS (2022)

Article Radiology, Nuclear Medicine & Medical Imaging

Airway Detection in COPD at Low-Dose CT Using Deep Learning and Multiparametric Freeze and Grow

Syed Ahmed Nadeem, Alejandro P. Comellas, Eric A. Hoffman, Punam K. Saha

Summary: The purpose of this study was to validate and present a fully automated airway detection method at low-dose CT in patients with chronic obstructive pulmonary disease (COPD). The study optimized deep learning (DL) and freeze-and-grow (FG) methods for automatic detection of airways. The results showed that the automated low-dose CT method outperformed the semi-automated method at standard-dose CT in terms of detecting airway phenotypes.

RADIOLOGY-CARDIOTHORACIC IMAGING (2022)

Proceedings Paper Computer Science, Interdisciplinary Applications

CT-Based Segmentation of Pectoral Muscle using Deep Learning and Association of Computed Metrics with Aging and Sex

Indra Narayan Dutta, Syed Ahmed Nadeem, Alejandro P. Comellas, Eric A. Hoffman, Punam K. Saha

Summary: Deterioration of the overall musculoskeletal system with aging is a universal phenomenon. In this study, a CT-based automated segmentation method using deep learning was developed to assess pectoral muscle health. The results showed that males had significantly greater pectoral muscle area than females, and muscle wasting increased with aging. CT-based automated segmentation methods are suitable for large population studies exploring broader scientific knowledge under various diseases.

MEDICAL IMAGING 2022: BIOMEDICAL APPLICATIONS IN MOLECULAR, STRUCTURAL, AND FUNCTIONAL IMAGING (2022)

Proceedings Paper Computer Science, Interdisciplinary Applications

Clinical CT-Based Assessment of Trabecular Bone Shear Modulus using Nonlinear Finite Element Modelling

Indranil Guha, Xiaoliu Zhang, Punam K. Saha

Summary: Nonlinear FEA method for computing trabecular bone shear modulus using clinical CT imaging was developed and validated. The method showed highly reproducible shear modulus values with high linear correlation to micro-CT-derived reference values. This approach broadens the scope of micro-mechanical analysis of trabecular bone network at relatively low in vivo resolution, without the need for binary segmentation of trabecular bone.

MEDICAL IMAGING 2022: BIOMEDICAL APPLICATIONS IN MOLECULAR, STRUCTURAL, AND FUNCTIONAL IMAGING (2022)

Proceedings Paper Computer Science, Interdisciplinary Applications

CT-based Segmentation of Thoracic Vertebrae using Deep Learning and Computation of the Kyphotic Angle

Syed Ahmed Nadeem, Alejandro P. Comellas, Indranil Guha, Elizabeth A. Regan, Eric A. Hoffman, Punam K. Saha

Summary: Spinal degeneration and vertebral fractures are common among the elderly and have significant impacts on various health indicators. This study presents an automated method for segmenting individual vertebrae and calculating the kyphotic angle of the spine from chest CT images. The method achieves high accuracy and consistency compared to manual segmentation and measurement.

MEDICAL IMAGING 2022: BIOMEDICAL APPLICATIONS IN MOLECULAR, STRUCTURAL, AND FUNCTIONAL IMAGING (2022)

Article Endocrinology & Metabolism

Computed Tomography-Based Stiffness Measures of Trabecular Bone Microstructure: Cadaveric Validation and In Vivo Application

Indranil Guha, Xialiou Zhang, Chamith S. Rajapakse, Elena M. Letuchy, Gregory Chang, Kathleen F. Janz, James C. Torner, Steven M. Levy, Punam K. Saha

Summary: This study presents a nonlinear finite element analysis method for distal tibia CT scans, which allows for assessment of trabecular bone microstructural stiffness without binary segmentation and accounts for bone microstructural distribution. The method provides an effective surrogate measure of trabecular bone microstructural stiffness and expands the scope for finite element analysis in low-resolution in vivo imaging.

JBMR PLUS (2022)

Proceedings Paper Engineering, Biomedical

Generalizability of a Deep Learning Airway Segmentation Algorithm to a Blinded Low-Dose CT Dataset

Syed Ahmed Nadeem, Alejandro P. Comellas, Eric A. Hoffman, Punam K. Saha

Summary: Chronic obstructive pulmonary disease (COPD) is a common inflammatory disease affecting over 300 million people worldwide, with CT being a standard tool for assessing airway and parenchymal physiology and function. Recently, deep learning methods have shown promise in medical image segmentation, but their generalizability remains a challenge in multi-center CT studies.

MEDICAL IMAGING 2021: IMAGE PROCESSING (2021)

Proceedings Paper Engineering, Biomedical

Anatomical Labeling of Human Airway Branches using a Novel Two-Step Machine Learning and Hierarchical Features

Syed Ahmed Nadeem, Eric A. Hoffman, Alejandro P. Comellas, Punam K. Saha

Summary: This paper presents an algorithm for anatomical labeling of human airway tree branches using a novel two-step machine learning and hierarchical features. The method achieved high labeling accuracies in different lung lobes and for clinically significant segmental branches, providing a standardized spatial referencing of airway phenotypes in large population-based studies.

MEDICAL IMAGING 2020: IMAGE PROCESSING (2021)

Proceedings Paper Engineering, Biomedical

CT-Based Characterization of Transverse and Longitudinal Trabeculae and Its Applications

Xiaoliu Zhang, Elena M. Letuchy, Steven M. Levy, James C. Torner, Punam K. Saha

Summary: Osteoporosis is a common age-related disease characterized by reduced bone mineral density and micro-structural deterioration, with bone micro-structural properties playing a significant role in determining bone strength and fracture-risk. A new clinical CT method for characterizing transverse and longitudinal trabeculae was introduced and validated in human studies, revealing associations with gender and body size. Results showed reproducibility of trabecular measures and significant differences between males and females in trabecular bone values, with correlations to body weight and height varying between genders.

MEDICAL IMAGING 2020: BIOMEDICAL APPLICATIONS IN MOLECULAR, STRUCTURAL, AND FUNCTIONAL IMAGING (2021)

暂无数据