Automated segmentation of micro-CT images of bone formation in calcium phosphate scaffolds

Polak, Samantha J.; Candido, Salvatore; Levengood, Sheeny K. Lan; Johnson, Amy J. Wagoner

doi:10.1016/j.compmedimag.2011.07.004

Cited by 19 publications

(18 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The excellent bone contrast can be used to investigate bone-related questions, for example, bone formation (in conjunction with automated image segmentation methods [25]) and tumor-induced bone destruction [26]. To our knowledge, these techniques had not yet been applied to the in ovo quantification of bone growth of live chick embryos.…”

Section: Discussionmentioning

confidence: 99%

Automated Segmentation and Object Classification of CT Images: Application toIn VivoMolecular Imaging of Avian Embryos

Heidrich

Schmidt

Zimmermann³

et al. 2013

International Journal of Biomedical Imaging

View full text Add to dashboard Cite

Background. Although chick embryogenesis has been studied extensively, there has been growing interest in the investigation of skeletogenesis. In addition to improved poultry health and minimized economic loss, a greater understanding of skeletal abnormalities can also have implications for human medicine. True in vivo studies require noninvasive imaging techniques such as high-resolution microCT. However, the manual analysis of acquired images is both time consuming and subjective. Methods. We have developed a system for automated image segmentation that entails object-based image analysis followed by the classification of the extracted image objects. For image segmentation, a rule set was developed using Definiens image analysis software. The classification engine was implemented using the WEKA machine learning tool. Results. Our system reduces analysis time and observer bias while maintaining high accuracy. Applying the system to the quantification of long bone growth has allowed us to present the first true in ovo data for bone length growth recorded in the same chick embryos. Conclusions. The procedures developed represent an innovative approach for the automated segmentation, classification, quantification, and visualization of microCT images. MicroCT offers the possibility of performing longitudinal studies and thereby provides unique insights into the morpho- and embryogenesis of live chick embryos.

show abstract

Section: Discussionmentioning

confidence: 99%

Automated Segmentation and Object Classification of CT Images: Application toIn VivoMolecular Imaging of Avian Embryos

Heidrich

Schmidt

Zimmermann³

et al. 2013

International Journal of Biomedical Imaging

View full text Add to dashboard Cite

show abstract

“…Knowledge about bone tissue state can help to understand the processes which happen in it, as traditionally, analysis of the biological data is manual and the quality of the analysis depends on a specialist's experience [1][2][3][4][5][6][7]. In general, automatization of such analysis is complicated because of random input data [8][9][10][11][12]. The following approaches to image processing can be distinguished: the elimination of necessary elements by various filters, image segmentation, and analysis of elements.…”

Section: Introductionmentioning

confidence: 99%

Automation of Bone Tissue Histology

et al. 2019

View full text Add to dashboard Cite

In abstract methods of automation of histology, bone structure is considered. Possible inputs are snapshots from a microscope or computed tomography slices. An algorithm is proposed that differentiates objects according to their color (or grayscale) and recover morphology topology. An algorithm to separate morphological objects by their dimensions and color parameters was built. Measured parameters were bone surface, bone area, porosity, cortical thickness, canal number, canal area, and etc. Additionally, we measured the anisotropy properties of the bone tissue: distribution of porosity direction and degree of porosity elongation. A bone example was scanned by computed tomography. All data were measured by the proposed method and the results presented. An example algorithm of work on computed tomography data is shown in this work.

show abstract

“…• Analyzing avascular necrosis [1,2] • Detecting microscopic bone features (e.g., osteons and Haversian canals) [3,4] • Separating bone calcium phosphate (an important ingredient of bone scaffolds) and soft tissue [5] • Segmenting the vertebra using the volume data [6] • Distinguishing normal cells from abnormal cells on the basis of shape definition [7] Abstract In cortical bone, solid (lamellar and interstitial) matrix occupies space left over by porous microfeatures such as Haversian canals, lacunae, and canaliculi-containing clusters. In this work, pulse-coupled neural networks (PCNN) were used to automatically distinguish the microfeatures present in histology slides of cortical bone.…”

Section: Introductionmentioning

confidence: 99%

Geometric-attributes-based segmentation of cortical bone slides using optimized neural networks

Hage

Hamade

2015

J Bone Miner Metab

View full text Add to dashboard Cite

In cortical bone, solid (lamellar and interstitial) matrix occupies space left over by porous microfeatures such as Haversian canals, lacunae, and canaliculi-containing clusters. In this work, pulse-coupled neural networks (PCNN) were used to automatically distinguish the microfeatures present in histology slides of cortical bone. The networks' parameters were optimized using particle swarm optimization (PSO). When forming the fitness functions for the PSO, we considered the microfeatures' geometric attributes-namely, their size (based on measures of elliptical perimeter or area), shape (based on measures of compactness or the ratio of minor axis length to major axis length), and a two-way combination of these two geometric attributes. This hybrid PCNN-PSO method was further enhanced for pulse evaluation by combination with yet another method, adaptive threshold (AT), where the PCNN algorithm is repeated until the best threshold is found corresponding to the maximum variance between two segmented regions. Together, this framework of using PCNN-PSO-AT constitutes, we believe, a novel framework in biomedical imaging. Using this framework and extracting microfeatures from only one training image, we successfully extracted microfeatures from other test images. The high fidelity of all resultant segments was established using quantitative metrics such as precision, specificity, and Dice indices.

show abstract

Automated segmentation of micro-CT images of bone formation in calcium phosphate scaffolds

Cited by 19 publications

References 34 publications

Automated Segmentation and Object Classification of CT Images: Application toIn VivoMolecular Imaging of Avian Embryos

Automated Segmentation and Object Classification of CT Images: Application toIn VivoMolecular Imaging of Avian Embryos

Automation of Bone Tissue Histology

Geometric-attributes-based segmentation of cortical bone slides using optimized neural networks

Contact Info

Product

Resources

About