Evaluation of Plant Histology by Automatic Clustering Based on Individual Cell Morphological Features

Guillemin, Florence; Devaux, Marie-Françoise; Guillon, Fabienne

doi:10.5566/ias.v23.p13-22

Cited by 25 publications

(14 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A k -means clustering approach was chosen as a suitable unsupervised algorithm capable of accommodating the variations in staining across the nodule datasets 4,5,7. The k -means clustering algorithm attempts to optimally partitioned data into a set number of natural groups, k 5.…”

Section: Methodsmentioning

confidence: 99%

An Automated Segmentation Approach for Highlighting the Histological Complexity of Human Lung Cancer

et al. 2010

View full text Add to dashboard Cite

Lung cancer nodules, particularly adenocarcinoma, contain a complex intermixing of cellular tissue types: incorporating cancer cells, fibroblastic stromal tissue, and inactive fibrosis. Quantitative proportions and distributions of the various tissue types may be insightful for understanding lung cancer growth, classification, and prognostic factors. However, current methods of histological assessment are qualitative and provide limited opportunity to systematically evaluate the relevance of lung nodule cellular heterogeneity. In this study we present both a manual and an automatic method for segmentation of tissue types in histological sections of resected human lung cancer nodules. A specialized staining approach incorporating immunohistochemistry with a modified Masson's Trichrome counterstain was employed to maximize color contrast in the tissue samples for automated segmentation. The developed, clustering-based, fully automated segmentation approach segments complete lung nodule crosssectional histology slides in less than 1 min, compared to manual segmentation which requires multiple hours to complete. We found the accuracy of the automated approach to be comparable to that of the manual segmentation with the added advantages of improved time efficiency, removal of susceptibility to human error, and 100% repeatability.

show abstract

Section: Methodsmentioning

confidence: 99%

An Automated Segmentation Approach for Highlighting the Histological Complexity of Human Lung Cancer

et al. 2010

View full text Add to dashboard Cite

show abstract

“…Confocal laser-scanning microscopy (CLSM) enables non destructive optical sectioning of samples and make sample preparation easier and more rapid (Gray, Kolesik, Hoj, & Coombe, 1999;Kalab, Allan-Wojtas, & Miller, 1995). The observation of a representative number of cells requires the acquisition of a large number of images or several adjacent images and the reconstruction of the whole region as a mosaic image (Guillemin, Devaux, & Guillon, 2004). An alternative technique to microscopy is to use stereomicroscope or macrovision systems making it possible to observe a field of view of about 1 cm 2 .…”

Section: Introductionmentioning

confidence: 99%

Changes in texture, cellular structure and cell wall composition in apple tissue as a result of freezing

Chassagne-Berces

Poirier

Devaux

et al. 2009

Food Research International

Self Cite

148

View full text Add to dashboard Cite

“…The approach involved segmentation of individual cells, extraction of their anatomical and morphological features and broad classification of the cells into different tissue types using mathematical techniques. The plant cells were classified using clustering approach [1], discriminant analysis [2] and Markov Random Field approach [3]. Consideration of neighboring cells information was reported to influence the cell classification.…”

Section: Introductionmentioning

confidence: 99%

A boundary expansion method for analysis of cell neighborhoods and identification of cells in plant cross sectional images

Sarma¹

2013

2013 International Conference on Advanced Electronic Systems (ICAES)

View full text Add to dashboard Cite

Microscopic inspection of plant cross sections is widely used for identification of plants and assessing their suitability for specific applications. The inspection involves identification and evaluation of different types of tissues, cells, specialized cells and cell inclusions in plant cross section. The present paper describes a boundary expansion method based on image analysis and distance transform techniques suitable for detailed analysis of neighborhood of individual cells in plant cross sectional images. The proposed method involves expanding the boundary of a selected cell, analyzing the encroachment of the expanding boundary on the neighboring cells and determining the properties of the cell neighborhood and the neighboring cells relative to the boundary of the selected cell. The proposed method allows determination of identity and number of neighboring cells, spacings with neighboring cells and dimensions of neighboring cells parallel and perpendicular to the selected cell boundary. The method is useful for identification of certain types of plant cells exhibiting distinguishable properties of their neighbourhood and neighboring cells relative to the cell boundary. The usefulness of the proposed method is demonstrated for identification of xylem cells and mucilage ducts in plant cross sectional images.

show abstract

Evaluation of Plant Histology by Automatic Clustering Based on Individual Cell Morphological Features

Cited by 25 publications

References 18 publications

An Automated Segmentation Approach for Highlighting the Histological Complexity of Human Lung Cancer

An Automated Segmentation Approach for Highlighting the Histological Complexity of Human Lung Cancer

Changes in texture, cellular structure and cell wall composition in apple tissue as a result of freezing

A boundary expansion method for analysis of cell neighborhoods and identification of cells in plant cross sectional images

Contact Info

Product

Resources

About