A survey of thresholding techniques

Sahoo, Prasanna K.; Soltani, Soheil; Wong, Alexander

doi:10.1016/0734-189x(88)90022-9

Cited by 2,227 publications

(740 citation statements)

References 33 publications

Supporting

Mentioning

681

Contrasting

Unclassified

Order By: Relevance

“…Several thresholding methods were applied to each image, including maximum entropy, 22 moment-preserving method, 22 Otsu's method, 22 the method of Ridler and Calvard, 23 the method of Reddi et al, 24 and a method based upon the spatial gray-level dependence (SGLD) matrix. 22 The best result among the above was selected for each image by one of the radiologists involved in the study. Figure 3 shows two examples of binarized breast regions with different shapes.…”

Section: Preprocessing Of Imagesmentioning

confidence: 99%

“…The fibroglandular disc was segmented by using the following thresholding methods: maximum entropy, 22 moment-preserving method, 22 and Otsu's method. 22 The best result among the above was selected for each image by one of the radiologists involved in the study.…”

Section: Preprocessing Of Imagesmentioning

confidence: 99%

“…22 The best result among the above was selected for each image by one of the radiologists involved in the study.…”

Section: Preprocessing Of Imagesmentioning

confidence: 99%

“…21 The Top-Hat morphological filter was applied to the mammogram to enhance lobular and ductal structures. The location of the maximum intensity in the Radon transform of the result was used to detect the nipple.The fibroglandular disc was segmented by using the following thresholding methods: maximum entropy, 22 moment-preserving method, 22 and Otsu's method. 22 The best result among the above was selected for each image by one of the radiologists involved in the study.…”

mentioning

confidence: 99%

See 3 more Smart Citations

Content-based Retrieval of Mammograms Using Visual Features Related to Breast Density Patterns

et al. 2007

View full text Add to dashboard Cite

This paper describes part of content-based image retrieval (CBIR) system that has been developed for mammograms. Details are presented of methods implemented to derive measures of similarity based upon structural characteristics and distributions of density of the fibroglandular tissue, as well as the anatomical size and shape of the breast region as seen on the mammogram. Wellknown features related to shape, size, and texture (statistics of the gray-level histogram, Haralick's texture features, and moment-based features) were applied, as well as less-explored features based in the Radon domain and granulometric measures. The Kohonen self-organizing map (SOM) neural network was used to perform the retrieval operation. Performance evaluation was done using precision and recall curves obtained from comparison between the query and retrieved images. The proposed methodology was tested with 1,080 mammograms, including craniocaudal and mediolateral-oblique views. Precision rates obtained are in the range from 79% to 83% considering the total image set. Considering the first 50% of the retrieved mages, the precision rates are in the range from 78% to 83%; the rates are in the range from 79% to 86% considering the first 25% of the retrieved images. Results obtained indicate the potential of the implemented methodology to serve as a part of a CBIR system for mammography.KEY WORDS: Mammography, contend-based image retrieval, Kohonen self-organizing map, texture features, granulometric measures, radon transform domain, breast density INTRODUCTION: BREAST CANCER AND MAMMOGRAPHYB reast density has been shown to be a risk factor in the development of breast cancer. Wolfe 1 presented the first study relating the density and structure of breast tissues as seen on mammograms to the characteristics of breast disease: he described and illustrated cases associating patterns of parenchymal distortion with the risk of development of breast cancer. Since then, several other researchers have studied the relation between the structural composition of breast tissue and the abnormalities found in the related regions. 2 A consequence of the understanding of this relationship has been the development of systems for the description and analysis of the density patterns found in mammograms: the Breast Imaging Reporting and Data System (BI-RADS), 3 developed by the American College of Radiology, is the most important of such systems. BI-RADS contains recommendations for standardization of terms used in image-based diagnosis of breast diseases, the division of breast composition and mammographic findings into categories, and suggestions for further actions by the radiologist. Visual analysis of mammograms takes into consideration the shape and size of the breast, the conditions of the breast contour and the nipple position, and the distribution of fibroglandular tissue (degree of granularity, amount, and distribution of breast density). Notwithstanding the developments mentioned above, visual analysis of mammograms by radiologists remains sub...

show abstract

Section: Preprocessing Of Imagesmentioning

confidence: 99%

Section: Preprocessing Of Imagesmentioning

confidence: 99%

“…22 The best result among the above was selected for each image by one of the radiologists involved in the study.…”

Section: Preprocessing Of Imagesmentioning

confidence: 99%

mentioning

confidence: 99%

See 2 more Smart Citations

Content-based Retrieval of Mammograms Using Visual Features Related to Breast Density Patterns

et al. 2007

View full text Add to dashboard Cite

show abstract

“…A variety of auto-threshold methods have been conceived (Sahoo et al 1988;Glasbey 1993), and we have found Huang's algorithm (Huang and Wang 1995), which minimizes image fuzziness (the difference between the original image and its binary version), to work particularly well for both object types. However, an inherent caveat of auto-threshold methods is that they adjust the cut-off values based on the intensity distribution within the image.…”

mentioning

confidence: 99%

Integrated High-Content Quantification of Intracellular ROS Levels and Mitochondrial Morphofunction

Sieprath

Corne

Willems

et al. 2016

Advances in Anatomy, Embryology and Cell Biology

View full text Add to dashboard Cite

Oxidative stress arises from an imbalance between the production of reactive oxygen species (ROS) and their removal by cellular antioxidant systems. Especially under pathological conditions, mitochondria constitute a relevant source of cellular ROS. These organelles harbor the electron transport chain, bringing electrons in close vicinity to molecular oxygen. Although a full understanding is still lacking, intracellular ROS generation and mitochondrial function are also linked to changes in mitochondrial morphology. To study the intricate relationships between the different factors that govern cellular redox balance in living cells, we have developed a high-content microscopy-based strategy for simultaneous quantification of intracellular ROS levels and mitochondrial morphofunction. Here, we summarize the principles of intracellular ROS generation and removal, and we explain the major considerations for performing quantitative microscopy analyses of ROS and mitochondrial morphofunction in living cells. Next, we describe our workflow and finally, we illustrate that a multiparametric readout enables the unambiguous classification of chemically perturbed cells as well as laminopathy patient cells. Principles of intracellular ROS generation and removalReactive oxygen species (ROS) are small, short-lived derivatives of molecular oxygen (O 2 ) of radical and non-radical nature (Halliwell and Gutteridge 2007 • ), nitrate radical (NO 3 • ) and many other nitrogen derivatives. ROS were originally described as molecular constituents of the defense system of phagocytic cells, but it has become clear that besides their damaging properties, they also function as signaling molecules and mediate a variety of other cellular responses including cell proliferation, differentiation, gene expression and migration (Lambeth 2004;Bartz and Piantadosi 2010). Intracellular ROS metabolismROS can be generated at various sites in the cell (Fig. 1A). This can be either deliberately, e.g. by NADPH oxidases (NOX), or as a byproduct, e.g. during normal cellular respiration in mitochondria (Babior 1999;Turrens 2003;Murphy 2009). The NOX family of NADPH oxidases (NOX1, NOX2, NOX3, NOX4, NOX5, DUOX1 and DUOX2) are proteins that transport electrons (e -) from NADPH across biological membranes (plasma or endomembranes) (Bedard and Krause 2007;Dupre-Crochet et al. 2013). The activation mechanisms and tissue distribution of the isoforms differ but they all use O 2 as e --acceptor, producing O 2•-. Through ROS generation, they play a role in many cellular processes including host defense, regulation of gene expression and cell differentiation (Bedard and Krause 2007). Despite their sometimes significant contribution to the global ROS pools, NOX are not the predominant source of intracellular ROS. Mitochondria are considered the major culprit, in particular under pathological conditions. Mitochondrial ROS are generated as a byproduct of the oxidative phosphorylation (OXPHOS, cf. below). Irrespective of its source, ROS production generally sta...

show abstract

Efficient cell segmentation tool for confocal microscopy tissue images and quantitative evaluation of FISH signals

Adiga

Chaudhuri

1999

Microsc. Res. Tech.

View full text Add to dashboard Cite

A survey of thresholding techniques

Cited by 2,227 publications

References 33 publications

Content-based Retrieval of Mammograms Using Visual Features Related to Breast Density Patterns

Content-based Retrieval of Mammograms Using Visual Features Related to Breast Density Patterns

Integrated High-Content Quantification of Intracellular ROS Levels and Mitochondrial Morphofunction

Efficient cell segmentation tool for confocal microscopy tissue images and quantitative evaluation of FISH signals

Contact Info

Product

Resources

About