SVM-Based Cancer Grading from Histopathological Images Using Morphological and Topological Features of Glands and Nuclei

Stoean, Cătălin; Stoean, Ruxandra; Săndiță, Adrian; Ciobanu, Daniela; Meşină, Cristian; Gruia, Corina Lavinia

doi:10.1007/978-3-319-39345-2_13

Cited by 17 publications

(24 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Zeiss MIRAX MIDI was used to capture the images from H&E-stained colon tissues. (4) Data set D: This data set provided by Stoean et al [26] consists of images captured from H&E-stained colon tissue slides obtained by the Emergency County Hospital of Craiova, Romania.…”

Section: Methodsmentioning

confidence: 99%

“…They prepared the data set providing the ground truth labels. (3) Data set C : The GlaS data set [28] consists of images collected by a team of pathologists at the University Hospitals Coventry and Warwickshire, UK. Zeiss MIRAX MIDI was used to capture the images from H&E‐stained colon tissues. (4) Data set D : This data set provided by Stoean et al [26] consists of images captured from H&E‐stained colon tissue slides obtained by the Emergency County Hospital of Craiova, Romania.…”

Section: Methodsmentioning

confidence: 99%

“…Various types of feature sets have been proposed in earlier literature towards this, such as grey‐scale co‐occurrence matrices [19], local binary patterns [20, 21], and wavelet packet transform [22, 23]. Many modern algorithms, such as the k‐nearest neighbour [4], fuzzy logic [7], neural networks [24], regression [25], and support vector machines (SVMs) [26], have shown a high degree of efficiency for the task of colon histology segmentation and classification. The defined feature space was studied using a Bayesian classifier, characterising fibroblast, and inflammatory cells by identifying the healthy state cells with an accuracy of 97.20% [27].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Colon cancer prediction using 2DReCA segmentation and hybrid features on histopathology images

2020

View full text Add to dashboard Cite

Since histopathological images exist in various forms, performing segmentation on these images is tedious. While in cancer-free colon tissue, epithelial cells generally have an elliptical shape; their structure alters in a malignant tissue. This study proposes a technique consisting of colon biopsy image segmentation and a hybrid set of features for classification, and is evaluated on multiple databases with various levels of magnifications. This study presents a novel image segmentation method with multi-level thresholding based on Rényi's two-dimensional entropy with a cultural algorithm (2DR e CA). Based on the entropy, elliptical epithelial cells, being the region of interest, are identified from the segmented background. After successful segmentation, shape descriptors are extracted with morphological operations. Two sets of texture features (grey-level cooccurrence matrix and block-wise elliptical local binary pattern) are calculated based on pre-processed grey-scale colon images. The proposed hybrid feature vector set, then concatenates the extracted features for training and testing with a random forest classifier. The proposed segmentation and classification model is evaluated by considering four data sets consisting of various colon images at different magnifications. In addition, it is evaluated by multiple performance measures and compared with existing techniques.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Colon cancer prediction using 2DReCA segmentation and hybrid features on histopathology images

2020

View full text Add to dashboard Cite

show abstract

“…Based on the name of the project that put forward the data, it will be further referred in the article as the IMEDIATREAT data set. It was initially introduced in [13] and is available for download [14].…”

Section: Methodsmentioning

confidence: 99%

Cancer diagnosis through a tandem of classifiers for digitized histopathological slides

Lichtblau

Stoean

2019

PLoS ONE

Self Cite

View full text Add to dashboard Cite

The current research study is concerned with the automated differentiation between histopathological slides from colon tissues with respect to four classes (healthy tissue and cancerous of grades 1, 2 or 3) through an optimized ensemble of predictors. Six distinct classifiers with prediction accuracies ranging from 87% to 95% are considered for the task. The proposed method of combining them takes into account the probabilities of the individual classifiers for each sample to be assigned to any of the four classes, optimizes weights for each technique by differential evolution and attains an accuracy that is significantly better than the individual results. Moreover, a degree of confidence is defined that would allow the pathologists to separate the data into two distinct sets, one that is correctly classified with a high level of confidence and the rest that would need their further attention. The tandem is also validated on other benchmark data sets. The proposed methodology proves to be efficient in improving the classification accuracy of each algorithm taken separately and performs reasonably well on other data sets, even with default weights. In addition, by establishing a degree of confidence the method becomes more viable for use by actual practitioners.

show abstract

“…Toll-like receptors are part of PRRs (pattern recognition receptors). PRRSs are a group of receptors, including Toll-like receptors, nucleotidebinding oligomerization domain leucine-rich repeat proteins, peptidoglycan recognition proteins, caspase recruitment domain-helicase proteins, manose-binding lectins (MBLs) [23][24][25][26][27][28] .…”

Section: Proinflammatory Cytokines In Chronic B-hepatitismentioning

confidence: 99%

Raspunsul gazdei la hepatita cronica virala B

Cringus¹,

Petrescu²,

Calborean³

et al. 2019

Rev. Chim.

Self Cite

View full text Add to dashboard Cite

This review discusses and tries to demonstrate the importance of proinflammatory and antiinflammatory cytokines in HBV infection. Hepatitis B virus is a virus that is both hepatotropic and non-cytopathic. It causes the development of liver diseases which could progress into both acute and chronic versions. The virus is very widespread and results in the death of quite a number of people each year. The outcome of the viral infection is a result of immunologically mediated event. This means that the outcome is determined by the response of the immune system of the host. The infection can lead to several different liver diseases as well as fibrosis and cirrhosis. When an infection occurs, there is an attempt by the body to fight it via the use of several mechanisms. One of these is the use of cytokines (which are proteins). There exist different kinds of cytokines of which interleukin-10 and interferon gamma are very important. Interleukin-10 is an anti-inflammatory cytokine which inhibits the effector mechanism of Th1 cytokines. It performs hepatoprotective and anti-inflammatory functions and also upregulates Th2 cytokines. The function and relevance of this cytokine in the pathogenesis of liver diseases cannot be underemphasized. Interferon gamma, on the other hand, is a pro-inflammatory cytokine which seeks to eliminate and expunge the virus from the liver upon infection. It does this by congregating at the site of infection which subsequently results in inflammation and eventually liver fibrosis. This effect could be reversed by administering another type of interferon; interferon alpha.

show abstract

SVM-Based Cancer Grading from Histopathological Images Using Morphological and Topological Features of Glands and Nuclei

Cited by 17 publications

References 12 publications

Colon cancer prediction using 2DReCA segmentation and hybrid features on histopathology images

Colon cancer prediction using 2DReCA segmentation and hybrid features on histopathology images

Cancer diagnosis through a tandem of classifiers for digitized histopathological slides

Raspunsul gazdei la hepatita cronica virala B

Contact Info

Product

Resources

About