Texture analysis of computed tomography images of acute ischemic stroke patients

Oliveira, Márcia Silva de; Fernándes, Paula Teíxeira; Avelar, Wagner Mauad; Santos, Sergio L.M.; Castellano, Gabriela; Li, L.M.

doi:10.1590/s0100-879x2009005000034

Cited by 34 publications

(33 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Each of the specified regions was classified as hypoattenuation or normality by linear discriminate analysis of z-score maps [13]. Oliveira et al proved the differences between the texture parameters of control and patients' tissues [21]. Similar suggestion was given by Ostrek et al presenting substantial efficiency of numerical hypodense tissue recognition [22].…”

Section: Computerized Processing Of Imaged Hypodense Tissuementioning

confidence: 83%

Recovery of CT stroke hypodensity – An adaptive variational approach

Przelaskowski

2015

Computerized Medical Imaging and Graphics

View full text Add to dashboard Cite

Section: Computerized Processing Of Imaged Hypodense Tissuementioning

confidence: 83%

Recovery of CT stroke hypodensity – An adaptive variational approach

Przelaskowski

2015

Computerized Medical Imaging and Graphics

View full text Add to dashboard Cite

“…The human quest for finding the image textural features dates back to 1970's when Haralick [1], Rosenfeld and Troy [2] have obtained textural coarseness of digital images by finding the difference of the gray values of the adjacent pixels and then performing autocorrelation of the image values. The texture based properties of digital images have also been used in medical images [3] and in tomography based images [4], analysis of ultrasound images [5] and classification of food items like Italian pasta and plum cakes [6,7].…”

Section: Introductionmentioning

confidence: 99%

An Approach to Improve Classification Accuracy of Leaf Images using Dorsal and Ventral Features

Kumar¹,

Patidar²,

Khazanachi³

et al. 2015

ijacsa

View full text Add to dashboard Cite

Abstract-This paper proposes to improve the classification accuracy of the leaf images by extracting texture and statistical features by utilizing the presence of striking features on the dorsal and ventral sides of the leaves, which on other types of objects may not be that prominent. The texture features have been extracted from dorsal, ventral and a combination of dorsalventral sides of leaf images using Gray level co-occurrence matrix. In addition to this, this work also uses certain general statistical features for discriminating them into various classes. The feature selection work has been performed separately for the dorsal, ventral and combined data sets (for both texture and statistical features) using the most common feature selection algorithms.After selecting the relevant features, the classification has been done using the classification algorithms: K-Nearest Neighbor, J48, Naïve Bayes, Partial Least Square (PLS), Classification and Regression Tree (CART), Classification Tree(CT). The classification accuracy has been calculated and compared to find which side of the leaf image (dorsal or ventral) gives better results with which type of features(texture or statistical). This study reveals that the ventral leaf features can be another alternative in discriminating the leaf images into various classes.

show abstract

“…A large variety of pathologies has been studied using many different approaches of this tool. To cite a few, Besson et al 17 used surface‐based features extracted from brain T1‐MR images for the detection of Focal Cortical Dysplasia; Georgiadis et al 18 applied cooccurrence and run‐length matrices features to the characterization of different types of brain tumors; McLaren et al 19 used morphologic, cooccurrence, and Laws texture parameters in MR images for breast cancer diagnosis; Oliveira et al 20 used cooccurrence matrix features to find alterations in CT images of acute ischemic stroke; Theocharakis et al 21 studied multiple sclerosis using histogram, cooccurrence, and run‐length matrices‐based features extracted from FLAIR‐MR images; Zhang et al 22 applied texture analysis based on the polar Stockwell Transform to gadolinium‐enhanced T2‐MR images, also for the study of multiple sclerosis. However, we did not find any work using texture analysis in MJD, and we believe this technique could add relevant information in better determining the extent of central nervous system involvement in MJD.…”

Section: Introductionmentioning

confidence: 99%