Tensor Radial Lengths for Mammographic Image Enhancement

Chatzistergos, Sevastianos; Andreadis, Ioannis; Nikita, Konstantina S.

doi:10.1007/978-3-319-00846-2_76

Cited by 2 publications

(2 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In our previous work (Chatzistergos et al, ), we demonstrated the ability to reveal diagnostically critical information in mammograms by improving the local contrast, using a series of equally rotated radials that propagate until they meet a certain limit. The basic idea is to treat gray level values at each image point ( x 0 , y 0 ) as values in the z‐axis ( z 0 ) and create this way a 3D surface from the original image (Figure ).…”

Section: Lbp Based Schemesmentioning

confidence: 99%

“…To the best of authors' knowledge, LBP has not been previously used for the identification of ADs in mammographic images. Moreover, in an earlier work, we have highlighted the potential of radial lengths (RL) to enhance the contrast on mammograms, achieving promising results (Chatzistergos, Andreadis, & Nikita, 2014). Motivated by the simplicity and efficacy of LBP in texture analysis and the ability of RL to reveal diagnostically critical information, we propose the combination of these two methodologies, in the process of discrimination between AD and normal tissue or other lesion types (masses, calcifications).…”

mentioning

confidence: 99%

See 1 more Smart Citation

Identification of architectural distortions in mammograms using local binary patterns and radial lengths through an exhaustive evaluation framework

2018

View full text Add to dashboard Cite

A method based on the combination of Local Binary Pattern operator and radial lengths is presented aiming at the identification of Architectural Distortions (ADs) in mammograms. Local Binary Pattern operator, a number of its variants, and radial lengths are combined together producing a high‐dimensional feature space. A process, based on the combination of Principal Component Analysis and ttest, is used to effectively transform feature space and reveal the most descriptive features. The classification step is performed using a Support Vector Machine classifier. Open access databases (Mammographic Image Analysis Society and Digital Database for Screening Mammography) are used through an exhaustive evaluation framework that aims at eliminating both mammogram selection bias and limited subtlety variation, thus enabling a fair and complete comparison procedure. Furthermore, in order to provide a test bed for future comparisons, a dataset is constructed from all the available AD Regions Of Interest in Digital Database for Screening Mammography (163 AD vs 375 Regions Of Interest from specific normal cases) and is used to further evaluate the performance of the proposed method. The method performed flawlessly and classified correctly all cases.

show abstract

Section: Lbp Based Schemesmentioning

confidence: 99%

mentioning

confidence: 99%