2019
DOI: 10.1016/j.bbe.2018.11.008
|View full text |Cite
|
Sign up to set email alerts
|

The use of the Hellwig's method for feature selection in the detection of myeloma bone destruction based on radiographic images

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
7
0

Year Published

2019
2019
2023
2023

Publication Types

Select...
7
2

Relationship

1
8

Authors

Journals

citations
Cited by 17 publications
(7 citation statements)
references
References 34 publications
0
7
0
Order By: Relevance
“…It seems that good results might be achieved by combining the effects of fractal analysis with the results of other methods for texture feature extraction, for example, autoregression model, wavelet transform and statistical methods (greyscale histogram, co-occurrence matrix, higher-order statistics, run-length matrix and gradient matrix). 45,46 The results obtained are difficult to compare with the ones reported by other authors, because (as noted in 'Introduction') there are no known publications presenting the classification results aimed at the detection of osteoporosis, where the fractal analysis of the spine CT images on the thoraco-lumbar region would be used to extract textural features. The advantages of the presented method include the fact that it is non-invasive and offers an acceptable (from a medical point of view) accuracy of recognising the cases belonging to particular categories.…”
Section: Discussionmentioning
confidence: 94%
“…It seems that good results might be achieved by combining the effects of fractal analysis with the results of other methods for texture feature extraction, for example, autoregression model, wavelet transform and statistical methods (greyscale histogram, co-occurrence matrix, higher-order statistics, run-length matrix and gradient matrix). 45,46 The results obtained are difficult to compare with the ones reported by other authors, because (as noted in 'Introduction') there are no known publications presenting the classification results aimed at the detection of osteoporosis, where the fractal analysis of the spine CT images on the thoraco-lumbar region would be used to extract textural features. The advantages of the presented method include the fact that it is non-invasive and offers an acceptable (from a medical point of view) accuracy of recognising the cases belonging to particular categories.…”
Section: Discussionmentioning
confidence: 94%
“…In [ 75 ], the authors extract image feature vectors based on computed radiography and obtain 279 image descriptors. Through the Hellwig method, they find the feature combination set of the overall index with the maximum information capacity.…”
Section: Methods Analysismentioning
confidence: 99%
“…In order to select variables that affect the consumer decision whether to install SM at home or not, correlation coefficients between individual variables were calculated. Because some variables show some degree of correlation, we used a method, described in Kamrat (2002); Omiotek et al (2019) to identify central variables of leading importance and subordinate (satellite, isolated) variables (i.e. variables that individually form clusters).…”
Section: Analysis Of Correlations Between Variables In Groups (Pearson Spearman Tau Kendall)mentioning
confidence: 99%