2016
DOI: 10.18287/2412-6179-2016-40-6-939-946
|View full text |Cite
|
Sign up to set email alerts
|

Feature selection for diagnozing the osteoporosis by femoral neck X-ray images A.V. Gaidel, V.R. Krasheninnikov

Abstract: Отбор признаков для задачи диагностики остеопороза по рентгеновским изображениям шейки бедра Гайдель А.В., Крашенинников В.Р. Аннотация В работе анализируется информативность нескольких признаков текстуры рентгеновских изображений костной ткани для компьютерной диагностики остеопороза. Описываются че-тыре эвристических признака, также рассматривается тринадцать согласованных квадратич-ных признаков, описанных ранее. Решается задача выбора минимального набора из этих при-знаков, достаточного для линейной раздел… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
4
0

Year Published

2017
2017
2021
2021

Publication Types

Select...
4
4

Relationship

0
8

Authors

Journals

citations
Cited by 10 publications
(4 citation statements)
references
References 0 publications
0
4
0
Order By: Relevance
“…The spectrum image in the domain of interest was segmented using a formula: ( ) Since the spectral image is symmetric around the center, only half of the image will be used to form up the areas [7,8].…”
Section: Informative Areas Generation Methodsmentioning
confidence: 99%
“…The spectrum image in the domain of interest was segmented using a formula: ( ) Since the spectral image is symmetric around the center, only half of the image will be used to form up the areas [7,8].…”
Section: Informative Areas Generation Methodsmentioning
confidence: 99%
“…3. We create two new candidates for each of which we supplement the current matrix 1D  for the step q with BCs (7) and (10) by the cut selection procedures (by the value of () j cs  or by radicality (11)): ( 1)…”
Section: Binary Cut-and-branch Algorithmmentioning
confidence: 99%
“…Big data analytics includes the feature selection task [1,2] for predictive modelling [3]. In many practical applications, candidate predictors correlate strongly.…”
Section: Introductionmentioning
confidence: 99%
“…The spectrum image in the domain of interest was segmented using a formula: Since the spectral image is symmetric around the center, only half of the image will be used to form up the areas [4,5].…”
Section: Description Of the Areas Usedmentioning
confidence: 99%