Tampere University of Technology

TUTCRIS Research Portal

The effect of region of interest size on textural parameters

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

Standard

The effect of region of interest size on textural parameters. / Sikiö, Minna; Holli-Helenius, Kirsi K.; Ryymin, Pertti; Dastidar, Prasun; Eskola, Hannu; Harrison, Lara.

2015 9th International Symposium on Image and Signal Processing and Analysis (ISPA) . IEEE, 2015. p. 149-153.

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

Harvard

Sikiö, M, Holli-Helenius, KK, Ryymin, P, Dastidar, P, Eskola, H & Harrison, L 2015, The effect of region of interest size on textural parameters. in 2015 9th International Symposium on Image and Signal Processing and Analysis (ISPA) . IEEE, pp. 149-153, International Symposium on Image and Signal Processing and Analysis, Croatia, 1/01/15. https://doi.org/10.1109/ISPA.2015.7306049

APA

Sikiö, M., Holli-Helenius, K. K., Ryymin, P., Dastidar, P., Eskola, H., & Harrison, L. (2015). The effect of region of interest size on textural parameters. In 2015 9th International Symposium on Image and Signal Processing and Analysis (ISPA) (pp. 149-153). IEEE. https://doi.org/10.1109/ISPA.2015.7306049

Vancouver

Sikiö M, Holli-Helenius KK, Ryymin P, Dastidar P, Eskola H, Harrison L. The effect of region of interest size on textural parameters. In 2015 9th International Symposium on Image and Signal Processing and Analysis (ISPA) . IEEE. 2015. p. 149-153 https://doi.org/10.1109/ISPA.2015.7306049

Author

Sikiö, Minna ; Holli-Helenius, Kirsi K. ; Ryymin, Pertti ; Dastidar, Prasun ; Eskola, Hannu ; Harrison, Lara. / The effect of region of interest size on textural parameters. 2015 9th International Symposium on Image and Signal Processing and Analysis (ISPA) . IEEE, 2015. pp. 149-153

Bibtex - Download

@inproceedings{dad26c055b1b44f1a0d3ef2ee5d111e7,
title = "The effect of region of interest size on textural parameters",
abstract = "Texture analysis provides quantitative information describing the properties of a digital image. The value of texture analysis has been tested in various medical applications, using mostly magnetic resonance images because of the amount of information the method is capable to provide. However, there exists no certain practice to define the region of interest (ROI) within the texture parameters are calculated. Many parameters seem to be dependent on the ROI size. We studied the effect of the ROI size with magnetic resonance head images from 64 healthy adults and artificial noise images. According to our results, ROI size has a significant effect on the computed value of several second-order texture features. We conclude that comparisons of different size ROIs will therefore lead to falsely optimistic classification between analyzed tissues.",
keywords = "magnetic resonance imaging, random pattern, region of interest, size, texture analysis",
author = "Minna Siki{\"o} and Holli-Helenius, {Kirsi K.} and Pertti Ryymin and Prasun Dastidar and Hannu Eskola and Lara Harrison",
note = "EXT={"}Dastidar, Prasun{"} EXT={"}Siki{\"o}, Minna{"}",
year = "2015",
month = "10",
day = "23",
doi = "10.1109/ISPA.2015.7306049",
language = "English",
publisher = "IEEE",
pages = "149--153",
booktitle = "2015 9th International Symposium on Image and Signal Processing and Analysis (ISPA)",

}

RIS (suitable for import to EndNote) - Download

TY - GEN

T1 - The effect of region of interest size on textural parameters

AU - Sikiö, Minna

AU - Holli-Helenius, Kirsi K.

AU - Ryymin, Pertti

AU - Dastidar, Prasun

AU - Eskola, Hannu

AU - Harrison, Lara

N1 - EXT="Dastidar, Prasun" EXT="Sikiö, Minna"

PY - 2015/10/23

Y1 - 2015/10/23

N2 - Texture analysis provides quantitative information describing the properties of a digital image. The value of texture analysis has been tested in various medical applications, using mostly magnetic resonance images because of the amount of information the method is capable to provide. However, there exists no certain practice to define the region of interest (ROI) within the texture parameters are calculated. Many parameters seem to be dependent on the ROI size. We studied the effect of the ROI size with magnetic resonance head images from 64 healthy adults and artificial noise images. According to our results, ROI size has a significant effect on the computed value of several second-order texture features. We conclude that comparisons of different size ROIs will therefore lead to falsely optimistic classification between analyzed tissues.

AB - Texture analysis provides quantitative information describing the properties of a digital image. The value of texture analysis has been tested in various medical applications, using mostly magnetic resonance images because of the amount of information the method is capable to provide. However, there exists no certain practice to define the region of interest (ROI) within the texture parameters are calculated. Many parameters seem to be dependent on the ROI size. We studied the effect of the ROI size with magnetic resonance head images from 64 healthy adults and artificial noise images. According to our results, ROI size has a significant effect on the computed value of several second-order texture features. We conclude that comparisons of different size ROIs will therefore lead to falsely optimistic classification between analyzed tissues.

KW - magnetic resonance imaging

KW - random pattern

KW - region of interest

KW - size

KW - texture analysis

U2 - 10.1109/ISPA.2015.7306049

DO - 10.1109/ISPA.2015.7306049

M3 - Conference contribution

SP - 149

EP - 153

BT - 2015 9th International Symposium on Image and Signal Processing and Analysis (ISPA)

PB - IEEE

ER -