Haralick texture features from apparent diffusion coefficient (ADC) MRI images depend on imaging and pre-processing parameters

Abstract In recent years, texture analysis of medical images has become increasingly popular in studies investigating diagnosis, classification and treatment response assessment of cancerous disease. Despite numerous applications in oncology and medical imaging in general, there is no consensus rega...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Patrik Brynolfsson, David Nilsson, Turid Torheim, Thomas Asklund, Camilla Thellenberg Karlsson, Johan Trygg, Tufve Nyholm, Anders Garpebring
Formato: article
Lenguaje:EN
Publicado: Nature Portfolio 2017
Materias:
R
Q
Acceso en línea:https://doaj.org/article/74ba0e7b0d094daf9ac8f49b66e5359c
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:74ba0e7b0d094daf9ac8f49b66e5359c
record_format dspace
spelling oai:doaj.org-article:74ba0e7b0d094daf9ac8f49b66e5359c2021-12-02T12:32:25ZHaralick texture features from apparent diffusion coefficient (ADC) MRI images depend on imaging and pre-processing parameters10.1038/s41598-017-04151-42045-2322https://doaj.org/article/74ba0e7b0d094daf9ac8f49b66e5359c2017-06-01T00:00:00Zhttps://doi.org/10.1038/s41598-017-04151-4https://doaj.org/toc/2045-2322Abstract In recent years, texture analysis of medical images has become increasingly popular in studies investigating diagnosis, classification and treatment response assessment of cancerous disease. Despite numerous applications in oncology and medical imaging in general, there is no consensus regarding texture analysis workflow, or reporting of parameter settings crucial for replication of results. The aim of this study was to assess how sensitive Haralick texture features of apparent diffusion coefficient (ADC) MR images are to changes in five parameters related to image acquisition and pre-processing: noise, resolution, how the ADC map is constructed, the choice of quantization method, and the number of gray levels in the quantized image. We found that noise, resolution, choice of quantization method and the number of gray levels in the quantized images had a significant influence on most texture features, and that the effect size varied between different features. Different methods for constructing the ADC maps did not have an impact on any texture feature. Based on our results, we recommend using images with similar resolutions and noise levels, using one quantization method, and the same number of gray levels in all quantized images, to make meaningful comparisons of texture feature results between different subjects.Patrik BrynolfssonDavid NilssonTurid TorheimThomas AsklundCamilla Thellenberg KarlssonJohan TryggTufve NyholmAnders GarpebringNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 7, Iss 1, Pp 1-11 (2017)
institution DOAJ
collection DOAJ
language EN
topic Medicine
R
Science
Q
spellingShingle Medicine
R
Science
Q
Patrik Brynolfsson
David Nilsson
Turid Torheim
Thomas Asklund
Camilla Thellenberg Karlsson
Johan Trygg
Tufve Nyholm
Anders Garpebring
Haralick texture features from apparent diffusion coefficient (ADC) MRI images depend on imaging and pre-processing parameters
description Abstract In recent years, texture analysis of medical images has become increasingly popular in studies investigating diagnosis, classification and treatment response assessment of cancerous disease. Despite numerous applications in oncology and medical imaging in general, there is no consensus regarding texture analysis workflow, or reporting of parameter settings crucial for replication of results. The aim of this study was to assess how sensitive Haralick texture features of apparent diffusion coefficient (ADC) MR images are to changes in five parameters related to image acquisition and pre-processing: noise, resolution, how the ADC map is constructed, the choice of quantization method, and the number of gray levels in the quantized image. We found that noise, resolution, choice of quantization method and the number of gray levels in the quantized images had a significant influence on most texture features, and that the effect size varied between different features. Different methods for constructing the ADC maps did not have an impact on any texture feature. Based on our results, we recommend using images with similar resolutions and noise levels, using one quantization method, and the same number of gray levels in all quantized images, to make meaningful comparisons of texture feature results between different subjects.
format article
author Patrik Brynolfsson
David Nilsson
Turid Torheim
Thomas Asklund
Camilla Thellenberg Karlsson
Johan Trygg
Tufve Nyholm
Anders Garpebring
author_facet Patrik Brynolfsson
David Nilsson
Turid Torheim
Thomas Asklund
Camilla Thellenberg Karlsson
Johan Trygg
Tufve Nyholm
Anders Garpebring
author_sort Patrik Brynolfsson
title Haralick texture features from apparent diffusion coefficient (ADC) MRI images depend on imaging and pre-processing parameters
title_short Haralick texture features from apparent diffusion coefficient (ADC) MRI images depend on imaging and pre-processing parameters
title_full Haralick texture features from apparent diffusion coefficient (ADC) MRI images depend on imaging and pre-processing parameters
title_fullStr Haralick texture features from apparent diffusion coefficient (ADC) MRI images depend on imaging and pre-processing parameters
title_full_unstemmed Haralick texture features from apparent diffusion coefficient (ADC) MRI images depend on imaging and pre-processing parameters
title_sort haralick texture features from apparent diffusion coefficient (adc) mri images depend on imaging and pre-processing parameters
publisher Nature Portfolio
publishDate 2017
url https://doaj.org/article/74ba0e7b0d094daf9ac8f49b66e5359c
work_keys_str_mv AT patrikbrynolfsson haralicktexturefeaturesfromapparentdiffusioncoefficientadcmriimagesdependonimagingandpreprocessingparameters
AT davidnilsson haralicktexturefeaturesfromapparentdiffusioncoefficientadcmriimagesdependonimagingandpreprocessingparameters
AT turidtorheim haralicktexturefeaturesfromapparentdiffusioncoefficientadcmriimagesdependonimagingandpreprocessingparameters
AT thomasasklund haralicktexturefeaturesfromapparentdiffusioncoefficientadcmriimagesdependonimagingandpreprocessingparameters
AT camillathellenbergkarlsson haralicktexturefeaturesfromapparentdiffusioncoefficientadcmriimagesdependonimagingandpreprocessingparameters
AT johantrygg haralicktexturefeaturesfromapparentdiffusioncoefficientadcmriimagesdependonimagingandpreprocessingparameters
AT tufvenyholm haralicktexturefeaturesfromapparentdiffusioncoefficientadcmriimagesdependonimagingandpreprocessingparameters
AT andersgarpebring haralicktexturefeaturesfromapparentdiffusioncoefficientadcmriimagesdependonimagingandpreprocessingparameters
_version_ 1718394102247063552