Haralick texture analysis of prostate MRI: utility for differentiating non-cancerous prostate from prostate cancer and differentiating prostate cancers with different Gleason scores

Andreas Wibmer, Hedvig Hricak, Tatsuo Gondo, Kazuhiro Matsumoto, Harini Veeraraghavan, Duc Fehr, Junting Zheng, Debra Goldman, Chaya Moskowitz, Samson W. Fine, Victor E. Reuter, James Eastham, Evis Sala, Hebert Alberto Vargas

Research output: Contribution to journalArticle

140 Citations (Scopus)

Abstract

Objectives: To investigate Haralick texture analysis of prostate MRI for cancer detection and differentiating Gleason scores (GS). Methods: One hundred and forty-seven patients underwent T2- weighted (T2WI) and diffusion-weighted prostate MRI. Cancers ≥0.5 ml and non-cancerous peripheral (PZ) and transition (TZ) zone tissue were identified on T2WI and apparent diffusion coefficient (ADC) maps, using whole-mount pathology as reference. Texture features (Energy, Entropy, Correlation, Homogeneity, Inertia) were extracted and analysed using generalized estimating equations. Results: PZ cancers (n = 143) showed higher Entropy and Inertia and lower Energy, Correlation and Homogeneity compared to non-cancerous tissue on T2WI and ADC maps (p-values: <.0001–0.008). In TZ cancers (n = 43) we observed significant differences for all five texture features on the ADC map (all p-values: <.0001) and for Correlation (p = 0.041) and Inertia (p = 0.001) on T2WI. On ADC maps, GS was associated with higher Entropy (GS 6 vs. 7: p = 0.0225; 6 vs. >7: p = 0.0069) and lower Energy (GS 6 vs. 7: p = 0.0116, 6 vs. >7: p = 0.0039). ADC map Energy (p = 0.0102) and Entropy (p = 0.0019) were significantly different in GS ≤3 + 4 versus ≥4 + 3 cancers; ADC map Entropy remained significant after controlling for the median ADC (p = 0.0291). Conclusion: Several Haralick-based texture features appear useful for prostate cancer detection and GS assessment. Key Points: • Several Haralick texture features may differentiate non-cancerous and cancerous prostate tissue. • Tumour Energy and Entropy on ADC maps correlate with Gleason score. • T2w-image-derived texture features are not associated with the Gleason score.

Original languageEnglish
Pages (from-to)2840-2850
Number of pages11
JournalEuropean Radiology
Volume25
Issue number10
DOIs
Publication statusPublished - 2015 Oct 13
Externally publishedYes

Fingerprint

Neoplasm Grading
Entropy
Prostate
Prostatic Neoplasms
Neoplasms
Diffusion Magnetic Resonance Imaging
Pathology

Keywords

  • Adenocarcinoma
  • Computer-assisted
  • Gleason grading
  • Image processing
  • Magnetic resonance imaging
  • Prostatic neoplasm

ASJC Scopus subject areas

  • Radiology Nuclear Medicine and imaging

Cite this

Haralick texture analysis of prostate MRI : utility for differentiating non-cancerous prostate from prostate cancer and differentiating prostate cancers with different Gleason scores. / Wibmer, Andreas; Hricak, Hedvig; Gondo, Tatsuo; Matsumoto, Kazuhiro; Veeraraghavan, Harini; Fehr, Duc; Zheng, Junting; Goldman, Debra; Moskowitz, Chaya; Fine, Samson W.; Reuter, Victor E.; Eastham, James; Sala, Evis; Vargas, Hebert Alberto.

In: European Radiology, Vol. 25, No. 10, 13.10.2015, p. 2840-2850.

Research output: Contribution to journalArticle

Wibmer, A, Hricak, H, Gondo, T, Matsumoto, K, Veeraraghavan, H, Fehr, D, Zheng, J, Goldman, D, Moskowitz, C, Fine, SW, Reuter, VE, Eastham, J, Sala, E & Vargas, HA 2015, 'Haralick texture analysis of prostate MRI: utility for differentiating non-cancerous prostate from prostate cancer and differentiating prostate cancers with different Gleason scores', European Radiology, vol. 25, no. 10, pp. 2840-2850. https://doi.org/10.1007/s00330-015-3701-8
Wibmer, Andreas ; Hricak, Hedvig ; Gondo, Tatsuo ; Matsumoto, Kazuhiro ; Veeraraghavan, Harini ; Fehr, Duc ; Zheng, Junting ; Goldman, Debra ; Moskowitz, Chaya ; Fine, Samson W. ; Reuter, Victor E. ; Eastham, James ; Sala, Evis ; Vargas, Hebert Alberto. / Haralick texture analysis of prostate MRI : utility for differentiating non-cancerous prostate from prostate cancer and differentiating prostate cancers with different Gleason scores. In: European Radiology. 2015 ; Vol. 25, No. 10. pp. 2840-2850.
@article{5a7374d91b804d7b98428b6d6929aac3,
title = "Haralick texture analysis of prostate MRI: utility for differentiating non-cancerous prostate from prostate cancer and differentiating prostate cancers with different Gleason scores",
abstract = "Objectives: To investigate Haralick texture analysis of prostate MRI for cancer detection and differentiating Gleason scores (GS). Methods: One hundred and forty-seven patients underwent T2- weighted (T2WI) and diffusion-weighted prostate MRI. Cancers ≥0.5 ml and non-cancerous peripheral (PZ) and transition (TZ) zone tissue were identified on T2WI and apparent diffusion coefficient (ADC) maps, using whole-mount pathology as reference. Texture features (Energy, Entropy, Correlation, Homogeneity, Inertia) were extracted and analysed using generalized estimating equations. Results: PZ cancers (n = 143) showed higher Entropy and Inertia and lower Energy, Correlation and Homogeneity compared to non-cancerous tissue on T2WI and ADC maps (p-values: <.0001–0.008). In TZ cancers (n = 43) we observed significant differences for all five texture features on the ADC map (all p-values: <.0001) and for Correlation (p = 0.041) and Inertia (p = 0.001) on T2WI. On ADC maps, GS was associated with higher Entropy (GS 6 vs. 7: p = 0.0225; 6 vs. >7: p = 0.0069) and lower Energy (GS 6 vs. 7: p = 0.0116, 6 vs. >7: p = 0.0039). ADC map Energy (p = 0.0102) and Entropy (p = 0.0019) were significantly different in GS ≤3 + 4 versus ≥4 + 3 cancers; ADC map Entropy remained significant after controlling for the median ADC (p = 0.0291). Conclusion: Several Haralick-based texture features appear useful for prostate cancer detection and GS assessment. Key Points: • Several Haralick texture features may differentiate non-cancerous and cancerous prostate tissue. • Tumour Energy and Entropy on ADC maps correlate with Gleason score. • T2w-image-derived texture features are not associated with the Gleason score.",
keywords = "Adenocarcinoma, Computer-assisted, Gleason grading, Image processing, Magnetic resonance imaging, Prostatic neoplasm",
author = "Andreas Wibmer and Hedvig Hricak and Tatsuo Gondo and Kazuhiro Matsumoto and Harini Veeraraghavan and Duc Fehr and Junting Zheng and Debra Goldman and Chaya Moskowitz and Fine, {Samson W.} and Reuter, {Victor E.} and James Eastham and Evis Sala and Vargas, {Hebert Alberto}",
year = "2015",
month = "10",
day = "13",
doi = "10.1007/s00330-015-3701-8",
language = "English",
volume = "25",
pages = "2840--2850",
journal = "European Radiology",
issn = "0938-7994",
publisher = "Springer Verlag",
number = "10",

}

TY - JOUR

T1 - Haralick texture analysis of prostate MRI

T2 - utility for differentiating non-cancerous prostate from prostate cancer and differentiating prostate cancers with different Gleason scores

AU - Wibmer, Andreas

AU - Hricak, Hedvig

AU - Gondo, Tatsuo

AU - Matsumoto, Kazuhiro

AU - Veeraraghavan, Harini

AU - Fehr, Duc

AU - Zheng, Junting

AU - Goldman, Debra

AU - Moskowitz, Chaya

AU - Fine, Samson W.

AU - Reuter, Victor E.

AU - Eastham, James

AU - Sala, Evis

AU - Vargas, Hebert Alberto

PY - 2015/10/13

Y1 - 2015/10/13

N2 - Objectives: To investigate Haralick texture analysis of prostate MRI for cancer detection and differentiating Gleason scores (GS). Methods: One hundred and forty-seven patients underwent T2- weighted (T2WI) and diffusion-weighted prostate MRI. Cancers ≥0.5 ml and non-cancerous peripheral (PZ) and transition (TZ) zone tissue were identified on T2WI and apparent diffusion coefficient (ADC) maps, using whole-mount pathology as reference. Texture features (Energy, Entropy, Correlation, Homogeneity, Inertia) were extracted and analysed using generalized estimating equations. Results: PZ cancers (n = 143) showed higher Entropy and Inertia and lower Energy, Correlation and Homogeneity compared to non-cancerous tissue on T2WI and ADC maps (p-values: <.0001–0.008). In TZ cancers (n = 43) we observed significant differences for all five texture features on the ADC map (all p-values: <.0001) and for Correlation (p = 0.041) and Inertia (p = 0.001) on T2WI. On ADC maps, GS was associated with higher Entropy (GS 6 vs. 7: p = 0.0225; 6 vs. >7: p = 0.0069) and lower Energy (GS 6 vs. 7: p = 0.0116, 6 vs. >7: p = 0.0039). ADC map Energy (p = 0.0102) and Entropy (p = 0.0019) were significantly different in GS ≤3 + 4 versus ≥4 + 3 cancers; ADC map Entropy remained significant after controlling for the median ADC (p = 0.0291). Conclusion: Several Haralick-based texture features appear useful for prostate cancer detection and GS assessment. Key Points: • Several Haralick texture features may differentiate non-cancerous and cancerous prostate tissue. • Tumour Energy and Entropy on ADC maps correlate with Gleason score. • T2w-image-derived texture features are not associated with the Gleason score.

AB - Objectives: To investigate Haralick texture analysis of prostate MRI for cancer detection and differentiating Gleason scores (GS). Methods: One hundred and forty-seven patients underwent T2- weighted (T2WI) and diffusion-weighted prostate MRI. Cancers ≥0.5 ml and non-cancerous peripheral (PZ) and transition (TZ) zone tissue were identified on T2WI and apparent diffusion coefficient (ADC) maps, using whole-mount pathology as reference. Texture features (Energy, Entropy, Correlation, Homogeneity, Inertia) were extracted and analysed using generalized estimating equations. Results: PZ cancers (n = 143) showed higher Entropy and Inertia and lower Energy, Correlation and Homogeneity compared to non-cancerous tissue on T2WI and ADC maps (p-values: <.0001–0.008). In TZ cancers (n = 43) we observed significant differences for all five texture features on the ADC map (all p-values: <.0001) and for Correlation (p = 0.041) and Inertia (p = 0.001) on T2WI. On ADC maps, GS was associated with higher Entropy (GS 6 vs. 7: p = 0.0225; 6 vs. >7: p = 0.0069) and lower Energy (GS 6 vs. 7: p = 0.0116, 6 vs. >7: p = 0.0039). ADC map Energy (p = 0.0102) and Entropy (p = 0.0019) were significantly different in GS ≤3 + 4 versus ≥4 + 3 cancers; ADC map Entropy remained significant after controlling for the median ADC (p = 0.0291). Conclusion: Several Haralick-based texture features appear useful for prostate cancer detection and GS assessment. Key Points: • Several Haralick texture features may differentiate non-cancerous and cancerous prostate tissue. • Tumour Energy and Entropy on ADC maps correlate with Gleason score. • T2w-image-derived texture features are not associated with the Gleason score.

KW - Adenocarcinoma

KW - Computer-assisted

KW - Gleason grading

KW - Image processing

KW - Magnetic resonance imaging

KW - Prostatic neoplasm

UR - http://www.scopus.com/inward/record.url?scp=84941420890&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84941420890&partnerID=8YFLogxK

U2 - 10.1007/s00330-015-3701-8

DO - 10.1007/s00330-015-3701-8

M3 - Article

C2 - 25991476

AN - SCOPUS:84941420890

VL - 25

SP - 2840

EP - 2850

JO - European Radiology

JF - European Radiology

SN - 0938-7994

IS - 10

ER -