CoChat
Sign Up
Cited by 162Radiomics and Machine Learning in Medical ImagingProstate Cancer Diagnosis and TreatmentImage Retrieval and Classification Techniques

Haralick textural features on T2-weighted MRI are associated with biochemical recurrence following radiotherapy for peripheral zone prostate cancer: Impact of MRI in Prostate Cancer

Open access
Gnep, Khémara, Fargeas, Auréline, Gutiérrez-Carvajal, Ricardo E., Commandeur, Frédéric, Mathieu, Romain, Ospina, Juan D., Rolland, Yan, Rohou, Tanguy +4 more·2017·Journal of Magnetic Resonance Imaging
DOI 10.1002/jmri.25335
Open this paper in CoChat — free accountOpen PDF

Abstract

Purpose To explore the association between magnetic resonance imaging (MRI), including Haralick textural features, and biochemical recurrence following prostate cancer radiotherapy. Materials and Methods In all, 74 patients with peripheral zone localized prostate adenocarcinoma underwent pretreatment 3.0T MRI before external beam radiotherapy. Median follow-up of 47 months revealed 11 patients with biochemical recurrence. Prostate tumors were segmented on T2-weighted sequences (T2-w) and contours were propagated onto the coregistered apparent diffusion coefficient (ADC) images. We extracted 140 image features from normalized T2-w and ADC images corresponding to first-order (n = 6), gradient-based (n = 4), and second-order Haralick textural features (n = 130). Four geometrical features (tumor diameter, perimeter, area, and volume) were also computed. Correlations between Gleason score and MRI features were assessed. Cox regression analysis and random survival forests (RSF) were performed to assess the association between MRI features and biochemical recurrence. Results Three T2-w and one ADC Haralick textural features were significantly correlated with Gleason score (P < 0.05). Twenty-eight T2-w Haralick features and all four geometrical features were significantly associated with biochemical recurrence (P < 0.05). The most relevant features were Haralick features T2-w contrast, T2-w difference variance, ADC median, along with tumor volume and tumor area (C-index from 0.76 to 0.82; P < 0.05). By combining these most powerful features in an RSF model, the obtained C-index was 0.90. Conclusion T2-w Haralick features appear to be strongly associated with biochemical recurrence following prostate cancer radiotherapy. Level of Evidence: 3 J. Magn. Reson. Imaging 2017;45:103–117.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1002/jmri.25335

Cites

3 of 3 references verified0 citation errors · 0 not checkable

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • Haralick's features are a well-established set of rotation invariant image statistics used in medical classification across many fields and imaging modalities.

    “Haralick’s features are a well-established set of rotation invariant image statistics that have been used in medical classification issues across many fields and imaging modalities (Doyle et al, 2008; Gnep et al, 2017; Hapsari et al, 2022).”

    From APOE from astrocytes restores Alzheimer’s Aβ-pathology and DAM-like responses in APOE deficient microglia (2024) · cites this paper as Gnep et al, 2017

    The MRI Feature Extraction section describes Haralick features as image statistics derived from gray-level co-occurrence matrices and says the study averaged values across four directions. The Discussion describes their use in several cancers, but only in a few MRI studies. The paper does not establish that the features are inherently rotation invariant or used for medical classification across many fields and imaging modalities. Page numbers were not available in our copy. (LLM, conf=0.84)

    Experimental — accuracy not yet measured

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Cites

Flagged first, then by citations

Research works printed but not linked: 43

  1. D'Amico AV, Whittington R, Malkowicz S, et al. Biochemical outcome after radical prostatectomy, external beam radiation therapy, or inter- stitial radiation therapy for clinically localized prostate cancer. JAMA 1998;280:969-974.
  2. Cahlon O, Hunt M, Zelefsky MJ. Intensity-modulated radiation ther- apy: supportive data for prostate cancer. Semin Radiat Oncol 2008; 18:48-57.
  3. Lambin P, Rios-Velazquez E, Leijenaar R, et al. Radiomics: extracting more information from medical images using advanced feature analy- sis. Eur J Cancer 2012;48:441-446.
  4. Barentsz JO, Weinreb JC, Verma S, et al. Synopsis of the PI-RADS v2 guidelines for multiparametric prostate magnetic resonance imaging and recommendations for use. Eur Urol 2016;69:41-49.
  5. Hamoen EHJ, de Rooij M, Witjes JA, Barentsz JO, Rovers MM. Use of the Prostate Imaging Reporting and Data System (PI-RADS) for pros- tate cancer detection with multiparametric magnetic resonance imag- ing: a diagnostic meta-analysis. Eur Urol 2015;67:1112-1121.
  6. Nguyen PL, Whittington R, Koo S, et al. Quantifying the impact of seminal vesicle invasion identified using endorectal magnetic reso- nance imaging on PSA outcome after radiation therapy for patients with clinically localized prostate cancer. Int J Radiat Oncol 2004;59: 400-405.
  7. McKenna DA, Coakley FV, Westphalen AC, et al. Prostate cancer: role of pre-treatment MR in predicting outcome after external-beam radia- tion therapy-initial experience. Radiology 2008;247:141-146.
  8. Joseph T, McKenna DA, Westphalen AC, et al. Pretreatment endorec- tal magnetic resonance imaging and magnetic resonance spectro- scopic imaging features of prostate cancer as predictors of response to external beam radiotherapy. Int J Radiat Oncol 2009;73:665-671.
  9. Riaz N, Afaq A, Akin O, et al. Pretreatment endorectal coil magnetic resonance imaging findings predict biochemical tumor control in pros- tate cancer patients treated with combination brachytherapy and external-beam radiotherapy. Int J Radiat Oncol 2012;84:707-711.
  10. Ganeshan B, Goh V, Mandeville HC, Ng QS, Hoskin PJ, Miles KA. Non-small cell lung cancer: histopathologic correlates for texture parameters at CT. Radiology 2013;266:326-336.
  11. Haralick RM, Shanmugam K, Dinstein I. Textural features for image classification. IEEE Trans Syst Man Cybern 1973;SMC-3:610-621.
  12. Harrison LC, Luukkaala T, Pertovaara H, et al. Non-Hodgkin lym- phoma response evaluation with MRI texture classification. J Exp Clin Cancer Res 2009;28:1.
  13. Ahmed A, Gibbs P, Pickles M, Turnbull L. Texture analysis in assess- ment and prediction of chemotherapy response in breast cancer. J Magn Reson Imaging 2013;8:89-101.
  14. Yang D, Rao G, Martinez J, Veeraraghavan A, Rao A. Evaluation of tumor-derived MRI-texture features for discrimination of molecular subtypes and prediction of 12-month survival status in glioblastoma. Med Phys 2015;42:6725-6735.
  15. Vallieres M, Freeman CR, Skamene SR, Naqa IE. A radiomics model from joint FDG-PET and MRI texture features for the prediction of lung metastases in soft-tissue sarcomas of the extremities. Phys Med Biol 2015;60:5471.
  16. Upadhaya T, Morvan Y, Stindel E, Le Reste P-J, Hatt M. A framework for multimodal imaging-based prognostic model building: preliminary study on multimodal MRI in glioblastoma multiforme. IRBM 2015;36: 345-350.
  17. Viswanath SE, Bloch NB, Chappelow JC, et al. Central gland and peripheral zone prostate tumors have significantly different quantitative imaging signatures on 3 Tesla endorectal, in vivo T2-weighted mag- netic resonance imagery. J Magn Reson Imaging 2012;36:213-224.
  18. Duda D, Kretowski M, Mathieu R, Crevoisier R de, Bezy-Wendling J. Multi-image texture analysis in classification of prostatic tissues from MRI. Preliminary results. In: Piêtka E, Kawa J, Wieclawek W, editors. Information technology and biomedicine, vol. 3. Springer International Publishing; 2014:139-150 [Advances in intelligent systems and com- puting, vol. 283].
  19. Vignati A, Mazzetti S, Giannini V, et al. Texture features on T2- weighted magnetic resonance imaging: new potential biomarkers for prostate cancer aggressiveness. Phys Med Biol 2015;0:2685.
  20. Abramowitz MC, Li T, Buyyounouski MK, et al. The Phoenix definition of biochemical failure predicts for overall survival in patients with prostate cancer. Cancer 2008;112:55-60.
  21. Itatani R, Namimoto T, Yoshimura A, et al. Clinical utility of the nor- malized apparent diffusion coefficient for preoperative evaluation of the aggressiveness of prostate cancer. Jpn J Radiol 2014;32:685-691.
  22. Delgado-Gonzalo R, Thevenaz P, Seelamantula CS, Unser M. Snakes with an ellipse-reproducing property. IEEE Trans Image Process 2012; 21:1258-1271.
  23. Breiman L. Random forests. Mach Learn 2001;45:5-32.
  24. Datema FR, Moya A, Krause P, et al. Novel head and neck cancer sur- vival analysis approach: random survival forests versus cox propor- tional hazards regression. Head Neck 2012;34:50-58.
  25. Jolliffe I. Principal component analysis. In: Everitt BS, Howell DC, edi- tors. Encyclopedia of statistical behavior science. Chichester, UK: John Wiley & Sons; 2005.
  26. Harrell FE, Lee KL, Mark DB. Multivariable prognostic models: issues in developing models, evaluating assumptions and adequacy, and measuring and reducing errors. Stat Med 1996;15:361-387.
  27. Lerski RA, Straughan K, Schad LR, Boyce D, Bl€ uml S, Zuna I. MR image texture analysis-an approach to tissue characterization. Magn Reson Imaging 1993;11:873-887.
  28. Tsai F, Chang C-K, Rau J-Y, Lin T-H, Liu G-R. 3D computation of gray level co-occurrence in hyperspectral image cubes. In: Yuille AL, Zhu S-C, Cremers D, Wang Y, editors. Energy minimization methods in computer visualizaion pattern recognition. Berlin, Heidelberg: Springer; 2007:429-440 [Lecture Notes in Computer Science, vol. 4679].
  29. Hatt M, Majdoub M, Vallie `res M, et al. 18F-FDG PET uptake charac- terization through texture analysis: investigating the complementary nature of heterogeneity and functional tumor volume in a multi- cancer site patient cohort. J Nucl Med 2015;56:38-44.
  30. D'Amico AV, Chen M-H, Renshaw AA, Loffredo B, Kantoff PW. Risk of prostate cancer recurrence in men treated with radiation alone or in conjunction with combined or less than combined androgen suppres- sion therapy. J Clin Oncol 2008;26:2979-2983.
  31. Rosenkrantz AB, Kopec M, Kong X, et al. Prostate cancer vs. post- biopsy hemorrhage: Diagnosis with T2-and diffusion-weighted imag- ing. J Magn Reson Imaging 2010;31:1387-1394.
  32. Giannini V, Vignati A, Mirasole S, et al. MR-T2-weighted signal inten- sity: a new imaging biomarker of prostate cancer aggressiveness. Comput Methods Biomech Biomed Eng Imaging Vis 2014;0:1-5.
  33. Vargas HA, Akin O, Franiel T, et al. Diffusion-weighted endorectal MR imaging at 3 T for prostate cancer: tumor detection and assessment of aggressiveness. Radiology 2011;259:775-784.
  34. Turkbey B, Shah VP, Pang Y, et al. Is apparent diffusion coefficient associated with clinical risk scores for prostate cancers that are visible on 3-T MR images? Radiology 2011;258:488-495.
  35. Oto A, Yang C, Kayhan A, et al. Diffusion-weighted and dynamic contrast-enhanced MRI of prostate cancer: correlation of quantitative MR parameters with gleason score and tumor angiogenesis. Am J Roentgenol 2011;197:1382-1390.
  36. Hambrock T, Somford DM, Huisman HJ, et al. Relationship between apparent diffusion coefficients at 3.0-T MR imaging and Gleason grade in peripheral zone prostate cancer. Radiology 2011;259:453- 461.
  37. Peng Y, Jiang Y, Yang C, et al. Quantitative analysis of multipara- metric prostate MR images: differentiation between prostate cancer and normal tissue and correlation with Gleason score -a computer-aided diagnosis development study. Radiology 2013;267: 787-796.
  38. Michoux N, Van den Broeck S, Lacoste L, et al. Texture analysis on MR images helps predicting non-response to NAC in breast cancer. BMC Cancer 2015;15:574.
  39. Herlidou-Même S, Constans JM, Carsin B, et al. MRI texture analysis on texture test objects, normal brain and intracranial tumors. Magn Reson Imaging 2003;21:989-993.
  40. Mayerhoefer ME, Breitenseher MJ, Kramer J, Aigner N, Hofmann S, Materka A. Texture analysis for tissue discrimination on T1-weighted MR images of the knee joint in a multicenter study: transferability of texture features and comparison of feature selection methods and classifiers. J Magn Reson Imaging 2005;22:674-680.
  41. Mayerhoefer ME, Szomolanyi P, Jirak D, Materka A, Trattnig S. Effects of MRI acquisition parameter variations and protocol het- erogeneity on the results of texture analysis and pattern discrimi- nation: an application-oriented study. Med Phys 2009;36:1236- 1243.
  42. Lv D, Guo X, Wang X, Zhang J, Fang J. Computerized characteriza- tion of prostate cancer by fractal analysis in MR images. J Magn Reson Imaging JMRI 2009;30:161-168.
  43. Niaf E, Rouvie `re O, Me `ge-Lechevallier F, Bratan F, Lartizien C. Com- puter-aided diagnosis of prostate cancer in the peripheral zone using multiparametric MRI. Phys Med Biol 2012;57:3833-3851.

Cited by

Sorted by citations

Authors
Gnep, K., Fargeas, A., Gutiérrez-Carvajal, R. E., Commandeur, F., Mathieu, R., Ospina, J. D., Rolland, Y., Rohou, T., Vincendeau, S., Hatt, M., Acosta, O., & de Crevoisier, R.
Affiliations
  • Inserm (FR)
  • INSERM, U1099; Rennes France
  • Centre Eugène Marquis (FR)
  • Hôpital Pontchaillou (FR)
Corresponding author
Gnep, Khémara
ORCID
Venue
Journal of Magnetic Resonance Imaging
Publisher
Wiley
Published
2016-06-27
Volume
45
Issue
1
Pages
103-117
ISSN
1053-1807 (ISSN-L)
DOI
10.1002/jmri.25335
OpenAlex
W2506062488
Cited by
162
References
3
Citations by year
2026: 4 · 2025: 11 · 2024: 11 · 2023: 17 · 2022: 16 · 2021: 17 · 2020: 24 · 2019: 26 · 2018: 21 · 2017: 11 · 2016: 4
FWCI
15.60
Type
journal article
Language
en
Open access
Licence
Locations
  • Journal of Magnetic Resonance Imaging (publishedVersion)
  • PubMed (publishedVersion)
  • HAL (submittedVersion)
Funders
Agence Nationale de la Recherche (ANR‐10‐LABX‐07‐01, -10-LABX-07-01, ANR-10)
Topics
  • Health Sciences › Medicine › Radiology, Nuclear Medicine and Imaging › Radiomics and Machine Learning in Medical Imaging
  • Health Sciences › Medicine › Pulmonary and Respiratory Medicine › Prostate Cancer Diagnosis and Treatment
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image Retrieval and Classification Techniques
Keywords
prostate cancer, biochemical recurrence, T2-weighted MRI, apparent diffusion coefficient, radiotherapy, Gleason score, tumor volume, random survival forest, prognostic imaging features
MeSH terms
Aged, Aged, 80 and over, Follow-Up Studies, Humans, Image Enhancement, Image Interpretation, Computer-Assisted, Longitudinal Studies, Male, Middle Aged, Neoplasm Recurrence, Local, Prostatic Neoplasms, Retrospective Studies, Sensitivity and Specificity, Biomarkers, Tumor, Reproducibility of Results, Observer Variation, Treatment Outcome, Prostate-Specific Antigen, Radiotherapy, Conformal

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review