Automatic stratification of prostate tumour aggressiveness using multiparametric MRI: a horizontal comparison of texture features

References

• Gordetsky J, Epstein J. Grading of prostatic adenocarcinoma: current state and prognostic implications. Diagn Pathol. 2016;11:2–9.
   PubMed Web of Science ®Google Scholar
• Evans MA, Millar JL, Earnest A, et al. Active surveillance of men with low risk prostate cancer: evidence from the Prostate Cancer Outcomes Registry-Victoria. Med J Aust. 2018;208:439–443.
   PubMed Web of Science ®Google Scholar
• van der Poel HG, van den Bergh RCN, Briers E, et al. Focal therapy in primary localised prostate cancer: the European Association of Urology Position in 2018. Eur Urol. 2018;74:84–91.
   PubMed Web of Science ®Google Scholar
• Haworth A, Williams S. Focal therapy for prostate cancer: the technical challenges. JCB. 2017;9:383–389.
   Google Scholar
• Bossart EL, Stoyanova R, Sandler K, et al. Feasibility and initial dosimetric findings for a randomized trial using dose-painted multiparametric magnetic resonance imaging-defined targets in prostate cancer. Int J Radiat Oncol. 2016;95:827–834.
   PubMed Web of Science ®Google Scholar
• Lips IM, van der Heide UA, Haustermans K, et al. Single blind randomized phase III trial to investigate the benefit of a focal lesion ablative microboost in prostate cancer (FLAME-trial): study protocol for a randomized controlled trial. Trials. 2011;12:255.
   PubMed Web of Science ®Google Scholar
• Haworth A, Williams S, Reynolds H, et al. Validation of a radiobiological model for low-dose-rate prostate boost focal therapy treatment planning. Brachytherapy. 2013;12:628–636.
   PubMed Web of Science ®Google Scholar
• Hassanzadeh E, Glazer D, Dunne R, et al. Prostate imaging reporting and data system version 2 (PI-RADS v2): a pictorial review. Abdominal Radiology. 2017;42:278–279.
   PubMed Web of Science ®Google Scholar
• Weinreb JC, Barentsz JO, Choyke PL, et al. PI-RADS prostate imaging – reporting and data system: 2015, version 2. Eur Urol. 2016;69:16–40.
   PubMed Web of Science ®Google Scholar
• Barentsz JO, Richenberg J, Clements R, et al. ESUR prostate MR guidelines 2012. Eur Radiol. 2012;22:746–757.
   PubMed Web of Science ®Google Scholar
• Penzkofer T, Tempany-Afdhal CM. Prostate cancer detection and diagnosis: the role of MR and its comparison with other diagnostic modalities – a radiologist’s perspective. NMR Biomed. 2014;27:3–15.
   PubMed Web of Science ®Google Scholar
• Le BD. Apparent diffusion coefficient and beyond: what diffusion MR imaging can tell us about tissue structure. Radiology. 2013;268:318–322.
   PubMed Web of Science ®Google Scholar
• Verma S, Turkbey B, Muradyan N, et al. Overview of dynamic contrast-enhanced MRI in prostate cancer diagnosis and management. AJR Am J Roentgenol. 2012;198:1277–1288.
   PubMed Web of Science ®Google Scholar
• Verma S, Rajesh A, Morales H, et al. Assessment of aggressiveness of prostate cancer: correlation of apparent diffusion coefficient with histologic grade after radical prostatectomy. Am J Roentgenol. 2011;196:374–381.
   PubMed Web of Science ®Google Scholar
• Woo S, Kim SY, Cho JY, et al. Preoperative evaluation of prostate cancer aggressiveness: using ADC and ADC ratio in determining Gleason score. Am J Roentgenol. 2016;207:114–120.
   PubMed Web of Science ®Google Scholar
• Donati OF, Mazaheri Y, Afaq A, et al. Prostate cancer aggressiveness: assessment with whole-lesion histogram analysis of the apparent diffusion coefficient. Radiology. 2014;271:143–152.
   PubMed Web of Science ®Google Scholar
• Giannini V, Vignati A, Mirasole S, et al. MR-T2-weighted signal intensity: a new imaging biomarker of prostate cancer aggressiveness. Comput Methods Biomech Biomed Eng Imaging Vis. 2016;4:130–134.
   Web of Science ®Google Scholar
• Rosenkrantz AB, Kopec M, Kong X, et al. Prostate cancer vs. post-biopsy hemorrhage: diagnosis with T2- and diffusion-weighted imaging. J Magn Reson Imaging. 2010;31:1387–1394.
   PubMed Web of Science ®Google Scholar
• Wang L, Mazaheri Y, Zhang J, et al. Assessment of biologic aggressiveness of prostate cancer: correlation of MR signal intensity with Gleason grade after radical prostatectomy. Radiology. 2008;246:168–176.
   PubMed Web of Science ®Google Scholar
• Chen Y-J, Chu W-C, Pu Y-S, et al. Washout gradient in dynamic contrast-enhanced MRI is associated with tumor aggressiveness of prostate cancer. J Magn Reson Imaging. 2012;36:912–919.
   PubMed Web of Science ®Google Scholar
• Isebaert S, Keyzer FD, Haustermans K, et al. Evaluation of semi-quantitative dynamic contrast-enhanced MRI parameters for prostate cancer in correlation to whole-mount histopathology. Eur J Radiol. 2012;81:e217–e222.
   PubMed Web of Science ®Google Scholar
• Langer DL, van der Kwast TH, Evans AJ, et al. Prostate tissue composition and MR measurements: investigating the relationships between ADC, T2, Ktrans, ve, and corresponding histologic features. Radiology. 2010;255:485–494.
   PubMed Web of Science ®Google Scholar
• Padhani AR, Gapinski CJ, Macvicar D. a, et al. Dynamic contrast enhanced MRI of prostate cancer: correlation with morphology and tumour stage, histological grade and PSA. Clin Radiol. 2000;55:99–109.
   PubMed Web of Science ®Google Scholar
• 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.
   PubMed Web of Science ®Google Scholar
• Yang F, Ford JC, Dogan N, et al. Magnetic resonance imaging (MRI)-based radiomics for prostate cancer radiotherapy. Transl Androl Urol. 2018;7:445–458.
   PubMed Web of Science ®Google Scholar
• Rozenberg R, Thornhill RE, Flood TA, et al. Whole-tumor quantitative apparent diffusion coefficient histogram and texture analysis to predict Gleason score upgrading in intermediate-risk 3 + 4 = 7 prostate cancer. Am J Roentgenol. 2016;206:775–782.
   Web of Science ®Google Scholar
• Nketiah G, Elschot M, Kim E, et al. T2-weighted MRI-derived textural features reflect prostate cancer aggressiveness: preliminary results. Eur Radiol. 2016;27:3050–3059.
   PubMed Web of Science ®Google Scholar
• Fehr D, Veeraraghavan H, Wibmer A, et al. Automatic classification of prostate cancer Gleason scores from multiparametric magnetic resonance images. Proc Natl Acad Sci USA. 2015;112:6265–6273.
   Web of Science ®Google Scholar
• 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;60:2685–2701.
   Web of Science ®Google Scholar
• Galloway MM. Texture analysis using gray level run lengths. Comput Graph Image Process. 1975;4:172–179.
   Google Scholar
• Thibault G, Fertil B, Navarro C, et al. Shape and texture indexes application to cell nuclei classification. Int J Patt Recogn Artif Intell. 2013;27:1357002.
   Web of Science ®Google Scholar
• Reynolds HM, Williams S, Zhang A, et al. Development of a registration framework to validate MRI with histology for prostate focal therapy. Med Phys. 2015;42:7078–7089.
   Web of Science ®Google Scholar
• Chan TY, Partin AW, Walsh PC, et al. Prognostic significance of Gleason score 3 + 4 versus Gleason score 4 + 3 tumor at radical prostatectomy. Urology. 2000;56:823–827.
   PubMed Web of Science ®Google Scholar
• Lv D, Guo X, Wang X, et al. Computerized characterization of prostate cancer by fractal analysis in MR images. J Magn Reson Imaging. 2009;30:161–168.
   PubMed Web of Science ®Google Scholar
• 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 MR imagery. J Magn Reson Imaging. 2012;36:213–224.
   PubMed Web of Science ®Google Scholar
• Viswanath S, Palumbo D, Chappelow J, et al. Empirical evaluation of bias field correction algorithms for computer-aided detection of prostate cancer on T2w MRI. Prog Biomed Opt Imaging - Proc SPIE. 2011;7963:79630V1–79630V12.
   Google Scholar
• Tustison NJ, Avants BB, Cook PA, et al. N4ITK: improved N3 bias correction. IEEE Trans Med Imaging. 2010;29:1310–1320.
   PubMed Web of Science ®Google Scholar
• Cheadle C, Vawter MP, Freed WJ, et al. Analysis of microarray data using Z score transformation. J Mol Diagn. 2003;5:73–81.
   PubMed Web of Science ®Google Scholar
• Artan Y, Haider MA, Langer DL, et al. Prostate cancer localization with multispectral MRI using cost-sensitive support vector machines and conditional random fields. IEEE Trans Image Process. 2010;19:2444–2455.
   PubMed Web of Science ®Google Scholar
• Artan Y, Langer DL, Haider MA, et al. Prostate cancer segmentation with multispectral MRI using cost-sensitive conditional random fields. ISBI’09. 2009 Jun 28–Jul 1; Boston, Massachusetts, USA: IEEE International Symposium on Biomedical Imaging; 2009. p. 278–281.
   Google Scholar
• Ozer S, Haider MA, Langer DL, et al. Prostate cancer localization with multispectral MRI based on relevance vector machines. 2009 Jun 28–Jul 01; Boston, Massachusetts, USA: IEEE International Symposium on Biomedical Imaging; 2009. p. 73–76.
   Google Scholar
• Ozer S, Langer DL, Liu X, et al. Supervised and unsupervised methods for prostate cancer segmentation with multispectral MRI. Med Phys. 2010;37:1873–1883.
   PubMed Web of Science ®Google Scholar
• Lemaître G, Martí R, Freixenet J, et al. Computer-aided detection and diagnosis for prostate cancer based on mono and multi-parametric MRI: a review. Comput Biol Med. 2015;60:8–31.
   PubMed Web of Science ®Google Scholar
• Sestelo M, Villanueva NM, Meira-Machado L, et al. FWDselect: an R package for variable selection in regression models. RJ. 2016;8:132–148.
   Web of Science ®Google Scholar
• Bozdogan H. Model selection and Akaike’s information criterion (AIC): the general theory and its analytical extensions. Psychometrika. 1987;52:345–370.
   Web of Science ®Google Scholar
• Peng C-Y, Lee KL, Ingersoll GM. An introduction to logistic regression analysis and reporting. J Educ Res. 2002;96:3–14.
   Web of Science ®Google Scholar
• Kumar R, Indrayan A. Receiver operating characteristic (ROC) curve for medical researchers. Indian Pediatr. 2011;48:277–287.
   PubMed Web of Science ®Google Scholar
• Suh E, Dougherty ER, Lowey J, et al. Optimal number of features as a function of sample size for various classification rules. Bioinformatics. 2004;21:1509–1515.
   PubMed Web of Science ®Google Scholar
• Chatterjee A, Watson G, Myint E, et al. Changes in epithelium, stroma, and lumen space correlate more strongly with Gleason pattern and are stronger predictors of prostate ADC changes than cellularity metrics. Radiology. 2015;277:751–762.
   PubMed Web of Science ®Google Scholar
• Lawrence EM, Warren AY, Priest AN, et al. Evaluating prostate cancer using fractional tissue composition of radical prostatectomy specimens and pre-operative diffusional kurtosis magnetic resonance imaging. PLoS One. 2016;11:1–12.
   Web of Science ®Google Scholar
• Khalifa F, Soliman A, El-Baz A, et al. Models and methods for analyzing DCE-MRI: a review. Med Phys. 2014; 41:124301.
   PubMed Web of Science ®Google Scholar
• Kuhn M. Building predictive models in R using the caret package. J Stat Softw. 2008;28:1–26.
   PubMed Web of Science ®Google Scholar
• Dormann CF, Elith J, Bacher S, et al. Collinearity: a review of methods to deal with it and a simulation study evaluating their performance. Ecography; 2013;36:27–46.
   Google Scholar
• Haralick RM, Shanmugam K, Dinstein I. Textural features for image classification. IEEE Trans Syst Man Cybern. 1973;3:610–621.
   Google Scholar
• Lee JJ, Thomas I-C, Nolley R, et al. Biologic differences between peripheral and transition zone prostate cancer. Prostate. 2015;75:183–190.
   PubMed Web of Science ®Google Scholar
• Dikaios N, Alkalbani J, Abd-Alazeez M, et al. Zone-specific logistic regression models improve classification of prostate cancer on multi-parametric MRI. Eur Radiol. 2015;25:2727–2737.
   PubMed Web of Science ®Google Scholar