Automatic classification of prostate cancer Gleason scores from multiparametric magnetic resonance images

Proceedings of the National Academy of Sciences of the United States of America

Volumn 112, Issue 46, 2015, Pages E6265-E6273

  Fehr, Duc ^a   Veeraraghavan, Harini ^a   Wibmer, Andreas ^a   Gondo, Tatsuo ^a   Matsumoto, Kazuhiro ^a   Vargas, Herbert Alberto ^a   Sala, Evis ^a   Hricak, Hedvig ^a   Deasy, Joseph O ^a  

^a MEMORIAL SLOAN KETTERING CANCER CENTER   (United States)

Author keywords

Gleason score classification; Learning from unbalanced data; Multiparametric mri; PCa gleason (3+4) vs. (4+3) cancers; PCa gleason 6 vs. 7

Indexed keywords

APPARENT DIFFUSION COEFFICIENT; ARTICLE; CANCER CLASSIFICATION; CANCER DIAGNOSIS; CANCER TISSUE; DIAGNOSTIC ACCURACY; DIAGNOSTIC TEST ACCURACY STUDY; DIFFUSION COEFFICIENT; GLEASON SCORE; HISTOPATHOLOGY; HUMAN; HUMAN TISSUE; IMAGE ANALYSIS; MAJOR CLINICAL STUDY; MALE; MULTIPARAMETRIC MAGNETIC RESONANCE IMAGING; PRIORITY JOURNAL; PROSTATE BIOPSY; PROSTATE CANCER; PROSTATECTOMY; SUPPORT VECTOR MACHINE; DIAGNOSTIC IMAGING; IMAGE PROCESSING; MACHINE LEARNING; NUCLEAR MAGNETIC RESONANCE IMAGING; PREDICTIVE VALUE; PROCEDURES; PROSTATE TUMOR; RADIOGRAPHY;

HUMANS; IMAGE PROCESSING, COMPUTER-ASSISTED; MACHINE LEARNING; MAGNETIC RESONANCE IMAGING; MALE; PREDICTIVE VALUE OF TESTS; PROSTATIC NEOPLASMS; RADIOGRAPHY;

EID: 84966335551     PISSN: 00278424     EISSN: 10916490     Source Type: Journal    
DOI: 10.1073/pnas.1505935112     Document Type: Article

References (50)

1. Siegel RL, Miller KD, Jemal A (2015) Cancer statistics, 2015. CA Cancer J Clin 65(1):5-29.
2. Wright JL, et al. (2009) Prostate cancer specific mortality and Gleason 7 disease differences in prostate cancer outcomes between cases with Gleason 4 + 3 and Gleason 3 + 4 tumors in a population based cohort. J Urol 182(6):2702-2707.
3. Ahmed HU, et al.; Transatlantic Consensus Group on Active Surveillance and Focal Therapy for Prostate Cancer (appendix) (2012) Transatlantic Consensus Group on active surveillance and focal therapy for prostate cancer. BJU Int 109(11): 1636-1647.
4. Eggener SE, et al. (2011) Predicting 15-year prostate cancer specific mortality after radical prostatectomy. J Urol 185(3):869-875.
5. Lavery HJ, Droller MJ (2012) Do Gleason patterns 3 and 4 prostate cancer represent separate disease states? J Urol 188(5):1667-1675.
6. King CR, Long JP (2000) Prostate biopsy grading errors: A sampling problem? Int J Cancer 90(6):326-330.
7. Epstein JI, Feng Z, Trock BJ, Pierorazio PM (2012) Upgrading and downgrading of prostate cancer from biopsy to radical prostatectomy: Incidence and predictive factors using the modified Gleason grading system and factoring in tertiary grades. Eur Urol 61(5):1019-1024.
8. Berglund R.K.et al.2008Pathological upgrading and up staging with immediate repeat biopsy in patients eligible for active surveillanceJ Urol18051964-1967discussion1967-1968
9. Moore CM, Petrides N, Emberton M (2014) Can MRI replace serial biopsies in men on active surveillance for prostate cancer? Curr Opin Urol 24(3):280-287.
10. Sato C, et al. (2005) Differentiation of noncancerous tissue and cancer lesions by apparent diffusion coefficient values in transition and peripheral zones of the prostate. J Magn Reson Imaging 21(3):258-262.
11. Fütterer JJ, et al. (2006) Prostate cancer localization with dynamic contrast-enhanced MR imaging and proton MR spectroscopic imaging. Radiology 241(2):449-458.
12. Tanimoto A, Nakashima J, Kohno H, Shinmoto H, Kuribayashi S (2007) Prostate cancer screening: The clinical value of diffusion-weighted imaging and dynamic MR imaging in combination with T2-weighted imaging. J Magn Reson Imaging 25(1):146-152.
13. Kitajima K, et al. (2010) Prostate cancer detection with 3 T MRI: Comparison of diffusion-weighted imaging and dynamic contrast-enhanced MRI in combination with T2-weighted imaging. J Magn Reson Imaging 31(3):625-631.
14. Mazaheri Y, et al. (2008) Prostate cancer: Identification with combined diffusionweighted MR imaging and 3D 1H MR spectroscopic imaging-correlation with pathologic findings. Radiology 246(2):480-488.
15. Langer DL, et al. (2010) Prostate tissue composition and MR measurements: Investigating the relationships between ADC, T2, K(trans), v(e), and corresponding histologic features. Radiology 255(2):485-494.
16. Oto A, et al. (2011) Diffusion-weighted and dynamic contrast-enhanced MRI of prostate cancer: Correlation of quantitative MR parameters with Gleason score and tumor angiogenesis. AJR Am J Roentgenol 197(6):1382-1390.
17. Nagarajan MB, et al. (2013) Classification of small lesions in breast MRI: Evaluating the role of dynamically extracted texture features through feature selection. J Med Biol Eng 33(1):33.
18. Vargas HA, et al. (2011) Diffusion-weighted endorectal MR imaging at 3 T for prostate cancer: Tumor detection and assessment of aggressiveness. Radiology 259(3): 775-784.
19. deSouza NM, et al. (2008) Diffusion-weighted magnetic resonance imaging: A potential non-invasive marker of tumour aggressiveness in localized prostate cancer. Clin Radiol 63(7):774-782.
20. Donati OF, et al. (2014) Prostate cancer aggressiveness: Assessment with whole-lesion histogram analysis of the apparent diffusion coefficient. Radiology 271(1):143-152.
21. Peng Y, et al. (2013) Quantitative analysis of multiparametric prostate MR images: Differentiation between prostate cancer and normal tissue and correlation with Gleason score-a computer-aided diagnosis development study. Radiology 267(3): 787-796.
22. Donati OF, et al. (2014) Prostate MRI: Evaluating tumor volume and apparent diffusion coefficient as surrogate biomarkers for predicting tumor Gleason score. Clin Cancer Res 20(14):3705-3711.
23. Tiwari P, Viswanath S, Kurhanewicz J, Sridhar A, Madabhushi A (2012) Multimodal wavelet embedding representation for data combination (MaWERiC): integrating magnetic resonance imaging and spectroscopy for prostate cancer detection. NMR Biomed 25(4):607-619.
24. Viswanath SE, et al. (2012) 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 36(1):213-224.
25. Moradi M, et al. (2012) Multiparametric MRI maps for detection and grading of dominant prostate tumors. J Magn Reson Imaging 35(6):1403-1413.
26. Tiwari P, Kurhanewicz J, Madabhushi A (2013) Multi-kernel graph embedding for detection, Gleason grading of prostate cancer via MRI/MRS. Med Image Anal 17(2): 219-235.
27. Lambin P, et al. (2012) Radiomics: Extracting more information from medical images using advanced feature analysis. Eur J Cancer 48(4):441-446.
28. Aerts HJ, et al. (2014) Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach. Nat Commun 5:4006.
29. Wibmer A, et al. (2015) Haralick texture analysis of prostate MRI: Differentiating normal prostate from clinically significant prostate cancer and associations with cancer aggressiveness. Eur Radiol 25(10):2840-2850.
30. Fedorov A, et al. (2012) 3D Slicer as an image computing platform for the quantitative imaging network. Magn Reson Imaging 30(9):1323-1341.
31. Haralick RM, Shanmugam K, Dinstein IH (1973) Textural features for image classification. IEEE Trans Syst Man Cybern 3(6):610-321.
32. MATLAB (2014) Version 8.3.0 (R2014a) (MathWorks, Natick, MA).
33. Yoo TS, et al. (2002) Engineering and algorithm design for an image processing Api: A technical report on ITK-the Insight Toolkit. Stud Health Technol Inform 85:586-592.
34. Chawla NV, Japkowicz N, Kotcz A (2004) Editorial: Special issue on learning from imbalanced data sets. ACM SIGKDD Explorations Newsl - Special Issue on Learning from Imbalanced Datasets 6:1-6.
35. Weiss GM (2004) Mining with rarity: A unifying framework. ACM SIGKDD Explorations Newsl - Special Issue on Learning from Imbalanced Datasets 6:7-19.
36. Resnik P, Hardisty E. Gibbs sampling for the uninitiated. College Park (MD): Institute of Advanced Computer Studies, University of Maryland; 2010. Report No.: UMIACS-TR-2010-04.
37. Gosset WS (1908) The probable error of a mean. Biometrika 6(1):1-25.
38. Freund Y, Schapire RE (1996) Experiments with a new boosting algorithm. Proceedings of the 13th International Conference on Machine Learning (ICML1996) (Morgan Kaufmann, San Francisco), pp 148-156.
39. Guyon I, Weston J, Barnhill S, Vapnik V (2002) Gene selection for cancer classification using support vector machines. Mach Learn 46(1):389-422.
40. Rakotomamonjy A (2003) Variable selection using SVM based criteria. J Mach Learn Res 3(1):1357-1370.
41. Tibshirani R, Tibshirani R (2009) A bias correction for the minimum error rate in cross validation. Ann Appl Stat 3(2):822-829.
42. Youden WJ (1950) Index for rating diagnostic tests. Cancer 3(1):32-35.
43. Madabhushi A, Feldman MD, Metaxas DN, Tomaszeweski J, Chute D (2005) Automated detection of prostatic adenocarcinoma from high-resolution ex vivo MRI. IEEE Trans Med Imaging 24(12):1611-1625.
44. Niaf E, Rouvière O, Mège-Lechevallier F, Bratan F, Lartizien C (2012) Computer-aided diagnosis of prostate cancer in the peripheral zone using multiparametric MRI. Phys Med Biol 57(12):3833-3851.
45. Ambroise C, McLachlan GJ (2002) Selection bias in gene extraction on the basis of microarray gene-expression data. Proc Natl Acad Sci USA 99(10):6562-6566.
46. Cawley G, Talbot N (2010) On over-fitting in model selection and subsequent selection bias in performance evaluation. J Mach Learn Res 11(1):2079-2107.
47. Krstajic D, Buturovic L, Leahy D, Thomas S (2014) Cross-validation pitfalls when selecting and assessing regression and classification methods. J Cheminformatics 6(1):1-15.
48. Tsamardinos I, Rakshani A, Lagani V (2014) Performance-estimation properties of cross-validation-based protocols with simultaneous hyper-parameter optimization. Artif Intell: Methods Appls 8445(1):1-14.
49. Kohavi R (1995) A study of cross validation and bootstrap for accuracy estimation and model selection. Proceedings of the 14th International Joint Conference on Artif Intell (IJCAI) (Morgan Kaufmann, San Francisco), Vol 2, pp 1137-1143.
50. Demsar J (2006) Statistical comparisons of classifiers over multiple data sets. J Mach Learn Res 7(1):1-30.