De Novo Radiomics Approach Using Image Augmentation and Features From T1 Mapping to Predict Gleason Scores in Prostate Cancer.
Journal
Investigative radiology
ISSN: 1536-0210
Titre abrégé: Invest Radiol
Pays: United States
ID NLM: 0045377
Informations de publication
Date de publication:
01 10 2021
01 10 2021
Historique:
pubmed:
29
5
2021
medline:
16
10
2021
entrez:
28
5
2021
Statut:
ppublish
Résumé
The aims of this study were to discriminate among prostate cancers (PCa's) with Gleason scores 6, 7, and ≥8 on biparametric magnetic resonance imaging (bpMRI) of the prostate using radiomics and to evaluate the added value of image augmentation and quantitative T1 mapping. Eighty-five patients with subsequently histologically proven PCa underwent bpMRI at 3 T (T2-weighted imaging, diffusion-weighted imaging) with 66 patients undergoing additional T1 mapping at 3 T. The PCa lesions as well as the peripheral and transition zones were segmented pixel by pixel in multiple slices of the 3D MRI data sets (T2-weighted images, apparent diffusion coefficient, and T1 maps). To increase the size of the data set, images were augmented for contrast, brightness, noise, and perspective multiple times, effectively increasing the sample size 10-fold, and 322 different radiomics features were extracted before and after augmentation. Four different machine learning algorithms, including a random forest (RF), stochastic gradient boosting (SGB), support vector machine (SVM), and k-nearest neighbor, were trained with and without features from T1 maps to differentiate among 3 different Gleason groups (6, 7, and ≥8). Support vector machine showed the highest accuracy of 0.92 (95% confidence interval [CI], 0.62-1.00) for classifying the different Gleason scores, followed by RF (0.83; 95% CI, 0.52-0.98), SGB (0.75; 95% CI, 0.43-0.95), and k-nearest neighbor (0.50; 95% CI, 0.21-0.79). Image augmentation resulted in an average increase in accuracy between 0.08 (SGB) and 0.48 (SVM). Removing T1 mapping features led to a decline in accuracy for RF (-0.16) and SGB (-0.25) and a higher generalization error. When data are limited, image augmentations and features from quantitative T1 mapping sequences might help to achieve higher accuracy and lower generalization error for classification among different Gleason groups in bpMRI by using radiomics.
Identifiants
pubmed: 34047538
pii: 00004424-202110000-00008
doi: 10.1097/RLI.0000000000000788
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
661-668Informations de copyright
Copyright © 2021 Wolters Kluwer Health, Inc. All rights reserved.
Déclaration de conflit d'intérêts
Conflicts of interest and sources of funding: none declared.
Références
Pernar CH, Ebot EM, Wilson KM, et al. The epidemiology of prostate cancer. Cold Spring Harb Perspect Med . 2018;8:a030361.
Bray F, Ferlay J, Soerjomataram I, et al. Global cancer statistics 2018: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA Cancer J Clin . 2018;68:394–424.
Lee HH, Shaw NM, Mohammed S, et al. Prostate cancer in men with treated advanced heart failure: should we keep screening? Urology . 2020;136:46–50.
Walsh PC, DeWeese TL, Eisenberger MA. Clinical practice. Localized prostate cancer. N Engl J Med . 2007;357:2696–2705.
Milonas D, Venclovas Ž, Gudinaviciene I, et al. Impact of the 2014 International Society of Urological Pathology grading system on concept of high-risk prostate cancer: comparison of long-term oncological outcomes in patients undergoing radical prostatectomy. Front Oncol . 2019;9:1272.
Carroll PH, Mohler JL. NCCN guidelines updates: prostate cancer and prostate cancer early detection. J Natl Compr Canc Netw . 2018;16:620–623.
Van Poppel H, Joniau S. An analysis of radical prostatectomy in advanced stage and high-grade prostate cancer. Eur Urol . 2008;53:253–259.
Egevad L, Granfors T, Karlberg L, et al. Prognostic value of the Gleason score in prostate cancer. BJU Int . 2002;89:538–542.
Wright JL, Salinas CA, Lin DW, et al. Differences in prostate cancer outcomes between cases with Gleason 4+3 and Gleason 3+4 tumors in a population-based cohort. J Urol . 2009;182:2702–2707.
Epstein JI, Zelefsky MJ, Sjoberg DD, et al. A contemporary prostate cancer grading system: a validated alternative to the Gleason score. Eur Urol . 2016;69:428–435.
Hernandez DJ, Nielsen ME, Han M, et al. Contemporary evaluation of the D'Amico risk classification of prostate cancer. Urology . 2007;70:931–935.
Hassan O, Han M, Zhou A, et al. Incidence of extraprostatic extension at radical prostatectomy with pure Gleason score 3+ 3= 6 (grade group 1) cancer: implications for whether Gleason score 6 prostate cancer should be renamed “not cancer” and for selection criteria for active surveillance. J Urol . 2018;199:1482–1487.
van der Leest M, Cornel E, Israel B, et al. Head-to-head comparison of transrectal ultrasound-guided prostate biopsy versus multiparametric prostate resonance imaging with subsequent magnetic resonance-guided biopsy in biopsy-naïve men with elevated prostate-specific antigen: a large prospective multicenter clinical study. Eur Urol . 2019;75:570–578.
Zhang G-M-Y, Han Y-Q, Wei JW, et al. Radiomics based on MRI as a biomarker to guide therapy by predicting upgrading of prostate cancer from biopsy to radical prostatectomy. J Magn Reson Imaging . 2020;52:1239–1248.
Baur ADJ, Hansen CM, Rogasch J, et al. Evaluation of T1 relaxation time in prostate cancer and benign prostate tissue using a modified Look-Locker inversion recovery sequence. Sci Rep . 2020;10:5249.
Gibbs P, Liney GP, Pickles MD, et al. Correlation of ADC and T2 measurements with cell density in prostate cancer at 3.0 Tesla. Invest Radiol . 2009;44:572–576.
Baur AD, Maxeiner A, Franiel T, et al. Evaluation of the prostate imaging reporting and data system for the detection of prostate cancer by the results of targeted biopsy of the prostate. Invest Radiol . 2014;49:411–420.
Ciris PA, George Chiou J-Y, Glazer DI, et al. Accelerated segmented diffusion-weighted prostate imaging for higher resolution, higher geometric fidelity, and multi-b perfusion estimation. Invest Radiol . 2019;54:238–246.
Adams LC, Brangsch J, Reimann C, et al. Noninvasive imaging of vascular permeability to predict the risk of rupture in abdominal aortic aneurysms using an albumin-binding probe. Sci Rep . 2020;10:3231.
Mai J, Abubrig M, Lehmann T, et al. T2 mapping in prostate cancer. Invest Radiol . 2019;54:146–152.
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.
Nketiah G, Elschot M, Kim E, et al. T2-weighted MRI-derived textural features reflect prostate cancer aggressiveness: preliminary results. Eur Radiol . 2017;27:3050–3059.
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.
Messroghli DR, Radjenovic A, Kozerke S, et al. Modified Look-Locker inversion recovery (MOLLI) for high-resolution T1 mapping of the heart. Magn Reson Med . 2004;52:141–146.
Maxeiner A, Fischer T, Schwabe J, et al. Contrast-enhanced ultrasound (CEUS) and quantitative perfusion analysis in patients with suspicion for prostate cancer. Ultraschall Med . 2019;40:340–348.
Epstein JI, Egevad L, Amin MB, et al. The 2014 International Society of Urological Pathology (ISUP) consensus conference on Gleason grading of prostatic carcinoma. Am J Surg Pathol . 2016;40:244–252.
Tustison NJ, Avants BB, Cook PA, et al. N4ITK: improved N3 bias correction. IEEE Trans Med Imaging . 2010;29:1310–1320.
Van Griethuysen JJM, Fedorov A, Parmar C, et al. Computational radiomics system to decode the radiographic phenotype. Cancer Res . 2017;77:e104–e107.
Lowekamp BC, Chen DT, Ibáñez L, et al. The design of SimpleITK. Front Neuroinform . 2013;7:45.
Howard J, Gugger S. Fastai: a layered API for deep learning. Information . 2020;11:108.
Paszke A, Gross S, Massa F, et al. Pytorch: an imperative style, high-performance deep learning library. Adv Neural Inf Process Syst . 2019;8026–8037.
R Core Team. R: A Language and Environment for Statistical Computing . Vienna, Austria: R Foundation for Statistical Computing; 2014. Available at: http://www.R-project.org/ . Accessed April 10, 2021.
Wickham H. The tidyverse. R package ver. 1.1. 2017;1.
Robin X, Turck N, Hainard A, et al. pROC: an open-source package for R and S+ to analyze and compare ROC curves. BMC Bioinformatics . 2011;12:77.
Mikołajczyk A, Grochowski M. Data augmentation for improving deep learning in image classification problem. 2018 international interdisciplinary PhD workshop (IIPhDW). IEEE . 2018;117–122.
Taylor AJ, Salerno M, Dharmakumar R, et al. T1 mapping: basic techniques and clinical applications. JACC Cardiovasc Imaging . 2016;9:67–81.
Panda A, O'Connor G, Lo W-C, et al. Targeted biopsy validation of peripheral zone prostate cancer characterization with MR fingerprinting and diffusion mapping. Invest Radiol . 2019;54:485–493.
Fehr D, Veeraraghavan H, Wibmer A, et al. Automatic classification of prostate cancer Gleason scores from multiparametric magnetic resonance images. Proc Natl Acad Sci . 2015;112:E6265–E6273.
Resnik P, Hardisty E. Gibbs Sampling for the Uninitiated . College Park, MD: Institute for Advanced Computer Studies; 2010.
Van Ravenzwaaij D, Cassey P, Brown SD. A simple introduction to Markov Chain Monte-Carlo sampling. Psychon Bull Rev . 2018;25:143–154.
Gong L, Xu M, Fang M, et al. Noninvasive prediction of high-grade prostate cancer via biparametric MRI radiomics. J Magn Reson Imaging . 2020;52:1102–1109.
Chowdhury MZI, Turin TC. Variable selection strategies and its importance in clinical prediction modelling. Fam Med Community Health . 2020;8:e000262.
Chaddad A, Kucharczyk MJ, Niazi T. Multimodal radiomic features for the predicting gleason score of prostate cancer. Cancer . 2018;10:249.
Krizhevsky A, Sutskever I, Hinton GE. Imagenet classification with deep convolutional neural networks. Commun ACM . 2017;60:84–90.
Andren O, Fall K, Franzen L, et al. How well does the Gleason score predict prostate cancer death? A 20-year followup of a population based cohort in Sweden. J Urol . 2006;175:1337–1340.
Mottet N, Bellmunt J, Bolla M, et al. EAU-ESTRO-SIOG Guidelines on Prostate Cancer. Part 1: screening, diagnosis, and local treatment with curative intent. Eur Urol . 2017;71:618–629.
Arif M, Schoots IG, Castillo Tovar J, et al. Clinically significant prostate cancer detection and segmentation in low-risk patients using a convolutional neural network on multi-parametric MRI. Eur Radiol . 2020;30:6582–6592.
Stark JR, Perner S, Stampfer MJ, et al. Gleason score and lethal prostate cancer: does 3 + 4 = 4 + 3? J Clin Oncol . 2009;27:3459–3464.
Rosenkrantz AB, Triolo MJ, Melamed J, et al. Whole-lesion apparent diffusion coefficient metrics as a marker of percentage Gleason 4 component within Gleason 7 prostate cancer at radical prostatectomy. J Magn Reson Imaging . 2015;41:708–714.
Loeb S, Vellekoop A, Ahmed HU, et al. Systematic review of complications of prostate biopsy. Eur Urol . 2013;64:876–992.
Maas MC, Litjens GJ, Wright AJ, et al. A single-arm, multicenter validation study of prostate cancer localization and aggressiveness with a quantitative multiparametric magnetic resonance imaging approach. Invest Radiol . 2019;54:437–447.