MRI Radiomics for the Prediction of Fuhrman Grade in Clear Cell Renal Cell Carcinoma: a Machine Learning Exploratory Study.
Fuhrman grade
MRI
Machine learning
Radiomics
Renal cell carcinoma
Journal
Journal of digital imaging
ISSN: 1618-727X
Titre abrégé: J Digit Imaging
Pays: United States
ID NLM: 9100529
Informations de publication
Date de publication:
08 2020
08 2020
Historique:
pubmed:
22
4
2020
medline:
17
8
2021
entrez:
22
4
2020
Statut:
ppublish
Résumé
The Fuhrman nuclear grade is a recognized prognostic factor for patients with clear cell renal cell carcinoma (CCRCC) and its pre-treatment evaluation significantly affects decision-making in terms of management. In this study, we aimed to assess the feasibility of a combined approach of radiomics and machine learning based on MR images for a non-invasive prediction of Fuhrman grade, specifically differentiation of high- from low-grade tumor and grade assessment. Images acquired on a 3-Tesla scanner (T2-weighted and post-contrast) from 32 patients (20 with low-grade and 12 with high-grade tumor) were annotated to generate volumes of interest enclosing CCRCC lesions. After image resampling, normalization, and filtering, 2438 features were extracted. A two-step feature reduction process was used to between 1 and 7 features depending on the algorithm employed. A J48 decision tree alone and in combination with ensemble learning methods were used. In the differentiation between high- and low-grade tumors, all the ensemble methods achieved an accuracy greater than 90%. On the other end, the best results in terms of accuracy (84.4%) in the assessment of tumor grade were achieved by the random forest. These evidences support the hypothesis that a combined radiomic and machine learning approach based on MR images could represent a feasible tool for the prediction of Fuhrman grade in patients affected by CCRCC.
Identifiants
pubmed: 32314070
doi: 10.1007/s10278-020-00336-y
pii: 10.1007/s10278-020-00336-y
pmc: PMC7522138
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
879-887Références
R.L. Siegel, K.D. Miller, A. Jemal, Cancer statistics, 2019, CA. Cancer J. Clin. 69 (2019) 7–34. https://doi.org/10.3322/caac.21551 .
doi: 10.3322/caac.21551
pubmed: 30620402
A. Znaor, J. Lortet-Tieulent, M. Laversanne, A. Jemal, F. Bray, International variations and trends in renal cell carcinoma incidence and mortality, Eur. Urol. 67 (2015) 519–530. https://doi.org/10.1016/j.eururo.2014.10.002 .
doi: 10.1016/j.eururo.2014.10.002
pubmed: 25449206
K. Sasaguri, N. Takahashi, CT and MR imaging for solid renal mass characterization, Eur. J. Radiol. 99 (2018) 40–54. https://doi.org/10.1016/j.ejrad.2017.12.008 .
doi: 10.1016/j.ejrad.2017.12.008
pubmed: 29362150
H. Lang, V. Lindner, M. de Fromont, V. Molinié, H. Letourneux, N. Meyer, M. Martin, D. Jacqmin, Multicenter determination of optimal interobserver agreement using the Fuhrman grading system for renal cell carcinoma, Cancer. 103 (2005) 625–629. https://doi.org/10.1002/cncr.20812 .
doi: 10.1002/cncr.20812
pubmed: 15611969
B. Delahunt, Advances and controversies in grading and staging of renal cell carcinoma, Mod. Pathol. 22 (2009) S24–S36. https://doi.org/10.1038/modpathol.2008.183 .
doi: 10.1038/modpathol.2008.183
pubmed: 19494851
A. Becker, D. Hickmann, J. Hansen, C. Meyer, M. Rink, M. Schmid, C. Eichelberg, K. Strini, T. Chromecki, J. Jesche, M. Regier, M. Randazzo, D. Tilki, S. Ahyai, R. Dahlem, M. Fisch, R. Zigeuner, F.K.H. Chun, Critical analysis of a simplified Fuhrman grading scheme for prediction of cancer specific mortality in patients with clear cell renal cell carcinoma – impact on prognosis, Eur. J. Surg. Oncol. 42 (2016) 419–425. https://doi.org/10.1016/j.ejso.2015.09.023 .
doi: 10.1016/j.ejso.2015.09.023
pubmed: 26520403
L. Marconi, S. Dabestani, T.B. Lam, F. Hofmann, F. Stewart, J. Norrie, A. Bex, K. Bensalah, S.E. Canfield, M. Hora, M.A. Kuczyk, A.S. Merseburger, P.F.A. Mulders, T. Powles, M. Staehler, B. Ljungberg, A. Volpe, Systematic review and meta-analysis of diagnostic accuracy of percutaneous renal tumour biopsy, Eur. Urol. 69 (2016) 660–673. https://doi.org/10.1016/j.eururo.2015.07.072 .
doi: 10.1016/j.eururo.2015.07.072
pubmed: 26323946
A. Volpe, K. Mattar, A. Finelli, J.R. Kachura, A.J. Evans, W.R. Geddie, M.A.S. Jewett, Contemporary results of percutaneous biopsy of 100 small renal masses: a single center experience, J. Urol. 180 (2008) 2333–2337. https://doi.org/10.1016/j.juro.2008.08.014 .
doi: 10.1016/j.juro.2008.08.014
pubmed: 18930274
C. Parada Villavicencio, R.J. Mc Carthy, F.H. Miller, Can diffusion-weighted magnetic resonance imaging of clear cell renal carcinoma predict low from high nuclear grade tumors, Abdom. Radiol. 42 (2017) 1241–1249. https://doi.org/10.1007/s00261-016-0981-7 .
doi: 10.1007/s00261-016-0981-7
Y. Deng, E. Soule, A. Samuel, S. Shah, E. Cui, M. Asare-Sawiri, C. Sundaram, C. Lall, K. Sandrasegaran, CT texture analysis in the differentiation of major renal cell carcinoma subtypes and correlation with Fuhrman grade., Eur. Radiol. (2019). https://doi.org/10.1007/s00330-019-06260-2 .
Z. Feng, Q. Shen, Y. Li, Z. Hu, CT texture analysis: a potential tool for predicting the Fuhrman grade of clear-cell renal carcinoma, Cancer Imaging. 19 (2019) 6. https://doi.org/10.1186/s40644-019-0195-7 .
doi: 10.1186/s40644-019-0195-7
pubmed: 30728073
pmcid: 6364463
J. Ding, Z. Xing, Z. Jiang, J. Chen, L. Pan, J. Qiu, W. Xing, CT-based radiomic model predicts high grade of clear cell renal cell carcinoma, Eur. J. Radiol. 103 (2018) 51–56. https://doi.org/10.1016/j.ejrad.2018.04.013 .
doi: 10.1016/j.ejrad.2018.04.013
pubmed: 29803385
J. Shu, Y. Tang, J. Cui, R. Yang, X. Meng, Z. Cai, J. Zhang, W. Xu, D. Wen, H. Yin, Clear cell renal cell carcinoma: CT-based radiomics features for the prediction of Fuhrman grade., Eur. J. Radiol. 109 (2018) 8–12. https://doi.org/10.1016/j.ejrad.2018.10.005 .
doi: 10.1016/j.ejrad.2018.10.005
pubmed: 30527316
C.T. Bektas, B. Kocak, A.H. Yardimci, M.H. Turkcanoglu, U. Yucetas, S.B. Koca, C. Erdim, O. Kilickesmez, Clear cell renal cell carcinoma: machine learning-based quantitative computed tomography texture analysis for prediction of Fuhrman nuclear grade, Eur. Radiol. 29 (2019) 1153–1163. https://doi.org/10.1007/s00330-018-5698-2 .
doi: 10.1007/s00330-018-5698-2
pubmed: 30167812
B. Kocak, E.S. Durmaz, E. Ates, O.K. Kaya, O. Kilickesmez, Unenhanced CT texture analysis of clear cell renal cell carcinomas: a machine learning–based study for predicting histopathologic nuclear grade, Am. J. Roentgenol. 212 (2019) W132–W139. https://doi.org/10.2214/AJR.18.20742 .
doi: 10.2214/AJR.18.20742
F. Lin, E.-M. Cui, Y. Lei, L. Luo, CT-based machine learning model to predict the Fuhrman nuclear grade of clear cell renal cell carcinoma, Abdom. Radiol. 44 (2019) 2528–2534. https://doi.org/10.1007/s00261-019-01992-7 .
doi: 10.1007/s00261-019-01992-7
K.M. Krajewski, A.B. Shinagare, Novel imaging in renal cell carcinoma, Curr. Opin. Urol. 26 (2016) 388–395. https://doi.org/10.1097/MOU.0000000000000314 .
doi: 10.1097/MOU.0000000000000314
pubmed: 27262139
F. Alessandrino, A.B. Shinagare, D. Bossé, T.K. Choueiri, K.M. Krajewski, Radiogenomics in renal cell carcinoma, Abdom. Radiol. 44 (2019) 1990–1998. https://doi.org/10.1007/s00261-018-1624-y .
doi: 10.1007/s00261-018-1624-y
R. Thomas, L. Qin, F. Alessandrino, S.P. Sahu, P.J. Guerra, K.M. Krajewski, A. Shinagare, A review of the principles of texture analysis and its role in imaging of genitourinary neoplasms, Abdom. Radiol. 44 (2019) 2501–2510. https://doi.org/10.1007/s00261-018-1832-5 .
doi: 10.1007/s00261-018-1832-5
R.J. Gillies, P.E. Kinahan, H. Hricak, Radiomics: images are more than pictures, they are data. Radiology. 278 (2016) 563–77. https://doi.org/10.1148/radiol.2015151169 .
doi: 10.1148/radiol.2015151169
pubmed: 26579733
M. Imbriaco, R. Cuocolo, Does texture analysis of MR images of breast tumors help predict response to treatment?, Radiology. 286 (2018) 421–423. https://doi.org/10.1148/radiol.2017172454 .
doi: 10.1148/radiol.2017172454
pubmed: 29356631
R. Cuocolo, A. Stanzione, A. Ponsiglione, V. Romeo, F. Verde, M. Creta, R. La Rocca, N. Longo, L. Pace, M. Imbriaco, Clinically significant prostate cancer detection on MRI: a radiomic shape features study, Eur. J. Radiol. 116 (2019) 144–149. https://doi.org/10.1016/j.ejrad.2019.05.006 .
doi: 10.1016/j.ejrad.2019.05.006
pubmed: 31153556
M. Zhou, J. Scott, B. Chaudhury, L. Hall, D. Goldgof, K.W. Yeom, M. Iv, Y. Ou, J. Kalpathy-Cramer, S. Napel, R. Gillies, O. Gevaert, R. Gatenby, Radiomics in brain tumor: image assessment, quantitative feature descriptors, and machine-learning approaches, Am. J. Neuroradiol. 39 (2018) 208–216. https://doi.org/10.3174/ajnr.A5391 .
doi: 10.3174/ajnr.A5391
pubmed: 28982791
V. Romeo, S. Maurea, R. Cuocolo, M. Petretta, P.P. Mainenti, F. Verde, M. Coppola, S. Dell’Aversana, A. Brunetti, Characterization of adrenal lesions on unenhanced MRI using texture analysis: a machine-learning approach, J. Magn. Reson. Imaging. 48 (2018) 198–204. https://doi.org/10.1002/jmri.25954 .
doi: 10.1002/jmri.25954
pubmed: 29341325
Z. Feng, P. Rong, P. Cao, Q. Zhou, W. Zhu, Z. Yan, Q. Liu, W. Wang, Machine learning-based quantitative texture analysis of CT images of small renal masses: differentiation of angiomyolipoma without visible fat from renal cell carcinoma, Eur. Radiol. 28 (2018) 1625–1633. https://doi.org/10.1007/s00330-017-5118-z .
doi: 10.1007/s00330-017-5118-z
pubmed: 29134348
A. Stanzione, R. Cuocolo, S. Cocozza, V. Romeo, F. Persico, F. Fusco, N. Longo, A. Brunetti, M. Imbriaco, Detection of extraprostatic extension of cancer on biparametric MRI combining texture analysis and machine learning: preliminary results, Acad. Radiol. (2019). https://doi.org/10.1016/j.acra.2018.12.025 .
P.A. Yushkevich, J. Piven, H.C. Hazlett, R.G. Smith, S. Ho, J.C. Gee, G. Gerig, User-guided 3D active contour segmentation of anatomical structures: significantly improved efficiency and reliability, Neuroimage. 31 (2006) 1116–1128. https://doi.org/10.1016/j.neuroimage.2006.01.015 .
doi: 10.1016/j.neuroimage.2006.01.015
pubmed: 16545965
J.J.M. van Griethuysen, A. Fedorov, C. Parmar, A. Hosny, N. Aucoin, V. Narayan, R.G.H. Beets-Tan, J.-C. Fillion-Robin, S. Pieper, H.J.W.L. Aerts, Computational radiomics system to decode the radiographic phenotype, Cancer Res. 77 (2017) e104–e107. https://doi.org/10.1158/0008-5472.CAN-17-0339 .
doi: 10.1158/0008-5472.CAN-17-0339
pubmed: 29092951
pmcid: 5672828
V. Romeo, C. Ricciardi, R. Cuocolo, A. Stanzione, F. Verde, L. Sarno, G. Improta, P.P. Mainenti, M. D’Armiento, A. Brunetti, S. Maurea, Machine learning analysis of MRI-derived texture features to predict placenta accreta spectrum in patients with placenta previa, Magn. Reson. Imaging. (2019). https://doi.org/10.1016/j.mri.2019.05.017 .
M.R. Berthold, N. Cebron, F. Dill, T.R. Gabriel, T. Kötter, T. Meinl, P. Ohl, K. Thiel, B. Wiswedel, KNIME - the Konstanz information miner, ACM SIGKDD Explor. Newsl. 11 (2009) 26. https://doi.org/10.1145/1656274.1656280 .
doi: 10.1145/1656274.1656280
T. Mannarino, R. Assante, C. Ricciardi, E. Zampella, C. Nappi, V. Gaudieri, C.G. Mainolfi, E. Di Vaia, M. Petretta, M. Cesarelli, A. Cuocolo, W. Acampa, Head-to-head comparison of diagnostic accuracy of stress-only myocardial perfusion imaging with conventional and cadmium-zinc telluride single-photon emission computed tomography in women with suspected coronary artery disease, J. Nucl. Cardiol. (2019). https://doi.org/10.1007/s12350-019-01789-7 .
S.I. Dimitriadis, D. Liparas, M.N. Tsolaki, Random forest feature selection, fusion and ensemble strategy: combining multiple morphological MRI measures to discriminate among healhy elderly, MCI, cMCI and alzheimer’s disease patients: from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) data, J. Neurosci. Methods. 302 (2018) 14–23. https://doi.org/10.1016/j.jneumeth.2017.12.010 .
doi: 10.1016/j.jneumeth.2017.12.010
pubmed: 29269320
N. V. Chawla, K.W. Bowyer, L.O. Hall, W.P. Kegelmeyer, SMOTE: Synthetic Minority Over-sampling Technique, J. Artif. Intell. Res. 16 (2002) 321–357. https://doi.org/10.1613/jair.953 .
doi: 10.1613/jair.953
R. Kohavi, D. Sommerfield, Feature subset selection using the Wrapper method: overfitting and dynamic search space topology, Knowl. Discov. Data Min. (1995).
H. M, S. M.N, A review on evaluation metrics for data classification evaluations, Int. J. Data Min. Knowl. Manag. Process. 5 (2015) 01–11. https://doi.org/10.5121/ijdkp.2015.5201 .
N. Bhargava, G. Sharma, R. Bhargava, M. Mathuria, Decision tree analysis on J48 algorithm for data mining, Proc. Int. J. Adv. Res. Comput. Sci. Softw. Eng. (2013).
T.G. Dietterich, An experimental comparison of three methods for constructing ensembles of decision trees: bagging, boosting, and randomization, Mach. Learn. 40 (2000) 139–157.
doi: 10.1023/A:1007607513941
L. Breiman, Random forests, Mach. Learn. 45 (2001) 5–32.
doi: 10.1023/A:1010933404324
M. Pal, Ensemble learning with decision tree for remote sensing classification, World Acad. Sci. Eng. Technol. 36 (2007) 258–260.
H. Yu, J. Scalera, M. Khalid, A.-S. Touret, N. Bloch, B. Li, M.M. Qureshi, J.A. Soto, S.W. Anderson, Texture analysis as a radiomic marker for differentiating renal tumors, Abdom. Radiol. 42 (2017) 2470–2478. https://doi.org/10.1007/s00261-017-1144-1 .
doi: 10.1007/s00261-017-1144-1
S.P. Raman, Y. Chen, J.L. Schroeder, P. Huang, E.K. Fishman, CT texture analysis of renal masses, Acad. Radiol. 21 (2014) 1587–1596. https://doi.org/10.1016/j.acra.2014.07.023 .
doi: 10.1016/j.acra.2014.07.023
pubmed: 25239842
pmcid: 4352301
B. Kocak, A.H. Yardimci, C.T. Bektas, M.H. Turkcanoglu, C. Erdim, U. Yucetas, S.B. Koca, O. Kilickesmez, Textural differences between renal cell carcinoma subtypes: machine learning-based quantitative computed tomography texture analysis with independent external validation, Eur. J. Radiol. 107 (2018) 149–157. https://doi.org/10.1016/j.ejrad.2018.08.014 .
doi: 10.1016/j.ejrad.2018.08.014
pubmed: 30292260
G.-M.-Y. Zhang, B. Shi, H.-D. Xue, B. Ganeshan, H. Sun, Z.-Y. Jin, Can quantitative CT texture analysis be used to differentiate subtypes of renal cell carcinoma?, Clin. Radiol. 74 (2019) 287–294. https://doi.org/10.1016/j.crad.2018.11.009 .
doi: 10.1016/j.crad.2018.11.009
pubmed: 30554807
U.N. Hoang, S. Mojdeh Mirmomen, O. Meirelles, J. Yao, M. Merino, A. Metwalli, W. Marston Linehan, A.A. Malayeri, Assessment of multiphasic contrast-enhanced MR textures in differentiating small renal mass subtypes, Abdom. Radiol. 43 (2018) 3400–3409. https://doi.org/10.1007/s00261-018-1625-x .
doi: 10.1007/s00261-018-1625-x
H. Li, A. Li, H. Zhu, Y. Hu, J. Li, L. Xia, D. Hu, I.R. Kamel, Z. Li, Whole-tumor quantitative apparent diffusion coefficient histogram and texture analysis to differentiation of minimal fat angiomyolipoma from clear cell renal cell carcinoma, Acad. Radiol. 26 (2019) 632–639. https://doi.org/10.1016/j.acra.2018.06.015 .
doi: 10.1016/j.acra.2018.06.015
pubmed: 30087067
C.L. Vendrami, Y.S. Velichko, F.H. Miller, A. Chatterjee, C.P. Villavicencio, V. Yaghmai, R.J. McCarthy, Differentiation of papillary renal cell carcinoma subtypes on MRI: qualitative and texture analysis, Am. J. Roentgenol. 211 (2018) 1234–1245. https://doi.org/10.2214/AJR.17.19213 .
doi: 10.2214/AJR.17.19213
A.S. Kierans, H. Rusinek, A. Lee, M.B. Shaikh, M. Triolo, W.C. Huang, H. Chandarana, Textural differences in apparent diffusion coefficient between low- and high-stage clear cell renal cell carcinoma, Am. J. Roentgenol. 203 (2014) W637–W644. https://doi.org/10.2214/AJR.14.12570 .
doi: 10.2214/AJR.14.12570
M.A. Haider, A. Vosough, F. Khalvati, A. Kiss, B. Ganeshan, G.A. Bjarnason, CT texture analysis: a potential tool for prediction of survival in patients with metastatic clear cell carcinoma treated with sunitinib, Cancer Imaging. 17 (2017) 4. https://doi.org/10.1186/s40644-017-0106-8 .
doi: 10.1186/s40644-017-0106-8
pubmed: 28114978
pmcid: 5259868
F. Abramovich, M. Pensky, Classification with many classes: challenges and pluses, (2015). http://arxiv.org/abs/1506.01567 .
A. Fernandez, S. Garcia, F. Herrera, N. V. Chawla, SMOTE for learning from imbalanced data: progress and challenges, marking the 15-year anniversary, J. Artif. Intell. Res. 61 (2018) 863–905. https://doi.org/10.1613/jair.1.11192 .
doi: 10.1613/jair.1.11192
D. Lv, Z. Ma, S. Yang, X. Li, Z. Ma, F. Jiang, The application of SMOTE algorithm for unbalanced data, in: Proc. 2018 Int. Conf. Artif. Intell. Virtual Real. - AIVR 2018, ACM Press, New York, New York, USA, 2018: pp. 10–13. https://doi.org/10.1145/3293663.3293686 .
B. Kocak, E.S. Durmaz, O.K. Kaya, E. Ates, O. Kilickesmez, Reliability of single-slice–based 2D CT texture analysis of renal masses: influence of intra- and interobserver manual segmentation variability on radiomic feature reproducibility, Am. J. Roentgenol. 213 (2019) 377–383. https://doi.org/10.2214/AJR.19.21212 .
doi: 10.2214/AJR.19.21212
B. Kocak, E. Ates, E.S. Durmaz, M.B. Ulusan, O. Kilickesmez, Influence of segmentation margin on machine learning–based high-dimensional quantitative CT texture analysis: a reproducibility study on renal clear cell carcinomas, Eur. Radiol. (2019). https://doi.org/10.1007/s00330-019-6003-8 .