Machine learning in preoperative glioma MRI: Survival associations by perfusion‐based support vector machine outperforms traditional MRI

Journal of Magnetic Resonance Imaging - Tập 40 Số 1 - Trang 47-54 - 2014
Kyrre E. Emblem1,2, Paulina Due‐Tønnessen3, John Hald3, Atle Bjørnerud4,2, Marco C. Pinho1,5, David Scheie6, Lothar R. Schad7, Torstein R. Meling8, Frank G. Zöllner7
1Department of Radiology and Athinoula A. Martinos Center for Biomedical Imaging; Massachusetts General Hospital and Harvard Medical School; Boston Massachusetts USA
2Intervention Centre; Rikshospitalet; Oslo University Hospital; Oslo Norway
3 Department of Radiology, Rikshospitalet, Oslo University Hospital, Oslo, #N#Norway
4Department of Physics, University of Oslo, Oslo, Norway
5Department of Radiology University of Texas Southwestern Medical Center, Dallas, Texas USA
6Department of Pathology, Rikshospitalet, Oslo University Hospital, Oslo, Norway
7Computer Assisted Clinical Medicine, Medical Faculty Mannheim, Heidelberg University, Heidelberg, Germany
8Department of Neurosurgery-Rikshospitalet, Oslo University Hospital, Oslo, Norway

Tóm tắt

PurposeTo retrospectively evaluate the performance of an automatic support vector machine (SVM) routine in combination with perfusion‐based dynamic susceptibility contrast magnetic resonance imaging (DSC‐MRI) for preoperative survival associations in patients with gliomas and compare our results to traditional MRI.Materials and MethodsThe study was approved by the Ethics Committee and informed consent was signed. Structural, diffusion‐ and perfusion‐weighted MRI was performed at 1.5‐T preoperatively in 94 adult patients (49 males, 45 females, 23–82 years; mean 51 years) later diagnosed with a primary glioma. Patients were randomly assigned in training and test datasets and the resulting DSC‐based survival associations by SVM were compared to traditional MRI features including contrast‐agent enhancement, perfusion‐ and diffusion‐weighted imaging, tumor size, and location. The results were adjusted for age, neurological status, and postoperative factors associated with survival, including surgery and adjuvant therapy.ResultsFor 1‐ (26/33 alive, 11/14 deceased), 2‐ (15/21, 21/26), 3‐ (12/16, 27/31) and 4‐ (12/15, 28/32) year survival associations in the test dataset (47 patients), the SVM routine was the only biomarker to consistently associate with survival (Cox; P < 0.001).ConclusionThe automatic machine learning routine presented in our study may provide the operator with a reliable instrument for assessing survival in patients with glioma. J. Magn. Reson. Imaging 2014;40:47–54. © 2013 Wiley Periodicals, Inc.

Từ khóa


Tài liệu tham khảo

10.1148/radiol.2492081429

10.1148/radiol.2473070571

10.1200/JCO.2001.19.2.551

10.1002/mrm.22147

10.1002/jmri.22432

10.1002/mrm.21736

10.1148/radiol.2472070898

10.3171/2010.6.JNS091246

10.1148/radiol.2532081623

10.1148/radiol.2432060450

10.1002/nbm.1091

10.1002/jmri.21064

10.1200/JCO.2010.30.0582

10.1002/mrm.22495

Boxerman JL, 2006, Relative cerebral blood volume maps corrected for contrast agent extravasation significantly correlate with glioma tumor grade, whereas uncorrected maps do not, AJNR Am J Neuroradiol, 27, 859

10.1038/jcbfm.2010.4

10.3174/ajnr.A0993

10.1002/mrm.21944

10.1162/089976601750399335

Vapnik VN, 2005, Universal learning technology: support vector machines, NEC J Advanced Technol, 2, 137

10.1200/JCO.2009.26.3541

10.1016/j.neuroimage.2004.12.034

10.1111/j.1600-0404.2010.01350.x

10.3174/ajnr.A2939

Garzon B, 2011, Multiparametric analysis of magnetic resonance images for glioma grading and patient survival time prediction, Acta Radiol, 46, 686

10.1148/radiol.2471062089

Law M, 2003, Glioma grading: sensitivity, specificity, and predictive values of perfusion MR imaging and proton MR spectroscopic imaging compared with conventional MR imaging, AJNR Am J Neuroradiol, 24, 1989

10.1002/mrm.20886

Hollingworth W, 2006, A systematic literature review of magnetic resonance spectroscopy for the characterization of brain tumors, AJNR Am J Neuroradiol, 27, 1404

Patankar TF, 2005, Is volume transfer coefficient (K (trans)) related to histologic grade in human gliomas?, AJNR Am J Neuroradiol, 26, 2455

Thông tin
Thông tin xuất bản

Journal of Magnetic Resonance Imaging

Tập 40 Số 1

47-54

Thông tin tác giả