Automatic glioma characterization from dynamic susceptibility contrast imaging: Brain tumor segmentation using knowledge‐based fuzzy clustering

Journal of Magnetic Resonance Imaging - Tập 30 Số 1 - Trang 1-10 - 2009
Kyrre E. Emblem1,2, Bård Nedregaard3, John Hald3, Terje Nome3, Paulina Due‐Tønnessen3, Atle Bjørnerud1,4
1Department of Medical Physics, Rikshospitalet University Hospital, Oslo, Norway
2The Interventional Center, Rikshospitalet University Hospital, Oslo, Norway
3Clinic for Imaging and Intervention, Rikshospitalet University Hospital, Oslo, Norway
4Department of Physics, University of Oslo, Oslo, Norway

Tóm tắt

AbstractPurposeTo assess whether glioma volumes from knowledge‐based fuzzy c‐means (FCM) clustering of multiple MR image classes can provide similar diagnostic efficacy values as manually defined tumor volumes when characterizing gliomas from dynamic susceptibility contrast (DSC) imaging.Materials and MethodsFifty patients with newly diagnosed gliomas were imaged using DSC MR imaging at 1.5 Tesla. To compare our results with manual tumor definitions, glioma volumes were also defined independently by four neuroradiologists. Using a histogram analysis method, diagnostic efficacy values for glioma grade and expected patient survival were assessed.ResultsThe areas under the receiver operator characteristics curves were similar when using manual and automated tumor volumes to grade gliomas (P = 0.576–0.970). When identifying a high‐risk patient group (expected survival <2 years) and a low‐risk patient group (expected survival >2 years), a higher log‐rank value from Kaplan‐Meier survival analysis was observed when using automatic tumor volumes (14.403; P < 0.001) compared with the manual volumes (10.650–12.761; P = 0.001–0.002).ConclusionOur results suggest that knowledge‐based FCM clustering of multiple MR image classes provides a completely automatic, user‐independent approach to selecting the target region for presurgical glioma characterization J. Magn. Reson. Imaging 2009;30:1–10. © 2009 Wiley‐Liss, Inc.

Từ khóa


Tài liệu tham khảo

10.1148/radiol.2392050661

10.1148/radiology.174.2.2153310

10.1148/radiology.170.1.2535765

10.1634/theoncologist.9-5-528

10.1148/radiology.211.3.r99jn46791

Lev MH, 2004, Glial tumor grading and outcome prediction using dynamic spin‐echo MR susceptibility mapping compared with conventional contrast‐enhanced MR: confounding effect of elevated rCBV of oligodendrogliomas, AJNR Am J Neuroradiol, 25, 214

10.1148/radiol.2382042180

10.1227/01.NEU.0000215944.81730.18

10.1148/radiol.2243011014

10.1148/radiol.2473070571

10.1002/jmri.21064

10.1148/radiology.154.1.3964938

10.1080/02841860802290516

10.1142/S0129065797000124

10.1016/S0304-3835(97)00233-4

Zhou J, 2005, Extraction of brain tumor from MR images using one‐class support vector machine, Conf Proc IEEE Eng Med Biol Soc, 6, 6411

10.1080/14639230500077444

10.1109/42.700731

10.1177/096228029700600302

10.1016/S0933-3657(00)00073-7

10.1148/radiology.218.2.r01fe44586

10.1002/mrm.20154

Kleihues P, 2000, Astrocytic tumors & oligodendroglial tumors and mixed gliomas. The WHO classification of tumors of the nervous system, 9

10.1002/mrm.1910140211

10.1002/mrm.1910360510

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

10.1109/42.563664

Schmainda KM, 2004, Characterization of a first‐pass gradient‐echo spin‐echo method to predict brain tumor grade and angiogenesis, AJNR Am J Neuroradiol, 25, 1524

10.1634/theoncologist.11-6-681

10.1016/S0360-3016(02)02869-9

10.1016/B978-0-12-336156-1.50061-6

10.1006/nimg.1997.0290

10.1109/TSMC.1979.4310076

10.1016/j.ijrobp.2004.01.026

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

10.1177/0272989X9101100203

10.1148/radiology.212.3.r99se22811

Law M, 2007, Histogram analysis versus region of interest analysis of dynamic susceptibility contrast perfusion MR imaging data in the grading of cerebral gliomas, AJNR Am J Neuroradiol, 28, 761

Price SJ, 2006, Improved delineation of glioma margins and regions of infiltration with the use of diffusion tensor imaging: an image‐guided biopsy study, AJNR Am J Neuroradiol, 27, 1969

10.1002/mrm.20759

Thông tin
Thông tin xuất bản

Journal of Magnetic Resonance Imaging

Tập 30 Số 1

1-10

Thông tin tác giả