Share：
Share this content in WeChat
X
[Chinese][PDF]812144
• Clinical Article •
The value of conventional MRI texture analysis in diagnosing temporal lobe epilepsy by hippocampal sclerosis
MA Xiang-hong  YUAN Guan-qian  XU Zhi-hua  YANG Ben-qiang 

DOI:10.12015/issn.1674-8034.2017.10.003.


[Abstract] Objective: To explore the value of conventional MRI texture analysis in diagnosing temporal lobe epilepsy due to hippocampal sclerosis.Materials and Methods: The oblique coronal T2 FLAIR images of 22 patients with temporal lobe epilepsy and hippocampal sclerosis confirmed by pathology were analyzed by using Mazda software. The feature selection methods included mutual information (MI), Fisher coefficient and classification error probability combined with average correlation coefficients (POE+ACC), Through these methods, the texture features of hippocampus were extracted. Then, four statistical methods were used to distinguish the hippocampal sclerosis side and normal side of the patients that were raw data analysis (Raw Date), the principal component analysis (PCA), linear discriminant analysis (LDA) and nonlinear discriminant analysis (NDA). The results are indicated with misclassification rate. Meanwhile, 2 neuroradiologists also reviewed the MR images of 22 patients. The differences of the results between the two analysis methods were analyzed finally.Results: The misclassification rate was the lowest (2/44, 4.55%) via the FPM selection and NDA statistical method. Furthermore, there were statistically significant differences of the misclassification rate between the texture analysis and neuroradiologists’ analysis (11/44, 25%).Conclusion: Texture analysis of conventional MRI can provide reliable objective basis for the diagnosis of temporal lobe epilepsy due to hippocampal sclerosis.
[Keywords] Epilepsy, temporal lobe；Hippocampal sclerosis；Magnetic resonance imaging；Texture analysis

MA Xiang-hong Dalian Medical University, Dalian 116044, China

YUAN Guan-qian Department of Neurosurgery, Shenyang Military General Hospital, Shenyang 110016, China

XU Zhi-hua Department of Radiology, Shenyang Military General Hospital, Shenyang 110016, China

YANG Ben-qiang* Department of Radiology, Shenyang Military General Hospital, Shenyang 110016, China

*Correspondence to: Yang BQ, E-mail: bqyang888@sina.com

Conflicts of interest   None.

ACKNOWLEDGMENTS  This work was part of Science and Technology Plan Project of Liaoning Province No. 2015305010
Received  2017-07-19
Accepted  2017-09-06
DOI: 10.12015/issn.1674-8034.2017.10.003
DOI:10.12015/issn.1674-8034.2017.10.003.

[1]
Stern JM. Overview of evaluation and treatment guidelines for epilepsy. Curr Treat Options Neurol, 2009, 11(4): 273-284.
[2]
岳伟，张雅静，管雅琳,等.内侧颞叶癫痫患者海马硬化的影像学研究.中国神经精神疾病杂志, 2014, 10(40): 607-611.
[3]
关乐，卢洁，曹燕翔,等.海马硬化致颞叶癫痫的SPECT与MRI研究.中国现代神经疾病杂志, 2015, 11(15): 12.
[4]
喻良，孙红斌.癫痫性脑病.实用医院临床杂志, 2004, 2(1): 24-26.
[5]
Dzienis W, Tarasów E, Kochanowicz J, et al. Utility of computed tomography and selected MR sequences in the diagnostics of patients with partial epileptic attacks. Med Sci Monitor, 2007, 13(1): 49-54.
[6]
艾丛慧，孙学进.磁共振诊断颞叶癫痫的研究进展.医学综述, 2009, 18(15): 2808-2811.
[7]
何明远，刘鹏飞.多模态磁共振成像对颞叶癫痫海马硬化诊断的研究.医学研究杂志, 2015, 44(2): 16-20.
[8]
Castellano G, Bonilha L, Li L M, et al. Texture analysis of medical images. Clin Radio, 2004, 59(12): 1061-1069.
[9]
Zhang Y, Zhu H, Ferrari R, et al. Texture analysis of MR images of minocycline treated MS patients. Lecture Notes in Computer Sci, 2003, 2878(8): 786-793.
[10]
Bonilha L, Kobayashi E, Castellano G, et al. Texture analysis of hippocampal sclerosis. Epilepsia, 2003, 44(12): 1546-1550.
[11]
Yu O, Mauss Y, Namer IJ, et al. Existence of contralateral abnormalities revealed by texture analysis in unilateral intractable hippocampal epilepsy. Magn Reson Imaging, 2001, 19(10):1305-1310.
[12]
Morita ME, Cendes F. Quantitative MRI techniques in MTLE: Toward a better understanding of hippocampal sclerosis. Epilepsia, 2010, 51(S1): 76-79.
[13]
Zacharaki EI, Wang S, Chawla S, et al. Classification of brain tumor type and grade using MRI texture and shape in a machine learning scheme. Magn Reson Med, 2009, 62(6): 1609-1618.
[14]
Orphanidou VE, Vlachos N, Davies NP, et al. Texture analysis of T1 and T2-weighted MR images and use of probabilistic neural network to discriminate posterior fossa tumours in children. NMR in Biomedicine, 2014, 27(6): 632-639.
[15]
Mayerhoefer ME, Schima W, Trattnig S, et al. Texture-based classification of focal liver lesions on MRI at 3.0 Tesla: a feasibility study in cysts and hemangiomas. J Magn Reson Imaging, 2010,32(2): 352-359.
[16]
Mayerhoefer ME, Breitenseher M, Amann G, et al. Are signalintensity and homogeneity useful parameters for distinguishing between benign and malignant soft tissue masses on MR images? Objective evaluation by means of texture analysis. Magn Reson Imaging, 2008, 26(9): 1316-1322.
[17]
张柳，冯永健，陈祥荣,等. MRI与18F-FDG PET/CT对海马硬化的诊断价值.暨南大学学报(自然科学与医学版), 2013, 34(2):216-220.

PREV Comparative study on contrast-enhanced Cube FLAIR and T1WI sequences in craniocerebral diseases
NEXT Voxel-based morphometry MRI primary study of brain grey matter between Tibetan bilinguals and Chinese monolinguals
  


LINK


Tel & Fax: +8610-67113815    E-mail: editor@cjmri.cn