Share：
Share this content in WeChat
X
[Chinese][PDF]74475
• Clinical Article •
Diagnostic value of texture analysis based on diffusion tensor imaging in Parkinson's disease
GU Huifang  DAI Hui 

Cite this article as: Gu HF, Dai H. Diagnostic value of texture analysis based on diffusion tensor imaging in Parkinson's disease[J]. Chin J Magn Reson Imaging, 2021, 12(11): 1-6. DOI:10.12015/issn.1674-8034.2021.11.001.


[Abstract] Objective To investigate the diagnostic value of texture analysis of gray matter nuclei and white matter on diffusion tensor imaging (DTI) in Parkinson's disease (PD) and its correlation with the development of PD. Meterials and Methods: Thirty PD patients and 22 normal controls were prospectively collected for DTI scanning. The fractional anisotropy (FA) diagrams of the two groups were obtained by post-processing. The regions of interest (ROI), including bilateral caudate head, globus pallidus, putamen, substantia nigra, red nucleus, dentate nucleus and centrum semiovale, were delineated by ITK-SNAP software. The texture features were extracted by A.K software. The Mann Whitney U test,Univariate logistic regression analysis,mRMR (maximum relevance minimum redundancy) was applied to select 5 texture features with the highest joint diagnostic efficiency, and random forest (RF) was constructed. Receiver operating characteristic (ROC) curve analysis was used to evaluate the diagnostic efficiency of the model; besides, the cross-validation method was employed to verify the reliability of the model. In addition. The texture features obtained by dimensionality reduction were analyzed by Pearson correlation with mini mental state examination (MMSE), unified Parkinson's Disease Rating Scale (UPDRS) and course of disease, and Spearman correlation with Hoehn-Yahr (H-Y) stages.Results Five texture features were obtained after dimensionality reduction, and AUC (area under the curve) of independent prediction of Parkinson's disease was ranging from 0.692 to 0.871 by ROC analysis. The AUC, accuracy, sensitivity and specificity of the Parkinson's disease prediction model were 0.92, 0.86, 0.89, 0.84, respectively. The accuracy, sensitivity and specificity of cross-validation were 0.89, 0.84, 0.94, respectively. No significant correlation was found between the five texture features and the clinical scale of disease.Conclusions Texture analysis based on DTI has a high diagnostic value for PD. However, the value for evaluating the disease development is limited.
[Keywords] magnetic resonance imaging；Parkinson's disease；diffusion tensor imaging；texture analysis；random forest

GU Huifang1   DAI Hui2, 3, 4*  

1 Department of Radiology, Jiangyin people's Hospital of Jiangsu Province, Jiangyin 214400, China

2 Department of Radiology, the First Affiliated Hospital of Soochow University, Suzhou 215006, China

3 Institute of Medical Imaging, Soochow University, Suzhou 215006, China

4 Suzhou Key Laboratory of Intelligent Medicine and Equipment, Suzhou 215123, China

Dai H, E-mail: huizi198208@126.com

Conflicts of interest   None.

ACKNOWLEDGMENTS National Natural Science Foundation of China (No. 81971573) and the Suzhou Gusu Medical Youth Talent (No.GSWS2020019).
Received  2021-06-04
Accepted  2021-07-13
DOI: 10.12015/issn.1674-8034.2021.11.001
Cite this article as: Gu HF, Dai H. Diagnostic value of texture analysis based on diffusion tensor imaging in Parkinson's disease[J]. Chin J Magn Reson Imaging, 2021, 12(11): 1-6. DOI:10.12015/issn.1674-8034.2021.11.001.

[1]
Liu WX, Lu P, Zhang XB, et al. Clinical application of magnetic resonance NODDI in the diagnosis of putamen disease in patients with Parkinson's disease[J]. Chin J Magn Reson Imaging, 2020, 11(8): 610-614. DOI: 10.12015/issn.1674-8034.2020.08.003.
[2]
Braak H, Del Tredici K. Neuropathological staging of brain pathology in sporadic Parkinson's disease: separating the wheat from the chaff[J]. J Parkinsons Dis, 2017, 7(s1): S71-85. DOI: 10.3233/JPD-179001.
[3]
Atkinson-Clement C, Pinto S, Eusebio A, et al. Diffusion tensor imaging in Parkinson's disease: review and Meta-analysis[J]. Neuroimage: Clin, 2017, 16: 98-110. DOI: 10.1016/j.nicl.2017.07.011.
[4]
Si HN, Tian YL, Wang XC, et al.Comparative study of diffusion kurtosis imaging in deep brain nucleus in different subtypes of Parkinson's disease[J]. Chin J Neurol, 2019, 52(5): 379-386. DOI: 10.3760/cma.j.issn.1006-7876.2019.05.004.
[5]
Ji GJ, Hu PP, Liu TT, et al. Functional connectivity of the cortico-basal Ganglia-thalamocortical network in parkinson disease: a systematic review and meta-analysis with cross-validation[J]. Radiology, 2018, 287(3): 973-982. DOI: 10.1148/radiol.2018172183.
[6]
Luo CY, Song W, Chen Q, et al. White matter microstructure damage in tremor-dominant Parkinson's disease patients[J]. Neuroradiology, 2017, 59(7): 691-698. DOI: 10.1007/s00234-017-1846-7.
[7]
Ma DH, Liu CC , Huang XP, et al. Clinical application of MR neurite orientation dispersion and density imaging technique to the changes of cerebellar dentate nucleus in patients with Parkinson's disease[J]. J Mol Imaging, 2021, 44(1): 22-26. DOI: 10.12122/j.issn.1674-4500.2021.01.04.
[8]
Le HB, Zeng WK, Zhang HH, et al. Mean apparent propagator MRI is better than conventional diffusion tensor imaging for the evaluation of Parkinson's disease: a prospective pilot study[J]. Front Aging Neurosci, 2020, 12: 563-595. DOI: 10.3389/fnagi.2020.563595.
[9]
Jiang MF, Niu GM, Yun Q, et al. Application of diffusion tensor imaging in early diagnosis of Parkinson's disease[J]. J Pract Radiol, 2015, 31(12): 1937-1941. DOI: 10.3969/j.issn.1002-1671.2015.12.002.
[10]
He JX, Wan Q, Yu JX, et al. Application of magnetic resonance diffusion tensor imaging in diagnosis of Parkinson's disease[J]. Modern Hospital, 2017, 17(11): 1708-1709, 1716. DOI: 10.3969/j.issn.1671-332X.2017.11.043.
[11]
Wang B, Ma S, Gong XR, et al. Diffusion kurtosis imaging characteristics of brain gray matter nucleus microstructure in Parkinson's disease with different movement disorder subtypes[J]. Chin J Behav Med & Brain Sci, 2019, 28(10): 875-880. DOI: 10.3760/cma.j.issn.1674-6554.2019.10.003.
[12]
Liu Y, Wang H, Ma JX. MR the value of diffusion tensor diffusion kurtosis imaging in the diagnosis of Parkinson's disease[J]. J Med Imaging, 2020, 30(3): 358-362.
[13]
Hu D, Wang B, Wu KH, et al. Diagnostic value of diffusion kurtosis imaging on microstructural changes of deep brain nuclei in patients with tremor-dominant Parkinson's disease[J]. Radiol Pract, 2020, 35(8): 999-1004. DOI: 10.1360/j.cnki.1000-0313.2020.08.009.
[14]
Xu JG, Song QW, Shen Y, et al. Application of brain white matter radiomics signature based on machine learning in prediction of early-stage Parkinson's disease[J]. Zhejiang Med J, 2020, 42(18): 1954-1959, 1964. DOI: 10.12056/j.issn.1006-2785.2020.42.18.2020-3211.
[15]
Heinrichs-Graham E, Santamaria PM, Gendelman HE, et al. The cortical signature of symptom laterality in Parkinson's disease[J]. Neurolmage Clin, 2017, 14: 433-440. DOI: 10.1016/j.nicl.2017.02.010.
[16]
Tian Y. The tumor texture analysis and its clinical application based on multi-scale wavelet transform[D]. Jinan: Shandong Normal University, 2015: 1-51.
[17]
Calvo FA, Sole CV, de la Mata D, et al. (18)F-FDG PET/CT-based treatment responseevaluation in locally advanced rectal cancer:a prospective validation of long-term outcomes[J]. Eur J Nucl Med Mol Imaging, 2013, 40(5): 657-667. DOI: 10.1007/s00259-013-2341-y.
[18]
Shi WY, Zhou LX, Peng XQ, et al. HIV-infected patients with opportunistic pulmonary infections misdiagnosed as lung cancers: the clinicoradiologic features and initial application of CT radiomics[J]. J Thorac Dis, 2019, 11(6): 2274-2286. DOI: 10.21037/jtd.2019.06.22.
[19]
Li GY, Zhai GQ, Zhao XX, et al. 3D texture analyses within the substantia nigra of Parkinson's disease patients on quantitative susceptibility maps and R2* maps[J]. Neuroimage, 2019, 188:465-472. DOI: 10.1016/j.neuroimage.2018.12.041.
[20]
Liu PS, Zheng SL, Wang H, et al. Diagnosis of conventional T2 FLAIR sequence autoregressive model texture analysis in Parkinson's disease[J], Chin J Med Imaging, 2019, 27 (2): 107-111. DOI: 10.3969/j.issn.1005-5185.2019.02.006.
[21]
Chakraborty S, Aich S, Kim HC. 3D textural, morphological and statistical analysis of voxel of interests in 3T MRI scans for the detection of Parkinson's disease using artificial neural networks[J]. Healthcare (Basel), 2020, 8(1). DOI: 10.3390/healthcare8010034.
[22]
Sikio M, Holli-Helenius KK, Harrison LC, et al. MR image texture in Parkinson's disease: a longitudinal study[J]. Acta Radiol, 2015, 56(1): 97-104. DOI: 10.1177/0284185113519775.

PREV MR diffusion weighted imaging:Application in soft tissue tumors
NEXT Study on long-rage and short-rage functional connectivity strength of brain network hubs in patients with subcortical ischemic vascular disease
  


LINK


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