Share：
Share this content in WeChat
X
Retraction: 2022-08-10
• Technical Article •
Application of different radiomics dignostic models based on conventional MR images in the preprotive grading of brain gliomag
MU Jianhua  ZHANG Yanwei  WU Zhigang 

Cite this article as: Mu JH, Zhang YW, Wu ZG. Application of different radiomics dignostic models based on conventional MR images in the preprotive grading of brain glioma. Chin J Magn Reson Imaging, 2020, 11(1): 55-59. DOI:10.12015/issn.1674-8034.2020.01.012.


[Abstract] Objective: This study intends to use different MR images and different machine learning models to establish a radiomics diagnostic model of preoperative grading of gliomas, exploring the feasibility of radiomics diagnostic models in preoperative grading of gliomas.Materials and Methods: This study retrospectively analyzed 93 patients with glioma who underwent routine MRI examination before operation. They were divided into low-grade glioma (LGG group) and high-grade glioma (HGG group). DICOM format images were imported into GE-AK software. The regions of interest (ROI) of T2-weighted (T2WI) and T1-enhanced (T1CE) images were delineated by software features extraction. Histogram and texture features were imported into R language software package for feature preprocessing and dimensionality reduction. Then six machine learning models were established by selecting three functions. All the data were divided into training sets and training sets according to the ratio of 7∶3. The six models were trained by 10-fold cross-validation, and then the ROC curve was drawn to calculate the sensitivity, specificity and AUC of the classification of LGG and HGG.Results: The average age of LGG group was lower than that of HGG group (P<0.01). There was no significant difference in gender composition between LGG group and HGG group (P>0.05). The AUC of the six radiomics diagnostic models is greater than 0.8. The AUC of the radiomics diagnostic model based on T1 enhancement image is larger than that based on T2WI image, and the AUC of the RF model based on T1 enhancement image is the highest, reaching 0.97.Conclusions: The diagnostic model of imaging histology has good diagnostic value for the pathological grading of glioma. The diagnostic efficiency of six imaging histology models is higher, and the RF model based on T1CE image has the highest diagnostic efficiency.
[Keywords] radiomics；glioma；pathological grading；machine learning

MU Jianhua Department of Radiology, Beijing Jishuitan Hospital, Beijing 100035, China

ZHANG Yanwei Department of Radiology, Beijing Jishuitan Hospital, Beijing 100035, China

WU Zhigang* Department of Radiology, Beijing Jishuitan Hospital, Beijing 100035, China

*Correspondence to: Wu ZG, E-mail: huaqingliw@163.com

Conflicts of interest   None.

Received  2019-09-05
Accepted  2019-11-21
DOI: 10.12015/issn.1674-8034.2020.01.012
Cite this article as: Mu JH, Zhang YW, Wu ZG. Application of different radiomics dignostic models based on conventional MR images in the preprotive grading of brain glioma. Chin J Magn Reson Imaging, 2020, 11(1): 55-59. DOI:10.12015/issn.1674-8034.2020.01.012.

[1]
Filippini G. Epidemiology of primary central nervous system tumors. Handb Clin Neurol, 2012, 104(104): 3.
[2]
Louis DN, Ohgaki H, Wiestler OD, et al. The 2007 who classification of tumours of the central nervous system. Acta Neuropathol, 2007, 114(2): 97-109.
[3]
Alattar AA, Brandel MG, Hirshman BR, et al. Oligodendroglioma resection: a surveillance, epidemiology, and end results (seer) analysis. J Neurosurg, 2017, 128(4): 1076-1083.
[4]
Raab SS, Dana Marie G, Janosky JE, et al. Clinical impact and frequency of anatomic pathology errors in cancer diagnoses. Cancer, 2010, 104(10): 2205-2213.
[5]
Suh HB, Choi YS, Bae S, et al. Primary central nervous system lymphoma and atypical glioblastoma: differentiation using radiomics approach. Eur Radiol, 2018, 28(9): 3832-3839.
[6]
Yang D, Rao G, Martinez J, et al. Evaluation of tumor-derived mri-texture features for discrimination of molecular subtypes and prediction of 12-month survival status in glioblastoma. Med Phys, 2015, 42(11): 6725-6735.
[7]
Li Y, Liu X, Xu K, et al. Mri features can predict egfr expression in lower grade gliomas: a voxel-based radiomic analysis. Eur Radiol, 2017, 28(1): 356-362.
[8]
Tian Q, Yan LF, Zhang X, et al. Radiomics strategy for glioma grading using texture features from multiparametric mri. J Magn Reson Imaging, 2018, 48(6): 1518-1528.
[9]
Breiman L. Random forests. Machine Learning, 2001, 45(1): 5-32.
[10]
Parmar C, Grossmann P, Bussink J, et al. Machine learning methods for quantitative radiomic biomarkers. Sci Rep, 2015, 5(1): 13087.
[11]
Montazeri M, Montazeri M, Montazeri M, et al. Machine learning models in breast cancer survival prediction. Technol Health Care, 2015, 24(1): 31-42.
[12]
Qin JB, Liu Z, Zhang H, et al. Grading of gliomas by using radiomic features on multiple magnetic resonance imaging (mri) sequences. Med Sci Monit, 2017, 23(1): 2168-2178.
[13]
Skogen K, Schulz A, Dormagen JB, et al. Diagnostic performance of texture analysis on mri in grading cerebral gliomas. Eur J Radiol, 2016, 85(4): 824-829.
[14]
Ryu YJ, Seung Hong C, Joon PS, et al. Glioma: application of whole-tumor texture analysis of diffusion-weighted imaging for the evaluation of tumor heterogeneity. PLoS One, 2014, 9(9): e108335.
[15]
Kickingereder P, Götz M, Wick A, et al. Large-scale radiomic profiling of recurrent glioblastoma identifies an imaging predictor for stratifying anti-angiogenic treatment response. Clin Cancer Res, 2017, 22(23): 5765-5771.
[16]
Ng F, Kozarski R, Ganeshan B, et al. Assessment of tumor heterogeneity by ct texture analysis: can the largest cross-sectional area be used as an alternative to whole tumor analysis? Eur J Radiol, 2013, 82(2): 342-348.
[17]
Lubner MG, Stabo N, Lubner SJ, et al. Ct textural analysis of hepatic metastatic colorectal cancer: pre-treatment tumor heterogeneity correlates with pathology and clinical outcomes. Abdom Imaging, 2015, 40(7): 2331-2337.
[18]
Louis DN, Perry A, Reifenberger G, et al. The 2016 world health organization classification of tumors of the central nervous system: a summary. Acta Neuropathol, 2016, 131(6): 803-820.

PREV An improved multi-echo field fitting algorithm in quantitative susceptibility mapping
NEXT Schwannoma in the right trigone of the lateral ventricle: a case report
  


LINK


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