Cite this article as: Guo R, Shen XZ, Xin RQ, et al. Predictive value of random forest based on MRI radiomics in evaluating the invasion depth of endometrial carcinoma. Chin J Magn Reson Imaging, 2020, 11(12): 1133-1137. DOI:10.12015/issn.1674-8034.2020.12.011.
[Abstract] Objective: To explore the predictive value of random forest based on MRI plain T2WI and contrast-enhanced T1WI radiomics in evaluating the invasion depth of endometrial carcinoma.Materials and Methods: We retrospectively analyzed one hundred and fourteen (eighty-six cases of stage ⅠA and twenty-eight cases of stage ⅠB) patients with endometrial carcinoma confirmed by surgical pathology and all patients underwent pelvic MRI plain and contrast-enhanced examination. All MRI data were divided into training and testing set by stratified sampling method with the ratio of 4∶1. The ITK-SNAP software was used to manually delineate the region of interest layer by layer on the sagittal T2WI images and the second phase of the multi-phase T1WI contrast-enhanced images. The radiomics features were extracted based on an open soured tool named pyradiomics (https://github.com/Radiomics/pyradiomics), and the model was established based on scikit-learn (https://www.sklearn.org/). Predictive performance was evaluated by the receiver operating characteristics (ROC) curve.Results: In the testing set, the area under the curve (AUC) of the RF model based on the plain T2WI images predicting the depth of myometrial invasion for endometrial carcinoma was 0.938, and the accuracy, sensitivity and specificity were 91.3%, 87.5%, and 93.3%, respectively. The top three most important features of the model were shape flatness, GLSZM zone variance, and GLRLM run variance; The AUC of the RF model based on contrast-enhanced T1WI images was 0.818, the accuracy, sensitivity and specificity were 81.8%, 100%, and 75.0%, respectively. The top three most important features of the model were shape flatness, GLDM large dependence high gray level emphasis, and GLCM correlation.Conclusions: The algorithm of random forest based on MRI radiomics demonstrated great potential in predicting the invasion depth of endometrial carcinoma, and the model based on T2WI images demonstrated more diagnostic value than that contrast-enhanced T1WI images. |
[Keywords] endometrial neoplasms;myometrial invasion;radiomics;magnetic resonance imaging |
GUO Ran Department of Radiology, Beijing Luhe Hospital, Capital Medical University, Beijing 101149, China
SHEN Xiuzhi Department of Radiology, Beijing Luhe Hospital, Capital Medical University, Beijing 101149, China
XIN Ruiqiang Department of Radiology, Beijing Luhe Hospital, Capital Medical University, Beijing 101149, China
SHI Qinglei MR Scientific, Siemens Healthcare, Beijing 100102, China; Machine Learning and Data Mining Lab. Software Colledge, Shandong University, Ji’nan 250101, China
WANG Jinjie Department of Radiology, Beijing Luhe Hospital, Capital Medical University, Beijing 101149, China
ZHONG Jiali Department of Radiology, Beijing Luhe Hospital, Capital Medical University, Beijing 101149, China
PENG Ruchen* Department of Radiology, Beijing Luhe Hospital, Capital Medical University, Beijing 101149, China
*Correspondence to: Peng RC, E-mail: 13501271260@163.com
Conflicts of interest None.
ACKNOWLEDGMENTS This work was part of Beijing Tongzhou District Science and Technology Project No. KJ2020CX004-19 |
Received 2020-06-08 |
Accepted 2020-11-13 |
DOI: 10.12015/issn.1674-8034.2020.12.011 |
Cite this article as: Guo R, Shen XZ, Xin RQ, et al. Predictive value of random forest based on MRI radiomics in evaluating the invasion depth of endometrial carcinoma. Chin J Magn Reson Imaging, 2020, 11(12): 1133-1137. DOI:10.12015/issn.1674-8034.2020.12.011. |