A pilot study of radiomics signature based on biparametric MRI for preoperative prediction of extrathyroidal extension in papillary thyroid carcinoma

Article type: Research Article

Authors: He, Junlin^{a; 1} | Zhang, Heng^{b; 2} | Wang, Xian^{c; 2} | Sun, Zongqiong^b | Ge, Yuxi^b | Wang, Kang^b | Yu, Chunjing^d | Deng, Zhaohong^e | Feng, Jianxin^f | Xu, Xin^f | Hu, Shudong^{b; c; *}

Affiliations: [a] School of Medicine, Jiangsu University, Zhenjiang, Jiangsu, China | [b] Department of Radiology, Affiliated Hospital, Jiangnan University, Huihe Road, Wuxi, Jiangsu, China | [c] Department of Radiology, Affiliated Renmin Hospital, Jiangsu University, Dianli Road, Zhenjiang, Jiangsu, China | [d] Department of Nuclear Medicine, Affiliated Hospital of Jiangnan University, Wuxi, China | [e] School of Digital Media, Jiangnan University and Jiangsu Key Laboratory of Digital Design and Software Technology, Digital Media Academy, Jiangnan University, China | [f] Haohua Technology Co., Ltd, Shanghai, China

Correspondence: [*] Corresponding author: Shudong Hu, Department of Radiology, Affiliated Hospital, Jiangnan University, No. 200, Huihe Road, Wuxi, Jiangsu 214062, China. Department of Radiology, Affiliated Renmin Hospital, Jiangsu University, No. 8, Dianli Road, Zhenjiang, Jiangsu 212002, China. Tel./Fax: +86 510 8868 3052; E-mail: hsd2001054@163.com.

Note: [1] First author: Junlin He E-mail: 912211529@qq.com.

Note: [2] Co-first author: Heng Zhang, Xian Wang.

Abstract: OBJECTIVE:To investigate efficiency of radiomics signature to preoperatively predict histological features of aggressive extrathyroidal extension (ETE) in papillary thyroid carcinoma (PTC) with biparametric magnetic resonance imaging findings. MATERIALS AND METHODS:Sixty PTC patients with preoperative MR including T2WI and T2WI-fat-suppression (T2WI-FS) were retrospectively analyzed. Among them, 35 had ETE and 25 did not. Pre-contrast T2WI and T2WI-FS images depicting the largest section of tumor were selected. Tumor regions were manually segmented using ITK-SNAP software and 107 radiomics features were computed from the segmented regions using the open Pyradiomics package. Then, a random forest model was built to do classification in which the datasets were partitioned randomly 10 times to do training and testing with ratio of 1:1. Furthermore, forward greedy feature selection based on feature importance was adopted to reduce model overfitting. Classification accuracy was estimated on the test set using area under ROC curve (AUC). RESULTS:The model using T2WI-FS image features yields much higher performance than the model using T2WI features (AUC = 0.906 vs. 0.760 using 107 features). Among the top 10 important features of T2WI and T2WI-FS, there are 5 common features. After feature selection, the models trained using top 2 features of T2WI and the top 6 features of T2WI-FS achieve AUC 0.845 and 0.928, respectively. Combining features computed from T2WI and T2WI-FS, model performance decreases slightly (AUC = 0.882 based on all features and AUC = 0.913 based on top features after feature selection). Adjusting hyper parameters of the random forest model have negligible influence on the model performance with mean AUC = 0.907 for T2WI-FS images. CONCLUSIONS:Radiomics features based on pre-contrast T2WI and T2WI-FS is helpful to predict aggressive ETE in PTC. Particularly, the model trained using the optimally selected T2WI-FS image features yields the best classification performance. The most important features relate to lesion size and the texture heterogeneity of the tumor region.

Keywords: Thyroid cancer, neoplasm staging, radiomics, diagnosis, magnetic resonance imaging

DOI: 10.3233/XST-200760

Journal: Journal of X-Ray Science and Technology, vol. 29, no. 1, pp. 171-183, 2021