Ying-Mei Zheng1, Jian Li2, Song Liu3, Jiu-Fa Cui3, Jin-Feng Zhan3, Jing Pang3, Rui-Zhi Zhou3, Xiao-Li Li3, Cheng Dong4. 1. Health Management Center, The Affiliated Hospital of Qingdao University, No.16, Jiangsu Road, Qingdao, 266000, China. 2. Department of Radiology, The University of Hong Kong - Shenzhen Hospital, No.1, Haiyuan Road, Futian District, Shenzhen, 518000, China. 3. Department of Radiology, The Affiliated Hospital of Qingdao University, No.16, Jiangsu Road, Qingdao, 266000, China. 4. Department of Radiology, The Affiliated Hospital of Qingdao University, No.16, Jiangsu Road, Qingdao, 266000, China. derc007@sina.com.
Abstract
OBJECTIVES: Preoperative differentiation between benign parotid gland tumors (BPGT) and malignant parotid gland tumors (MPGT) is important for treatment decisions. The purpose of this study was to develop and validate an MRI-based radiomics nomogram for the preoperative differentiation of BPGT from MPGT. METHODS: A total of 115 patients (80 in training set and 35 in external validation set) with BPGT (n = 60) or MPGT (n = 55) were enrolled. Radiomics features were extracted from T1-weighted and fat-saturated T2-weighted images. A radiomics signature model and a radiomics score (Rad-score) were constructed and calculated. A clinical-factors model was built based on demographics and MRI findings. A radiomics nomogram model combining the Rad-score and independent clinical factors was constructed using multivariate logistic regression analysis. The diagnostic performance of the three models was evaluated and validated using ROC curves on the training and validation datasets. RESULTS: Seventeen features from MR images were used to build the radiomics signature. The radiomics nomogram incorporating the clinical factors and radiomics signature had an AUC value of 0.952 in the training set and 0.938 in the validation set. Decision curve analysis showed that the nomogram outperformed the clinical-factors model in terms of clinical usefulness. CONCLUSIONS: The above-described radiomics nomogram performed well for differentiating BPGT from MPGT, and may help in the clinical decision-making process. KEY POINTS: • Differential diagnosis between BPGT and MPGT is rather difficult by conventional imaging modalities. • A radiomics nomogram integrated with the radiomics signature, clinical data, and MRI features facilitates differentiation of BPGT from MPGT with improved diagnostic efficacy.
OBJECTIVES: Preoperative differentiation between benign parotid gland tumors (BPGT) and malignant parotid gland tumors (MPGT) is important for treatment decisions. The purpose of this study was to develop and validate an MRI-based radiomics nomogram for the preoperative differentiation of BPGT from MPGT. METHODS: A total of 115 patients (80 in training set and 35 in external validation set) with BPGT (n = 60) or MPGT (n = 55) were enrolled. Radiomics features were extracted from T1-weighted and fat-saturated T2-weighted images. A radiomics signature model and a radiomics score (Rad-score) were constructed and calculated. A clinical-factors model was built based on demographics and MRI findings. A radiomics nomogram model combining the Rad-score and independent clinical factors was constructed using multivariate logistic regression analysis. The diagnostic performance of the three models was evaluated and validated using ROC curves on the training and validation datasets. RESULTS: Seventeen features from MR images were used to build the radiomics signature. The radiomics nomogram incorporating the clinical factors and radiomics signature had an AUC value of 0.952 in the training set and 0.938 in the validation set. Decision curve analysis showed that the nomogram outperformed the clinical-factors model in terms of clinical usefulness. CONCLUSIONS: The above-described radiomics nomogram performed well for differentiating BPGT from MPGT, and may help in the clinical decision-making process. KEY POINTS: • Differential diagnosis between BPGT and MPGT is rather difficult by conventional imaging modalities. • A radiomics nomogram integrated with the radiomics signature, clinical data, and MRI features facilitates differentiation of BPGT from MPGT with improved diagnostic efficacy.
Entities:
Keywords:
Magnetic resonance imaging; Parotid neoplasms; Radiomics
Authors: Naglaa Mansour; Murat Bas; Konrad Friedrich Stock; Ulrich Strassen; Benedikt Hofauer; Andreas Knopf Journal: Ultraschall Med Date: 2015-08-14 Impact factor: 6.548