ObjectivesThis study aimed to utilize MR radiomics-based machine learning classifiers on a large-sample, multicenter dataset to develop an optimal model for predicting malignant sinonasal tumors and tumor-like lesions. MethodsThis study included 1711 adult patients (875 benign and 836 malignant) with sinonasal tumors or tumor-like lesions from three institutions. Patients from institution 1 (n = 1367) constituted both the training and validation cohorts, while those from institution 2 and 3 (n = 158/186) made up the test cohorts. Manual segmentation of the region of interest of the tumor was performed on T1WI, T2WI, and contrast-enhanced T1WI (CE-T1WI). Data normalization, dimensional reductions, feature selection, and classifications were performed using ten machine-learning classifiers. Four fusion models, namely T1WI + T2WI, T1WI + CE-T1WI, T2WI + CE-T1WI, and T1WI + T2WI + CE-T1WI, were constructed using the top ten features with the highest contribution in feature selection in the optimal models of T1WI, T2WI, and CE-T1WI. The Delong test compared areas under the curve (AUC) between models. ResultsThe AUCs of training/validation/test1/test2 datasets for T1WI, T2WI, and CE-T1WI were 0.900/0.842/0.872/0.839, 0.876/0.789/0.842/0.863, and 0.899/0.824/0.831/0.707, respectively. The fusion model from T1WI + T2WI + CE-T1WI had the highest AUC. The AUCs of training/validation/test1/test2 datasets were 0.947/0.849/0.871/0.887. The T1WI + T2WI + CE-T1WI model demonstrated a significantly higher AUC than the T2WI + CE-T1WI model in both cohorts (p < 0.05) and outperformed the T2WI model in test 1 (p = 0.008) and the T1WI model in test 2 (p = 0.006). ConclusionsThis fusion model based on radiomics from T1WI + T2WI + CE-T1WI images and machine learning can improve the power in predicting malignant sinonasal tumors with high accuracy, resilience, and robustness. Clinical relevance statementOur study proposes a radiomics-based machine learning fusion model from T1- and T2-weighted images and contrast-enhanced T1-weighted images, which can non-invasively identify the nature of sinonasal tumors and improve the performance in predicting malignant sinonasal tumors. Key Points. ..
基金：
Beijing Municipal Administration of Hospitals' Ascent Plan [DFL20190203]; National Key R&D Program of China [2022YFC2404005]; National Health Commission's Capacity Building and Continuing Education Center [YXFSC2022JJSJ009]; Beijing Nova Program [20230484460]; Priming scientific research foundation for the junior researcher in Beijing Tongren Hospital, Capital Medical University [2023-YJJ-ZZL-045]
第一作者机构：[1]Capital Med Univ, Beijing Tongren Hosp, Dept Radiol, Beijing, Peoples R China
共同第一作者：
通讯作者：
通讯机构：[5]Capital Med Univ, Beijing Tongren Hosp, Dept Otolaryngol Head & Neck Surg, Beijing, Peoples R China[6]Beijing Inst Otorhinolaryngol, Beijing Lab Allerg Dis, Beijing, Peoples R China[7]Beijing Inst Otorhinolaryngol, Beijing Key Lab Nasal Dis, Beijing, Peoples R China[8]Chinese Acad Med Sci, Res Unit Diag & Treatment Chron Nasal Dis, Beijing, Peoples R China[9]Capital Med Univ, Beijing Tongren Hosp, Dept Allergy, Beijing, Peoples R China
推荐引用方式(GB/T 7714)：
Wang Yuchen,Han Qinghe,Wen Baohong,et al.Development and validation of a prediction model for malignant sinonasal tumors based on MR radiomics and machine learning[J].EUROPEAN RADIOLOGY.2024,doi:10.1007/s00330-024-11033-7.
APA：
Wang, Yuchen,Han, Qinghe,Wen, Baohong,Yang, Bingbing,Zhang, Chen...&Xian, Junfang.(2024).Development and validation of a prediction model for malignant sinonasal tumors based on MR radiomics and machine learning.EUROPEAN RADIOLOGY,,
MLA：
Wang, Yuchen,et al."Development and validation of a prediction model for malignant sinonasal tumors based on MR radiomics and machine learning".EUROPEAN RADIOLOGY .(2024)
医学