Radiomics analysis for the prediction of locoregional recurrence of locally advanced oropharyngeal cancer and hypopharyngeal cancer

doi:10.1007/s00405-023-08380-4

CNU IR > Offices > 456 > Item 310902800/34916

Please use this identifier to cite or link to this item: https://ir.cnu.edu.tw/handle/310902800/34916

Title:	Radiomics analysis for the prediction of locoregional recurrence of locally advanced oropharyngeal cancer and hypopharyngeal cancer
Authors:	Wu, Te-Chang Liu, Yan-Lin Chen, Jeon-Hor Chen, Tai-Yuan Ko, Ching-Chung Lin, Chiao-Yun Kao, Cheng-Yi Yeh, Lee-Ren Su, Min-Ying
Contributors:	Chi Mei Med Ctr, Dept Med Imaging Chang Jung Christian Univ, Dept Med Sci Ind Univ Calif Irvine, Dept Radiol Sci E DA Hosp, Dept Med Imaging Chang Jung Christian Univ, Grad Inst Med Sci Chia Nan Univ Pharm & Sci, Ctr Gen Educ I Shou Univ, Coll Med E DA Canc Hosp, Div Med Radiol I Shou Univ, Coll Med, Dept Med Imaging & Radiol Sci
Keywords:	Oropharyngeal cancer Hypopharyngeal cancer Recurrence Prediction Radiomics
Date:	2024
Issue Date:	2024-12-25 11:05:36 (UTC+8)
Publisher:	SPRINGER
Abstract:	PurposeBy radiomic analysis of the postcontrast CT images, this study aimed to predict locoregional recurrence (LR) of locally advanced oropharyngeal cancer (OPC) and hypopharyngeal cancer (HPC).MethodsA total of 192 patients with stage III-IV OPC or HPC from two independent cohort were randomly split into a training cohort with 153 cases and a testing cohort with 39 cases. Only primary tumor mass was manually segmented. Radiomic features were extracted using PyRadiomics, and then the support vector machine was used to build the radiomic model with fivefold cross-validation process in the training data set. For each case, a radiomics score was generated to indicate the probability of LR.ResultsThere were 94 patients with LR assigned in the progression group and 98 patients without LR assigned in the stable group. There was no significant difference of TNM staging, treatment strategies and common risk factors between these two groups. For the training data set, the radiomics model to predict LR showed 83.7% accuracy and 0.832 (95% CI 0.72, 0.87) area under the ROC curve (AUC). For the test data set, the accuracy and AUC slightly declined to 79.5% and 0.770 (95% CI 0.64, 0.80), respectively. The sensitivity/specificity of training and test data set for LR prediction were 77.6%/89.6%, and 66.7%/90.5%, respectively.ConclusionsThe image-based radiomic approach could provide a reliable LR prediction model in locally advanced OPC and HPC. Early identification of those prone to post-treatment recurrence would be helpful for appropriate adjustments to treatment strategies and post-treatment surveillance.
Relation:	European Archives of Oto-Rhino-Laryngology, v.281, n.3, pp.1473-1481
Appears in Collections:	[Offices] 456

Files in This Item:

File	Description	Size	Format
index.html		0Kb	HTML	4	View/Open

Loading...