Li Qi, Li Xuezhou, Liu Wenbin, Yu Jieyu, Chen Yukun, Zhu Mengmeng, Li Na, Liu Fang, Wang Tiegong, Fang Xu, Li Jing, Lu Jianping, Shao Chengwei, Bian Yun
Department of Radiology, Changhai Hospital, Navy Medical University, Shanghai, China.
Department of Radiology, 96601 Military Hospital of PLA, Huangshan, Anhui, China.
Front Oncol. 2023 Jan 23;13:1108545. doi: 10.3389/fonc.2023.1108545. eCollection 2023.
To evaluate the diagnostic performance of radiomics model based on fully automatic segmentation of pancreatic tumors from non-enhanced magnetic resonance imaging (MRI) for differentiating pancreatic adenosquamous carcinoma (PASC) from pancreatic ductal adenocarcinoma (PDAC).
In this retrospective study, patients with surgically resected histopathologically confirmed PASC and PDAC who underwent MRI scans between January 2011 and December 2020 were included in the study. Multivariable logistic regression analysis was conducted to develop a clinical and radiomics model based on non-enhanced T1-weighted and T2-weighted images. The model performances were determined based on their discrimination and clinical utility. Kaplan-Meier and log-rank tests were used for survival analysis.
A total of 510 consecutive patients including 387 patients (age: 61 ± 9 years; range: 28-86 years; 250 males) with PDAC and 123 patients (age: 62 ± 10 years; range: 36-84 years; 78 males) with PASC were included in the study. All patients were split into training (n=382) and validation (n=128) sets according to time. The radiomics model showed good discrimination in the validation (AUC, 0.87) set and outperformed the MRI model (validation set AUC, 0.80) and the ring-enhancement (validation set AUC, 0.74).
The radiomics model based on non-enhanced MRI outperformed the MRI model and ring-enhancement to differentiate PASC from PDAC; it can, thus, provide important information for decision-making towards precise management and treatment of PASC.
评估基于非增强磁共振成像（MRI）对胰腺肿瘤进行全自动分割的放射组学模型在鉴别胰腺腺鳞癌（PASC）与胰腺导管腺癌（PDAC）方面的诊断性能。
在这项回顾性研究中，纳入了2011年1月至2020年12月期间接受MRI扫描且经手术切除并经组织病理学证实为PASC和PDAC的患者。基于非增强T1加权和T2加权图像进行多变量逻辑回归分析，以建立临床和放射组学模型。根据模型的辨别力和临床实用性来确定其性能。采用Kaplan-Meier法和对数秩检验进行生存分析。
本研究共纳入510例连续患者，其中387例（年龄：61±9岁；范围：28 - 86岁；男性250例）为PDAC患者，123例（年龄：62±10岁；范围：36 - 84岁；男性78例）为PASC患者。所有患者按时间分为训练集（n = 382）和验证集（n = 128）。放射组学模型在验证集（AUC，0.87）中显示出良好的辨别力，优于MRI模型（验证集AUC，0.80）和环形强化（验证集AUC，0.74）。
基于非增强MRI的放射组学模型在鉴别PASC与PDAC方面优于MRI模型和环形强化；因此，它可为PASC的精确管理和治疗决策提供重要信息。
