评估术前基于对比增强 CT (CECT) 的深度学习放射组学列线图 (DLRN) 预测小鼠双分钟 2 (MDM2) 基因扩增作为区分腹膜后高分化脂肪肉瘤 (WDLPS) 和脂肪瘤的方法的效果这项回顾性多中心研究包括 167 名患有 MDM2 阳性 WDLPS 或 MDM2 阴性脂肪瘤的患者（训练/外部测试队列，104/63）。临床数据和 CECT 特征由两名放射科医生独立测量和分析。开发了临床放射学模型、放射组学特征 (RS)、深度学习和放射组学特征 (DLRS) 以及结合放射组学和深度学习特征的 DLRN，以区分 WDLPS 和脂肪瘤。根据受试者工作特征曲线下面积 (AUC)、准确性、校准曲线和决策曲线分析 (DCA) 评估模型实用性。DLRN 在训练中表现出区分腹膜后脂肪瘤和 WDLPS 的良好性能（AUC，0.981） ；准确度，0.933）和外部验证组（AUC，0.861；准确度，0.810）。 DeLong 测试显示 DLRN 明显优于临床放射学和 RS 模型（训练：0.981 vs. 0.890 vs. 0.751；验证：0.861 vs. 0.724 vs. 0.700；均 P < 0.05）；然而，DLRN 和 DLRS 之间的性能没有明显差异（训练：0.981 与 0.969；验证：0.861 与 0.837；两者 P > 0.05）。校准曲线分析和DCA表明，列线图具有良好的校准效果，具有显着的临床优势。DLRN在术前预测WDLPS和腹膜后脂肪瘤方面表现出强大的预测能力，使其成为一种有前景的影像学生物标志物，可以促进个性化管理和精准医疗。版权所有© 2024 年大学放射科医生协会。由爱思唯尔公司出版。保留所有权利。

To assess the efficacy of a preoperative contrast-enhanced CT (CECT)-based deep learning radiomics nomogram (DLRN) for predicting murine double minute 2 (MDM2) gene amplification as a means of distinguishing between retroperitoneal well-differentiated liposarcomas (WDLPS) and lipomas.This retrospective multi-center study included 167 patients (training/external test cohort, 104/63) with MDM2-positive WDLPS or MDM2-negative lipomas. Clinical data and CECT features were independently measured and analyzed by two radiologists. A clinico-radiological model, radiomics signature (RS), deep learning and radiomics signature (DLRS), and a DLRN incorporating radiomics and deep learning features were developed to differentiate between WDLPS and lipoma. The model utility was evaluated based on the area under the receiver operating characteristic curve (AUC), accuracy, calibration curve, and decision curve analysis (DCA).The DLRN showed good performance for distinguishing retroperitoneal lipomas and WDLPS in the training (AUC, 0.981; accuracy, 0.933) and external validation group (AUC, 0.861; accuracy, 0.810). The DeLong test revealed the DLRN was noticeably better than clinico-radiological and RS models (training: 0.981 vs. 0.890 vs. 0.751; validation: 0.861 vs. 0.724 vs. 0.700; both P < 0.05); however, no discernible difference in performance was seen between the DLRN and DLRS (training: 0.981 vs. 0.969; validation: 0.861 vs. 0.837; both P > 0.05). The calibration curve analysis and DCA demonstrated that the nomogram exhibited good calibration and offered substantial clinical advantages.The DLRN exhibited strong predictive capability in predicting WDLPS and retroperitoneal lipomas preoperatively, making it a promising imaging biomarker that can facilitate personalized management and precision medicine.Copyright © 2024 The Association of University Radiologists. Published by Elsevier Inc. All rights reserved.