机构地区:[1]上海交通大学医学院附属第九人民医院放射科,上海200011 [2]复旦大学信息科学与工程学院,上海200082 [3]复旦大学附属眼耳鼻喉科医院放射科,上海200030
出 处:《中华放射学杂志》2025年第2期206-211,共6页Chinese Journal of Radiology
基 金:上海市“医苑新星”青年医学人才培养资助计划(沪卫计人事[2019]72号);上海九院研究型医师项目(2022hbyjxys-rjl)。
摘 要:目的:探讨基于常规MRI的深度学习(DL)模型在鉴别眼眶孤立性纤维瘤(SFT)与神经鞘瘤的价值。方法:该研究为病例对照研究。回顾性分析2014年12月至2022年1月复旦大学附属眼耳鼻喉科医院(机构1)和2015年7月至2022年5月上海交通大学医学院附属第九人民医院(机构2)收治的经病理证实的眼眶SFT和神经鞘瘤患者资料。共140例患者,其中来自机构1的104例患者组成用于构建DL模型的训练队列,来自机构2的36例患者组成用于评估模型性能的外部验证队列。基于患者术前横断面脂肪抑制T_(2)WI和增强T_(1)WI图像,于所有包含肿瘤的层面勾画肿瘤轮廓。应用18层网络结构的残差网络和分散注意力残差网络(分别表示为ResNet-18和ResNeSt-18)分别构建基于单独T_(2)WI、增强T_(1)WI和两者联合序列的6个诊断模型。1名放射科住院医师和1名主治医师分别独立阅片来确定肿瘤类型。通过受试者操作特征曲线评估外部验证队列中DL模型与放射科医师鉴别眼眶SFT与神经鞘瘤的效能,并采用DeLong检验比较曲线下面积(AUC)。结果:在外部验证队列,基于单独T_(2)WI、增强T_(1)WI和联合序列的ResNet-18模型的AUC(95%CI)分别为0.861(0.719~1)、0.896(0.774~1)和0.885(0.755~1),ResNeSt-18模型的AUC(95%CI)分别为0.889(0.748~1)、0.872(0.726~1)和0.910(0.801~1),其中联合序列的ResNeSt-18模型鉴别眼眶SFT与神经鞘瘤的效能最佳。放射科住院医师和主治医师单独阅片的AUC(95%CI)分别为0.729(0.571~0.887)和0.771(0.618~0.923)。联合序列的ResNeSt-18模型与住院医师、主治医师单独阅片的AUC差异有统计学意义(Z=1.96、2.00,P=0.049、0.045)。结论:基于常规MRI的ResNeSt-18模型可以有效鉴别眼眶SFT与神经鞘瘤,且效能优于放射科住院医师和主治医师。Objective To explore the value of deep learning(DL)models based on conventional MRI in differentiating orbital solitary fibrous tumors(SFT)from schwannomas.Methods This was a case-control study.A retrospective analysis was conducted on patients with pathologically confirmed orbital SFT and schwannoma admitted to Eye&ENT Hospital,Fudan University(institution 1)from December 2014 to January 2022 and Ninth People′s Hospital,Shanghai Jiao Tong University School of Medicine(institution 2)from July 2015 to May 2022.A total of 140 patients were included,with 104 patients from institution 1 comprising the training cohort for building DL models and 36 patients from institution 2 comprising the external validation cohort for assessing model performance.Based on the preoperative cross-sectional fat-suppressed T_(2)WI and contrast-enhanced T_(1)WI(ceT_(1)WI),tumor contours were outlined on all tumor-containing slices.Six diagnostic models were constructed using residual networks(ResNet)and split-attention residual networks(ResNeSt)with 18 layers(ResNet-18 and ResNeSt-18),based solely on individual T_(2)WI and ceT_(1)WI,as well as a combination of both.A radiology resident and an attending radiologist independently reviewed conventional MRI images to determine the tumor type.The performance of the DL models and radiologists in differentiating orbital SFT from schwannoma in the external validation cohort was evaluated using receiver operating characteristic curves,and the areas under the curves(AUC)were compared using the DeLong test.Results In the external validation cohort,the AUC(95%CI)of the ResNet-18 models based on T_(2)WI,ceT_(1)WI,and their combination were 0.861(0.719-1),0.896(0.774-1),and 0.885(0.755-1),respectively,while the AUC(95%CI)of the ResNeSt-18 models were 0.889(0.748-1),0.872(0.726-1),and 0.910(0.801-1),respectively.Among these,the ResNeSt-18 model based on the combined sequences achieved the best performance in differentiating the two tumors.The AUC(95%CI)for the individual interpretation of the radiolog
关 键 词:眼眶肿瘤 孤立性纤维瘤 神经鞘瘤 磁共振成像 深度学习
分 类 号:R445.2[医药卫生—影像医学与核医学] R739.72[医药卫生—诊断学]
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...