3D DenseNet Deep Learning Based Preoperative Computed Tomography for Detecting Myasthenia Gravis in Patients With Thymoma.
3D DenseNet Deep Learning Based Preoperative Computed Tomography for Detecting Myasthenia Gravis in Patients With Thymoma.
复制标题
DOI：
10.3389/fonc.2021.631964
复制
发表时间：
2021
影响因子：
4.7
通讯作者：
Ke Z
中科院分区：
文献类型：
--
作者：
Liu Z;Zhu Y;Yuan Y;Yang L;Wang K;Wang M;Yang X;Wu X;Tian X;Zhang R;Shen B;Luo H;Feng H;Feng S;Ke Z
重症肌无力（MG）是胸腺瘤最常见的副肿瘤综合征，与胸腺异常密切相关。及时发现MG的危险性，有利于胸腺瘤患者的临床管理和治疗决策。在此，我们开发了一种基于术前计算机断层扫描（CT）的3D DenseNet深度学习（DL）模型，作为检测胸腺瘤患者MG的非侵入性方法。一个大的队列230胸腺瘤患者在附属医院与医学院的参与。对182例胸腺瘤患者（81例MG，101例非MG）进行训练和建模。来自另一家医院的48例病例用于外部验证。采用3D-DenseNet-DL模型和5种放射组学模型检测胸腺瘤患者的MG。结合机器学习和语义CT图像特征进行综合分析，命名为基于3D-DenseNet-DL的多模型，以建立更有效的预测模型。通过详细比较预测效果，3D-DenseNet-DL有效识别MG患者，上级其他五种放射组学模型，平均ROC曲线下面积（AUC）、准确性、灵敏度和特异性分别为0.734、0.724、0.787和0.672。基于3D-DenseNet-DL的多模型的有效性进一步提高，如以下指标所证明：AUC 0.766，准确性0.790，灵敏度0.739和特异性0.801。外部验证结果证实了该基于DL的多模型的可行性，指标分别为：AUC 0.730，准确度0.732，灵敏度0.700和特异性0.690。我们的3D-DenseNet-DL模型可以根据术前CT成像有效检测胸腺瘤患者的MG。该模型可作为胸腺瘤相关MG常规诊断标准的补充。
Myasthenia gravis (MG) is the most common paraneoplastic syndromes of thymoma and closely related to thymus abnormalities. Timely detecting of the risk of MG would benefit clinical management and treatment decision for patients with thymoma. Herein, we developed a 3D DenseNet deep learning (DL) model based on preoperative computed tomography (CT) as a non-invasive method to detect MG in thymoma patients. A large cohort of 230 thymoma patients in a hospital affiliated with a medical school were enrolled. 182 thymoma patients (81 with MG, 101 without MG) were used for training and model building. 48 cases from another hospital were used for external validation. A 3D-DenseNet-DL model and five radiomic models were performed to detect MG in thymoma patients. A comprehensive analysis by integrating machine learning and semantic CT image features, named 3D-DenseNet-DL-based multi-model, was also performed to establish a more effective prediction model. By elaborately comparing the prediction efficacy, the 3D-DenseNet-DL effectively identified MG patients and was superior to other five radiomic models, with a mean area under ROC curve (AUC), accuracy, sensitivity, and specificity of 0.734, 0.724, 0.787, and 0.672, respectively. The effectiveness of the 3D-DenseNet-DL-based multi-model was further improved as evidenced by the following metrics: AUC 0.766, accuracy 0.790, sensitivity 0.739, and specificity 0.801. External verification results confirmed the feasibility of this DL-based multi-model with metrics: AUC 0.730, accuracy 0.732, sensitivity 0.700, and specificity 0.690, respectively. Our 3D-DenseNet-DL model can effectively detect MG in patients with thymoma based on preoperative CT imaging. This model may serve as a supplement to the conventional diagnostic criteria for identifying thymoma associated MG.
登录
查看更多内容
NCI研讨会报告：将成像表型与基因组学特征相关联的临床和计算要求。
影响因子：
5
作者：
Colen, Rivka;Foster, Ian;Gatenby, Robert;Giger, Mary Ellen;Gillies, Robert;Gutman, David;Heller, Matthew;Jain, Rajan;Madabhushi, Anant;Madhavan, Subha;Napel, Sandy;Rao, Arvind;Saltz, Joel;Tatum, James;Verhaak, Roeland;Whitman, Gary
通讯作者：
Whitman, Gary
影响因子：
8.9
作者：
Iannarelli, Angelo;Sacconi, Beatrice;Catalano, Carlo
通讯作者：
Catalano, Carlo
影响因子：
19.7
作者：
Jain, Rajan;Poisson, Laila M.;Flanders, Adam
通讯作者：
Flanders, Adam
影响因子：
9.9
作者：
LINDSTROM, JM;SEYBOLD, ME;DUANE, DD
通讯作者：
DUANE, DD
影响因子：
3.4
作者：
Sanders, DB
通讯作者：
Sanders, DB