当前位置: X-MOL 学术IEEE J. Biomed. Health Inform. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Modeling Texture in Deep 3D CNN for Survival Analysis
IEEE Journal of Biomedical and Health Informatics ( IF 6.7 ) Pub Date : 2020-09-22 , DOI: 10.1109/jbhi.2020.3025901
Ahmad Chaddad , Paul Sargos , Christian Desrosiers

Radiomics has shown remarkable potential for predicting the survival outcome for various types of cancers such as pancreatic ductal adenocarcinoma (PDAC). However, to date, there has been limited research using convolutional neural networks (CNN) with radiomic methods for this task, due to their requirement for large training sets. To overcome this issue, we propose a new type of radiomic descriptor modeling the distribution of learned features with a Gaussian mixture model (GMM). These parametric features (GMM-CNN) are computed from gross tumor volumes of PDAC patients defined semi-automatically in pre-operative computed tomography (CT) scans. We use the proposed GMM-CNN features as input to a robust classifier based on random forests (RF) to predict the survival outcome of patients with PDAC. Our experiments assess the advantage of GMM-CNN compared to employing the same 3D CNN model directly, standard radiomic (i.e., histogram, texture and shape), conditional entropy (CENT) based on 3DCNN, and clinical features (i.e., serum carbohydrate antigen 19-9 and chemotherapy neoadjuvant). Using the RF model (100 samples for training; 59 samples for validation), GMM-CNN features provided the highest area under the ROC curve (AUC) of 72.0% (p = $6.4\times 10^{-5}$ ) compared to 64.0% (p = 0.01) for the 3D CNN model output, 66.8% (p = 0.01) for standard radiomic features, 64.2% (p = 0.003) for CENT, and 57.6% (p = 0.3) for clinical variables. Our results suggest that the proposed GMM-CNN features used with a RF classifier can significantly improve the capacity to prognosticate PDAC patients prior to surgery via routinely-acquired imaging data.

中文翻译:

在深度 3D CNN 中建模纹理以进行生存分析

放射组学在预测胰腺导管腺癌 (PDAC) 等各种类型癌症的生存结果方面显示出巨大的潜力。然而,迄今为止,由于需要大型训练集,使用带有放射组学方法的卷积神经网络 (CNN) 进行这项任务的研究有限。为了克服这个问题,我们提出了一种新型的放射组学描述符,使用高斯混合模型(GMM)对学习特征的分布进行建模。这些参数特征 (GMM-CNN) 是根据在术前计算机断层扫描 (CT) 扫描中半自动定义的 PDAC 患者的总肿瘤体积计算得出的。我们使用提出的 GMM-CNN 特征作为基于随机森林 (RF) 的稳健分类器的输入,以预测 PDAC 患者的生存结果。我们的实验评估了 GMM-CNN 与直接使用相同 3D CNN 模型相比的优势、标准放射组学(即直方图、纹理和形状)、基于 3DCNN 的条件熵 (CENT) 和临床特征(即血清碳水化合物抗原 19 -9 和化疗新辅助)。使用 RF 模型(100 个样本用于训练;59 个样本用于验证),GMM-CNN 特征提供的 ROC 曲线下面积 (AUC) 最高,为 72.0% (p =$6.4\乘以 10^{-5}$ ) 相比,3D CNN 模型输出为 64.0% (p = 0.01),标准放射组学特征为 66.8% (p = 0.01),CENT 为 64.2% (p = 0.003),临床变量为 57.6% (p = 0.3) . 我们的结果表明,提出的 GMM-CNN 特征与 RF 分类器一起使用可以显着提高通过常规获得的成像数据在手术前预测 PDAC 患者的能力。
更新日期:2020-09-22
down
wechat
bug