Development of a self-constrained 3D DenseNet model in automatic detection and segmentation of nasopharyngeal carcinoma using magnetic resonance images
Development of a self-constrained 3D DenseNet model in automatic detection and segmentation of nasopharyngeal carcinoma using magnetic resonance images
复制标题
使用磁共振图像自动检测和分割鼻咽癌的自约束 3D DenseNet 模型的开发
DOI：
10.1016/j.oraloncology.2020.104862
复制
发表时间：
2020-11-01
期刊：
影响因子：
4.8
通讯作者：
Li, Chaofeng
中科院分区：
文献类型：
--
作者：
Ke, Liangru;Deng, Yishu;Li, Chaofeng
目的：针对鼻咽癌（NPC）与非典型良性增生鉴别诊断困难，放疗靶区勾画劳动强度大的问题，提出一种基于深度学习方法的双任务模型，用于在磁源图像（MRI）中自动检测和分割NPC。材料和方法：使用分离的训练集和验证集改进了自约束3D DenseNet（SC-DenseNet）架构。最终共有4100名受试者入组，并使用简单随机化以8：1：1的近似比例分为训练集、验证集和WA集。在WA集中比较了建立的模型与有经验的放射科医生的诊断指标。结果：共获得鼻咽癌（NPC）3142例，良性增生958例。SC-DenseNet模型在检测NPC方面表现出令人鼓舞的性能，总体准确性、敏感性和特异性均高于有经验的放射科医生（分别为97.77% vs 95.87%、99.68% vs 99.24%和91.67% vs 85.21%）。结论：SC-DenseNet模型在鼻咽癌MRI图像的自动检测和分割中具有较好的应用价值，可作为临床工作中的辅助工具，尤其是在筛查项目中具有重要的应用价值。
Objectives: We aimed to develop a dual-task model to detect and segment nasopharyngeal carcinoma (NPC) automatically in magnetic resource images (MRI) based on deep learning method, since the differential diagnosis of NPC and atypical benign hyperplasia was difficult and the radiotherapy target contouring of NPC was labor-intensive.Materials and methods: A self-constrained 3D DenseNet (SC-DenseNet) architecture was improved using separated training and validation sets. A total of 4100 individuals were finally enrolled and split into the training, validation and WA sets at a proximate ratio of 8:1:1 using simple randomization. The diagnostic metrics of the established model against experienced radiologists was compared in the WA set. The dice similarly coefficient (DSC) of manual and model-defined tumor region was used to evaluate the efficacy of segmentation.Results: Totally, 3142 nasopharyngeal carcinoma (NPC) and 958 benign hyperplasia were included. The SC-DenseNet model showed encouraging performance in detecting NPC, attained a higher overall accuracy, sensitivity and specificity than those of the experienced radiologists (97.77% vs 95.87%, 99.68% vs 99.24% and 91.67% vs 85.21%, respectively). Moreover, the model also exhibited promising performance in automatic segmentation of tumor region in NPC, with an average DSC at 0.77 +/- 0.07 in the test set.Conclusions: The SC-DenseNet model showed competence in automatic detection and segmentation of NPC in MRI, indicating the promising application value as an assistant tool in clinical practice, especially in screening project.