Sun Yat-sen University Cancer Center, State Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Guangdong Key Laboratory of Nasopharyngeal Carcinoma Diagnosis and Therapy, Guangzhou 510060, PR China; Department of Radiology, Sun Yat-Sen University Cancer Center, Guangzhou 510060, PR China.
Sun Yat-sen University Cancer Center, State Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Guangdong Key Laboratory of Nasopharyngeal Carcinoma Diagnosis and Therapy, Guangzhou 510060, PR China; Department of Information, Sun Yat-Sen University Cancer Center, Guangzhou 510060, PR China.
Oral Oncol. 2020 Nov;110:104862. doi: 10.1016/j.oraloncology.2020.104862. Epub 2020 Jun 29.
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.
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 test 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 test set. The dice similarity coefficient (DSC) of manual and model-defined tumor region was used to evaluate the efficacy of segmentation.
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.
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.
我们旨在开发一种双重任务模型，通过深度学习方法自动检测和分割磁共振成像（MRI）中的鼻咽癌（NPC），因为 NPC 与非典型良性增生的鉴别诊断较为困难，且 NPC 的放疗靶区勾画非常耗时。
使用分离的训练集和验证集改进了一种自约束 3D DenseNet（SC-DenseNet）架构。最终共纳入 4100 名个体，并使用简单随机化按近似 8:1:1 的比例将其分为训练集、验证集和测试集。在测试集中比较了该模型与有经验的放射科医生的诊断指标。使用手动和模型定义的肿瘤区域的骰子相似系数（DSC）来评估分割的效果。
共纳入 3142 例 NPC 和 958 例良性增生。SC-DenseNet 模型在检测 NPC 方面表现出令人鼓舞的性能，其整体准确性、敏感性和特异性均高于有经验的放射科医生（97.77%比 95.87%，99.68%比 99.24%和 91.67%比 85.21%）。此外，该模型在 NPC 肿瘤区域的自动分割中也表现出良好的性能，在测试集中的平均 DSC 为 0.77±0.07。
SC-DenseNet 模型在 MRI 中 NPC 的自动检测和分割方面表现出良好的性能，表明其作为临床实践辅助工具具有良好的应用价值，尤其是在筛查项目中。
