基于深度学习的鼻咽癌放疗磁共振成像中鼻咽部大体肿瘤体积(GTVnx)自动检测与识别
本研究收集200例患者的MRI图像,构建训练验证集与测试集,比较FCN、U-Net、Deeplabv3三种深度学习模型自动勾画鼻咽部大体肿瘤体积(GTVnx)的性能,采用mIoU和mPA评价。Deeplabv3表现最佳(mIoU 0.8529±0.0017,mPA 0.9103±0.0039),FCN稍差,U-Net在检测精度和内存消耗上均明显最差,不建议用于GTVnx自动勾画。
要点
- Deeplabv3检测GTVnx的mIoU为0.8529±0.0017、mPA为0.9103±0.0039,在三种模型中表现最佳。
- FCN检测精度稍差,但与Deeplabv3消耗相近的GPU内存和训练时间。
- U-Net在检测精度和内存消耗上均明显最差,不建议用于GTVnx自动勾画。
核心结论
- 所提出的GTVnx自动靶区勾画框架取得了理想且有前景的结果,可节省人力并使轮廓评估更客观,初步结果为后续研究提供了明确方向。
研究设计与样本
- 收集200例患者的MRI图像用于训练验证集和测试集,比较FCN、U-Net、Deeplabv3三种深度学习模型自动勾画GTVnx。
主要发现
- Deeplabv3检测表现最佳,mIoU为0.8529±0.0017,mPA为0.9103±0.0039。
- FCN在检测精度上稍差,但与Deeplabv3消耗相似的GPU内存和训练时间。
- U-Net在检测精度和内存消耗上均明显最差。
关键数值与推荐
- 采用mIoU和mPA两种评价标准评估检测结果。
- 三种模型在相同公平标准下比较,仅U-Net的学习率设置不同。
临床怎么用
- 原文未据此给出推荐。
局限性
- 原文称该结果为初步结果,并指出为进一步研究提供了明确方向。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
BACKGROUND: In this study, we propose the deep learning model-based framework to automatically delineate nasopharynx gross tumor volume (GTVnx) in MRI images. METHODS: MRI images from 200 patients were collected for training-validation and testing set. Three popular deep learning models (FCN, U-Net, Deeplabv3) are proposed to automatically delineate GTVnx. FCN was the first and simplest fully convolutional model. U-Net was proposed specifically for medical image segmentation. In Deeplabv3, the proposed Atrous Spatial Pyramid Pooling (ASPP) block, and fully connected Conditional Random Field(CRF) may improve the detection of the small scattered distributed tumor parts due to its different scale of spatial pyramid layers. The three models are compared under same fair criteria, except the learning rate set for the U-Net. Two widely applied evaluation standards, mIoU and mPA, are employed for the detection result evaluation. RESULTS: The extensive experiments show that the results of FCN and Deeplabv3 are promising as the benchmark of automatic nasopharyngeal cancer detection. Deeplabv3 performs best with the detection of mIoU 0.8529 ± 0.0017 and mPA 0.9103 ± 0.0039. FCN performs slightly worse in term of detection accuracy. However, both consume similar GPU memory and training time. U-Net performs obviously worst in both detection accuracy and memory consumption. Thus U-Net is not suggested for automatic GTVnx delineation. CONCLUSIONS: The proposed framework for automatic target delineation of GTVnx in nasopharynx bring us the desirable and promising results, which could not only be labor-saving, but also make the contour evaluation more objective. This preliminary results provide us with clear directions for further study.
引用
- Wang Y, Chen H, Lin J, et al. Automatic detection and recognition of nasopharynx gross tumour volume (GTVnx) by deep learning for nasopharyngeal cancer radiotherapy through magnetic resonance imaging. Radiat Oncol. 2023. PMID: 37158943. doi:10.1186/s13014-023-02260-1
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。