头颈部放疗正常组织自动分割的原型深度学习算法与商业算法的比较评估
研究使用864例头颈癌病例训练和评估一种基于全卷积网络的原型深度学习自动分割算法,并在75例验证病例上与两种商业模型比较。原型算法在DSC、VPM、HD等五项指标上最接近金标准数据,平均DSC为0.81,93%的结构被评为临床可用,但同一算法在不同机构训练时结果存在差异。
要点
- 原型算法在75例验证病例中平均DSC为0.81,优于两种商业模型(0.74和0.66)。
- 93%的原型模型结构被主观评估为临床可用。
- 同一商业算法在不同机构数据训练时分割结果存在差异。
核心结论
- 原型算法性能优于商业算法,即使使用相同数据训练也得到验证。
- 同一算法在不同机构训练时,自动分割结果可能不同。
研究设计与样本
- 共864例头颈癌病例用于训练和评估原型算法,验证集为75例。
- 原型算法基于全卷积网络,结合U-Net和V-net,使用Dice损失加交叉熵损失函数和Adam优化器训练。
- 验证病例生成三组OAR集:A为金标准数据训练的原型模型,B为相同数据训练的商业软件,C为另一机构数据训练的商业软件。
- 评估指标包括Dice相似系数(DSC)、Hausdorff距离(HD)、体素惩罚度量(VPM)和剂量体积直方图下面积DSC,并对20例随机病例进行主观定性评估。
主要发现
- 五种指标总体趋势均显示原型算法最接近金标准数据。
- 算法A、B、C的平均DSC分别为0.81、0.74、0.66,VPM分别为84.1、62.8、46.8,HD分别为1.6 mm、3.2 mm、3.3 mm。
- 93%的模型A结构被评估为临床有用。
局限性
- 原文未报告局限性。
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
PURPOSE: To introduce and validate a newly developed deep-learning (DL) auto-segmentation algorithm for head and neck (HN) organs at risk (OARs) and to compare its performance with a published commercial algorithm. METHODS: A total of 864 HN cancer cases were available to train and evaluate a prototype algorithm. The algorithm is based on a fully convolutional network with combined U-Net and V-net. A Dice loss plus Cross-Entropy Loss function with Adam optimizer was used in training. For 75 validation cases, OAR sets were generated with three DL-based models (A: the prototype model trained with gold data, B: a commercial software trained with the same data, and C: the same software trained with data from another institution). The auto-segmented structures were evaluated with Dice similarity coefficient (DSC), Hausdorff distance (HD), voxel-penalty metric (VPM) and DSC of area under dose-volume histograms. A subjective qualitative evaluation was performed on 20 random cases. RESULTS: Overall trend was for the prototype algorithm to be the closest to the gold data by all five metrics. The average DSC/VPM/HD for algorithms A, B, and C were 0.81/84.1/1.6 mm, 0.74/62.8/3.2 mm, and 0.66/46.8/3.3 mm, respectively. 93% of model A structures were evaluated to be clinically useful. CONCLUSION: The superior performance of the prototype was validated, even when trained with the same data. In addition to the challenges of perfecting the algorithms, the auto-segmentation results can differ when the same algorithm is trained at different institutions.
引用
- Koo J, Caudell JJ, Latifi K, et al. Comparative evaluation of a prototype deep learning algorithm for autosegmentation of normal tissues in head and neck radiotherapy. Radiother Oncol. 2022. PMID: 35817322. doi:10.1016/j.radonc.2022.06.024
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。