基于MRI数据准确可靠分类椎间盘退变的深度学习模型
研究基于1599例患者(7948个椎间盘)的MRI数据训练深度卷积神经网络,自动按Pfirrmann分级评估椎间盘退变;默认交叉熵分类器获得κ=0.92的可靠性、平均敏感度90.2%、平均精确率92.5%,99.2%的验证病例预测与真实分级相差不超过1级。
要点
- 模型按Pfirrmann分级自动评估椎间盘退变,可靠性κ=0.92,平均敏感度90.2%、平均精确率92.5%。
- 99.2%的验证病例网络预测与真实分级相差不超过1个Pfirrmann等级。
- 以序数回归框架,预测与真实分级的平均绝对误差为0.08个Pfirrmann等级,相关性r=0.96。
核心结论
- 该深度卷积神经网络分类器可靠性κ>0.9,明显优于平均人类评分者间及评分者内可靠性;平均敏感度超过90%,超过现有自动分级椎间盘退变的机器学习方案。
研究设计与样本
- 基于深度卷积神经网络分类器,训练集为1599例患者(7948个椎间盘)的手工评估数据;模型开发与超参数优化采用固定90%/10%训练/验证集划分,并以10折交叉验证估计真实预测性能。
关键影像表现/征象
- 所评估图像数据的退变等级呈高斯分布,因此训练集中1级和5级略被低估。
- 默认交叉熵分类器获得κ=0.92(Cohen κ)、平均敏感度90.2%、平均精确率92.5%。
- 99.2%的验证病例网络预测与真实分级最多相差1个Pfirrmann等级。
- 以序数回归问题框架,预测与真实分级的平均绝对误差为0.08个Pfirrmann等级,相关性r=0.96。
- 10折交叉验证结果证实上述性能估计,提示无实质性过拟合。
诊断标准与关键数值
- 默认交叉熵分类器:可靠性κ=0.92(Cohen κ),平均敏感度90.2%,平均精确率92.5%。
- 验证病例中99.2%的网络预测与真实分级相差不超过1个Pfirrmann等级。
- 序数回归框架下平均绝对误差0.08个Pfirrmann等级,相关性r=0.96。
临床应用与阅片要点
- 模型可基于常规临床MRI数据自动、可重复地按Pfirrmann分级评估椎间盘退变。
- 更复杂的损失函数(soft kappa损失、序数交叉熵损失或回归损失)、基于类别的损失加权或类别合并未带来整体分类性能改善。
局限性
- 所评估图像数据的退变等级呈高斯分布,训练集中1级和5级略被低估。
- 更复杂的损失函数、基于类别的损失加权或类别合并未带来整体分类性能改善。
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)。
英文原文(摘要)· 点击展开
OBJECTIVES: Although magnetic resonance imaging-based formalized grading schemes for intervertebral disc degeneration offer improved reproducibility compared with purely subjective ratings, their intrarater and interrater reliability are not nearly good enough to be able to detect small to medium effects in clinical longitudinal studies. The aim of this study thus was to develop a method that enables automatic and therefore reproducible and reliable evaluation of disc degeneration based on conventional clinical image data and Pfirrmann's grading scheme.
MATERIALS AND METHODS: We propose a classifier based on a deep convolutional neural network that we trained on a large, manually evaluated data set of 1599 patients (7948 intervertebral discs). To improve upon the status quo, we focused on the quality of the training data and performed extensive hyperparameter optimization. We assessed the potential benefits of optimizing loss functions beyond common cross-entropy loss, such as soft kappa loss, ordinal cross-entropy loss, or regression losses. We furthermore experimented with ways to mitigate class imbalance by pooling classes or using class-weighted loss functions. During model development and hyperparameter optimization, we used a fixed 90%/10% training/validation set split. To estimate real-world prediction performance, we performed 10-fold cross-validation.
RESULTS: The evaluated image data results in a Gaussian degeneration grade distribution, and thus grades 1 and 5 are slightly underrepresented in the training set. Our default cross-entropy-based classifier achieves a reliability of κ = 0.92 (Cohen κ), an average sensitivity of 90.2%, and an average precision of 92.5%. In 99.2% of validation cases, the network's prediction deviates at most 1 Pfirrmann grades from the ground truth. Framed as an ordinal regression problem, the mean absolute error between the ground truth and the prediction is 0.08 Pfirrmann grade with a correlation of r = 0.96. The results of the 10-fold cross validation confirm those performance estimates, indicating no substantial overfitting. More sophisticated loss functions, class-based loss weighting, or class pooling did not lead to improved classification performance overall.
CONCLUSIONS: With a reliability of κ > 0.9, our system clearly outperforms average human interrater as well as intrarater reliability. With an average sensitivity of more than 90%, our classifier also surpasses state-of-the-art machine learning solutions for automatically grading disc degeneration.
引用
- Niemeyer F, Galbusera F, Tao Y, et al. A Deep Learning Model for the Accurate and Reliable Classification of Disc Degeneration Based on MRI Data. Invest Radiol. 2021. PMID: 32694451. doi:10.1097/RLI.0000000000000709
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。