深度学习用于肝脏肿瘤诊断第二部分:利用影像学特征解释卷积神经网络
本研究开发了一种可解释的深度学习原型,基于多期MRI上494个肝脏病变训练卷积神经网络分类六种肝脏肿瘤,并对60个测试病变推断关键影像特征的存在。该系统识别正确影像特征的阳性预测值为76.5%、敏感度为82.9%,模型对12%的病变分类错误。特征图与原始图像体素一致,特征相关性评分倾向于反映各类别最突出的影像学标准。
要点
- 可解释深度学习系统能识别影像特征并显示特征在图像上的位置。
- 识别正确影像特征的阳性预测值为76.5%、敏感度为82.9%。
- 模型对12%的病变分类错误,错误特征在误分类病变中更常见。
核心结论
- 该可解释深度学习系统通过分析内部层并自动描述贡献于预测的特征,展示了阐明预训练深度神经网络部分决策原理的概念验证。
研究设计与样本
- 研究为概念验证性可解释深度学习原型开发,使用多期MRI上494个肝脏病变训练卷积神经网络分类六种肝脏肿瘤实体,每个病变类别的一个子集被标记最多四个关键影像特征,通过分析预训练CNN模型的激活模式在60个病变的测试集中推断这些特征的存在。
诊断标准与关键数值
- 可解释深度学习系统识别每个测试病变中存在的正确影像特征的阳性预测值为76.5%,敏感度为82.9%;模型对12%的病变分类错误;错误特征在误分类病变中的出现率为85.6%,在正确识别病变中为60.4%。
临床应用与阅片要点
- 作者认为可解释深度学习系统通过提供各种影像特征在鉴别诊断中重要性的反馈,有潜力与LI-RADS等标准化报告系统对接,验证辅助特征并提高临床实用性;该系统可能为放射学报告增加定量数据,并为放射科医生提供基于证据的决策支持。
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)。
英文原文(摘要)· 点击展开
OBJECTIVES: To develop a proof-of-concept "interpretable" deep learning prototype that justifies aspects of its predictions from a pre-trained hepatic lesion classifier.
METHODS: A convolutional neural network (CNN) was engineered and trained to classify six hepatic tumor entities using 494 lesions on multi-phasic MRI, described in Part 1. A subset of each lesion class was labeled with up to four key imaging features per lesion. A post hoc algorithm inferred the presence of these features in a test set of 60 lesions by analyzing activation patterns of the pre-trained CNN model. Feature maps were generated that highlight regions in the original image that correspond to particular features. Additionally, relevance scores were assigned to each identified feature, denoting the relative contribution of a feature to the predicted lesion classification.
RESULTS: The interpretable deep learning system achieved 76.5% positive predictive value and 82.9% sensitivity in identifying the correct radiological features present in each test lesion. The model misclassified 12% of lesions. Incorrect features were found more often in misclassified lesions than correctly identified lesions (60.4% vs. 85.6%). Feature maps were consistent with original image voxels contributing to each imaging feature. Feature relevance scores tended to reflect the most prominent imaging criteria for each class.
CONCLUSIONS: This interpretable deep learning system demonstrates proof of principle for illuminating portions of a pre-trained deep neural network's decision-making, by analyzing inner layers and automatically describing features contributing to predictions.
KEY POINTS: • An interpretable deep learning system prototype can explain aspects of its decision-making by identifying relevant imaging features and showing where these features are found on an image, facilitating clinical translation. • By providing feedback on the importance of various radiological features in performing differential diagnosis, interpretable deep learning systems have the potential to interface with standardized reporting systems such as LI-RADS, validating ancillary features and improving clinical practicality. • An interpretable deep learning system could potentially add quantitative data to radiologic reports and serve radiologists with evidence-based decision support.
引用
- Wang CJ, Hamm CA, Savic LJ, et al. Deep learning for liver tumor diagnosis part II: convolutional neural network interpretation using radiologic imaging features. Eur Radiol. 2019. PMID: 31093705. doi:10.1007/s00330-019-06214-8
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。