传统磁共振成像深度学习提高多发性硬化模拟病的诊断
回顾性收集268例脑MRI扫描(偏头痛56例、多发性硬化70例、视神经脊髓炎谱系疾病91例、中枢神经系统血管炎51例),训练深度学习模型,并在90例独立测试集上与2名神经放射学专家比较;模型总体分类准确率优于专家,多发性硬化和视神经脊髓炎谱系疾病诊断准确率最高和最低分别见于多发性硬化和视神经脊髓炎谱系疾病。
要点
- 深度学习在测试集上对多发性硬化的诊断准确率98.8%,高于阅片者1的72.8%和阅片者2的81.8%(P<0.001)。
- 深度学习对神经脊髓炎谱系疾病的准确率88.6%,而两名阅片者均为4.4%(P<0.001)。
- 模型总体鉴别白质病变的准确率超过专家阅片者,最差误诊发生在神经脊髓炎谱系疾病与血管炎或偏头痛之间。
核心结论
- 神经网络在基于磁共振成像的白质病变分类准确率上优于专家阅片者,可能有助于其诊断检查。
研究设计与样本
- 回顾性研究,共纳入268例T2加权和T1加权脑磁共振成像扫描,来自偏头痛患者56例、多发性硬化患者70例、神经脊髓炎谱系疾病患者91例和中枢神经系统血管炎患者51例。
- 神经网络架构基于4个三维卷积层级联,特征提取后接全稠密层,在178例扫描上训练。
- 在90例扫描的独立测试集上比较最终算法与神经放射学专家的分类能力。
诊断标准与关键数值
- 测试集中深度学习与专家阅片者对多发性硬化的诊断准确率最高:深度学习98.8%,阅片者1为72.8%(P<0.001),阅片者2为81.8%(P<0.001)。
- 对神经脊髓炎谱系疾病的诊断准确率最低:深度学习88.6%,两名阅片者均为4.4%(P<0.001)。
- 对偏头痛的诊断准确率:深度学习92.2%,阅片者1为53%(P=0.03),阅片者2为64.8%(P=0.01)。
- 对血管炎的诊断准确率:深度学习92.1%,阅片者1为54.6%(P=0.3),阅片者2为45.5%(P=0.2)。
- 阅片者间一致性为84.9%(Cohen κ=0.78,P<0.001)。
临床应用与阅片要点
- 作者认为神经网络在基于磁共振成像的白质病变分类准确率上优于专家阅片者,可能有助于其诊断检查。
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: The aims of this study were to present a deep learning approach for the automated classification of multiple sclerosis and its mimics and compare model performance with that of 2 expert neuroradiologists.
MATERIALS AND METHODS: A total of 268 T2-weighted and T1-weighted brain magnetic resonance imagin scans were retrospectively collected from patients with migraine (n = 56), multiple sclerosis (n = 70), neuromyelitis optica spectrum disorders (n = 91), and central nervous system vasculitis (n = 51). The neural network architecture, trained on 178 scans, was based on a cascade of 4 three-dimensional convolutional layers, followed by a fully dense layer after feature extraction. The ability of the final algorithm to correctly classify the diseases in an independent test set of 90 scans was compared with that of the neuroradiologists.
RESULTS: The interrater agreement was 84.9% (Cohen κ = 0.78, P < 0.001). In the test set, deep learning and expert raters reached the highest diagnostic accuracy in multiple sclerosis (98.8% vs 72.8%, P < 0.001, for rater 1; and 81.8%, P < 0.001, for rater 2) and the lowest in neuromyelitis optica spectrum disorders (88.6% vs 4.4%, P < 0.001, for both raters), whereas they achieved intermediate values for migraine (92.2% vs 53%, P = 0.03, for rater 1; and 64.8%, P = 0.01, for rater 2) and vasculitis (92.1% vs 54.6%, P = 0.3, for rater 1; and 45.5%, P = 0.2, for rater 2). The overall performance of the automated method exceeded that of expert raters, with the worst misdiagnosis when discriminating between neuromyelitis optica spectrum disorders and vasculitis or migraine.
CONCLUSIONS: A neural network performed better than expert raters in terms of accuracy in classifying white matter disorders from magnetic resonance imaging and may help in their diagnostic work-up.
引用
- Rocca MA, Anzalone N, Storelli L, et al. Deep Learning on Conventional Magnetic Resonance Imaging Improves the Diagnosis of Multiple Sclerosis Mimics. Invest Radiol. 2021. PMID: 33109920. doi:10.1097/RLI.0000000000000735
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。