文献速递神经技术与安全MR

人工智能系统在脑MRI鉴别诊断准确率上接近神经放射科医生水平

Artificial Intelligence System Approaching Neuroradiologist-level Differential Diagnosis Accuracy at Brain MRI.
PubMed 文献 · Radiology · 2020-04-07

这项回顾性研究评估了人工智能系统在脑MRI上生成鉴别诊断的表现,该系统结合深度学习和贝叶斯网络,在92例独立测试集患者中比较了其与前三位鉴别诊断准确率。人工智能系统前三位准确率为91%,与学术型神经放射科医生(86%)相似(P=0.20),优于放射科住院医师(56%)、普通放射科医生(57%)和神经放射学研究员(77%)。

要点

  • 人工智能系统前三位鉴别诊断准确率91%,与学术型神经放射科医生86%相似(P=0.20)。
  • 人工智能系统优于放射科住院医师56%、普通放射科医生57%和神经放射学研究员77%。
  • 人工智能系统准确率不受疾病患病率影响(常见病93% vs 罕见病85%,P=0.26)。

核心结论

  • 人工智能系统在脑MRI上的前一位、前两位和前三位鉴别诊断准确率总体接近神经放射科医生水平,并超过专科化程度较低的放射科医生。

研究设计与样本

  • 回顾性研究,测试人工智能系统对19种常见和罕见诊断的脑MRI患者进行概率性诊断的表现,MRI采集于2008年1月至2018年1月。
  • 人工智能系统结合数据驱动和领域专家方法,包括深度学习和贝叶斯网络。
  • 首先用深度学习检测病灶,然后通过基于图谱的配准和分割提取18个定量影像特征,再将影像特征与5个临床特征通过贝叶斯推断结合,生成按概率排序的鉴别诊断。
  • 定量特征提取算法和条件概率在86例患者(平均年龄49岁±16,53例女性)的训练集上微调。
  • 在92例独立测试集患者(平均年龄47岁±18,52例女性)中,通过前一位、前两位和前三位鉴别诊断准确率与放射科住院医师、普通放射科医生、神经放射学研究员和学术型神经放射科医生比较。

关键影像表现/征象

  • 人工智能系统前三位鉴别诊断准确率为91%,学术型神经放射科医生为86%(P=0.20)。
  • 放射科住院医师前三位准确率为56%(P<0.001),普通放射科医生为57%(P<0.001),神经放射学研究员为77%(P=0.003)。
  • 人工智能系统对常见病前三位准确率为93%,对罕见病为85%(P=0.26)。
  • 所有放射科医生对常见病诊断准确率为78%,对罕见病为47%(P<0.001)。

诊断标准与关键数值

  • 前三位鉴别诊断准确率:人工智能系统91%,学术型神经放射科医生86%(P=0.20),神经放射学研究员77%(P=0.003),普通放射科医生57%(P<0.001),放射科住院医师56%(P<0.001)。
  • 人工智能系统常见病前三位准确率93% vs 罕见病85%(P=0.26)。
  • 所有放射科医生常见病准确率78% vs 罕见病47%(P<0.001)。

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

Background Although artificial intelligence (AI) shows promise across many aspects of radiology, the use of AI to create differential diagnoses for rare and common diseases at brain MRI has not been demonstrated. Purpose To evaluate an AI system for generation of differential diagnoses at brain MRI compared with radiologists. Materials and Methods This retrospective study tested performance of an AI system for probabilistic diagnosis in patients with 19 common and rare diagnoses at brain MRI acquired between January 2008 and January 2018. The AI system combines data-driven and domain-expertise methodologies, including deep learning and Bayesian networks. First, lesions were detected by using deep learning. Then, 18 quantitative imaging features were extracted by using atlas-based coregistration and segmentation. Third, these image features were combined with five clinical features by using Bayesian inference to develop probability-ranked differential diagnoses. Quantitative feature extraction algorithms and conditional probabilities were fine-tuned on a training set of 86 patients (mean age, 49 years ± 16 [standard deviation]; 53 women). Accuracy was compared with radiology residents, general radiologists, neuroradiology fellows, and academic neuroradiologists by using accuracy of top one, top two, and top three differential diagnoses in 92 independent test set patients (mean age, 47 years ± 18; 52 women). Results For accuracy of top three differential diagnoses, the AI system (91% correct) performed similarly to academic neuroradiologists (86% correct; P = .20), and better than radiology residents (56%; P < .001), general radiologists (57%; P < .001), and neuroradiology fellows (77%; P = .003). The performance of the AI system was not affected by disease prevalence (93% accuracy for common vs 85% for rare diseases; P = .26). Radiologists were more accurate at diagnosing common versus rare diagnoses (78% vs 47% across all radiologists; P < .001). Conclusion An artificial intelligence system for brain MRI approached overall top one, top two, and top three differential diagnoses accuracy of neuroradiologists and exceeded that of less-specialized radiologists. © RSNA, 2020 Online supplemental material is available for this article. See also the editorial by Zaharchuk in this issue.

来源:Radiology,查看原文。版权归原作者所有。

引用

  1. Rauschecker AM, Rudie JD, Xie L, et al. Artificial Intelligence System Approaching Neuroradiologist-level Differential Diagnosis Accuracy at Brain MRI. Radiology. 2020. PMID: 32255417. doi:10.1148/radiol.2020190283

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。