文献速递胸部CT

基于深度学习与CT图像的肺纤维化计算机辅助诊断

Computer-Aided Diagnosis of Pulmonary Fibrosis Using Deep Learning and CT Images.
PubMed 文献 · Invest Radiol · 2019-01-01

本研究评估INTACT计算机辅助诊断系统将高分辨率CT图像自动分类为4类放射学诊断类别的性能,并与放射科医生比较。共纳入105例肺纤维化病例(54例非特异性间质性肺炎,51例普通型间质性肺炎),诊断均为间质性肺病委员会共识诊断。结果显示INTACT系统分类准确率与读片者相似,4分类准确率分别为0.56、0.6和0.54(P>0.45)。

要点

  • INTACT系统对肺纤维化4分类的准确率为0.56,与读片者1的0.6和读片者2的0.54相似(P>0.45)。
  • 在二分类(是否需要活检)中,INTACT系统准确率为0.81,与读片者1的0.81和读片者2的0.70相似。
  • INTACT系统F-score为0.56,读片者平均为0.57(P=0.991);二分类中分别为0.80和0.79(P=0.898)。

核心结论

  • 基于机器学习的计算机辅助检测算法对特发性肺纤维化的分类准确率与人类读片者相似。

研究设计与样本

  • 回顾性研究,共纳入105例肺纤维化病例(54例非特异性间质性肺炎,51例普通型间质性肺炎),所有诊断均为间质性肺病委员会共识诊断(放射学或组织学证实),从本中心数据库回顾性选取。
  • 由两名专科胸部放射科医生根据Fleischner学会建议达成共识作为放射学诊断参考标准。
  • INTACT系统为顺序处理流程:先分割肺部解剖结构,再识别和表征各类病理肺组织,然后将信息输入随机森林分类器以推荐放射学诊断。
  • 比较INTACT系统与两名不同年资放射科医生(读片者1和读片者2)在相同任务上的性能。

诊断标准与关键数值

  • 4分类准确率:读片者1为0.6,读片者2为0.54,INTACT系统为0.56,P>0.45。
  • 4分类F-score:INTACT系统为0.56,两名读片者平均为0.57,P=0.991。
  • 二分类(有/无活检需要)准确率:读片者1为0.81,读片者2为0.70,INTACT系统为0.81。
  • 二分类F-score:INTACT系统为0.80,读片者平均为0.79,P=0.898。

临床应用与阅片要点

  • 原文未据此给出推荐。

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 objective of this study is to assess the performance of a computer-aided diagnosis (CAD) system (INTACT system) for the automatic classification of high-resolution computed tomography images into 4 radiological diagnostic categories and to compare this with the performance of radiologists on the same task.

MATERIALS AND METHODS: For the comparison, a total of 105 cases of pulmonary fibrosis were studied (54 cases of nonspecific interstitial pneumonia and 51 cases of usual interstitial pneumonia). All diagnoses were interstitial lung disease board consensus diagnoses (radiologically or histologically proven cases) and were retrospectively selected from our database. Two subspecialized chest radiologists made a consensual ground truth radiological diagnosis, according to the Fleischner Society recommendations. A comparison analysis was performed between the INTACT system and 2 other radiologists with different years of experience (readers 1 and 2). The INTACT system consists of a sequential pipeline in which first the anatomical structures of the lung are segmented, then the various types of pathological lung tissue are identified and characterized, and this information is then fed to a random forest classifier able to recommend a radiological diagnosis.

RESULTS: Reader 1, reader 2, and INTACT achieved similar accuracy for classifying pulmonary fibrosis into the original 4 categories: 0.6, 0.54, and 0.56, respectively, with P > 0.45. The INTACT system achieved an F-score (harmonic mean for precision and recall) of 0.56, whereas the 2 readers, on average, achieved 0.57 (P = 0.991). For the pooled classification (2 groups, with and without the need for biopsy), reader 1, reader 2, and CAD had similar accuracies of 0.81, 0.70, and 0.81, respectively. The F-score was again similar for the CAD system and the radiologists. The CAD system and the average reader reached F-scores of 0.80 and 0.79 (P = 0.898).

CONCLUSIONS: We found that a computer-aided detection algorithm based on machine learning was able to classify idiopathic pulmonary fibrosis with similar accuracy to a human reader.

来源:Invest Radiol,查看原文。版权归原作者所有。

引用

  1. Christe A, Peters AA, Drakopoulos D, et al. Computer-Aided Diagnosis of Pulmonary Fibrosis Using Deep Learning and CT Images. Invest Radiol. 2019. PMID: 31483764. doi:10.1097/RLI.0000000000000574

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。