Background

Evaluation of interstitial lung disease (ILD) at CT is a challenging task that requires experience and is subject to substantial interreader variability.

Purpose

To investigate whether a proposed content-based image retrieval (CBIR) of similar chest CT images by using deep learning can aid in the diagnosis of ILD by readers with different levels of experience.

Materials and Methods

This retrospective study included patients with confirmed ILD after multidisciplinary discussion and available CT images identified between January 2000 and December 2015. Database was composed of four disease classes: usual interstitial pneumonia (UIP), nonspecific interstitial pneumonia (NSIP), cryptogenic organizing pneumonia, and chronic hypersensitivity pneumonitis. Eighty patients were selected as queries from the database. The proposed CBIR retrieved the top three similar CT images with diagnosis from the database by comparing the extent and distribution of different regional disease patterns quantified by a deep learning algorithm. Eight readers with varying experience interpreted the query CT images and provided their most probable diagnosis in two reading sessions 2 weeks apart, before and after applying CBIR. Diagnostic accuracy was analyzed by using McNemar test and generalized estimating equation, and interreader agreement was analyzed by using Fleiss κ.

Results

A total of 288 patients were included (mean age, 58 years ± 11 [standard deviation]; 145 women). After applying CBIR, the overall diagnostic accuracy improved in all readers (before CBIR, 46.1% [95% CI: 37.1, 55.3]; after CBIR, 60.9% [95% CI: 51.8, 69.3]; P < .001). In terms of disease category, the diagnostic accuracy improved after applying CBIR in UIP (before vs after CBIR, 52.4% vs 72.8%, respectively; P < .001) and NSIP cases (before vs after CBIR, 42.9% vs 61.6%, respectively; P < .001). Interreader agreement improved after CBIR (before vs after CBIR Fleiss κ, 0.32 vs 0.47, respectively; P = .005).

Conclusion

The proposed content-based image retrieval system for chest CT images with deep learning improved the diagnostic accuracy of interstitial lung disease and interreader agreement in readers with different levels of experience.

© RSNA, 2021

Online supplemental material is available for this article.

See also the editorial by Wielpütz in this issue.

中文翻译：

---

使用深度学习的基于内容的图像检索用于胸部 CT 间质性肺疾病的诊断

背景

在 CT 上评估间质性肺病 (ILD) 是一项具有挑战性的任务，需要经验并且受大量读者间变异性的影响。

目的

研究通过使用深度学习对相似胸部 CT 图像进行基于内容的图像检索 (CBIR) 是否可以帮助具有不同经验水平的读者诊断 ILD。

材料和方法

这项回顾性研究包括在 2000 年 1 月至 2015 年 12 月期间确定的多学科讨论和可用 CT 图像后确诊的 ILD 患者。数据库由四个疾病类别组成：普通间质性肺炎 (UIP)、非特异性间质性肺炎 (NSIP)、隐源性机化性肺炎和慢性过敏性肺炎。从数据库中选择了 80 名患者作为查询。所提出的 CBIR 通过比较由深度学习算法量化的不同区域疾病模式的程度和分布，从数据库中检索到前三张相似的诊断 CT 图像。八位具有不同经验的读者解释了查询 CT 图像，并在应用 CBIR 之前和之后的两个阅读会话中提供了他们最可能的诊断，相隔 2 周。

结果

共纳入 288 名患者（平均年龄 58 岁 ± 11 [标准差]；145 名女性）。应用 CBIR 后，所有读卡器的总体诊断准确性均有所提高（CBIR 前为 46.1% [95% CI: 37.1, 55.3]；CBIR 后为 60.9% [95% CI: 51.8, 69.3]；P < .001）。在疾病类别方面，在 UIP（CBIR 之前和之后，分别为 52.4% 和 72.8%；P < .001）和 NSIP 病例（CBIR 之前和之后，分别为 42.9% 和 61.6%）应用 CBIR 后，诊断准确性有所提高; P < .001)。CBIR 后读者间一致性得到改善（CBIR Fleiss κ 前后分别为 0.32 和 0.47；P = .005）。

结论

所提出的基于内容的深度学习胸部 CT 图像检索系统提高了间质性肺病的诊断准确性和不同经验水平读者的读者间一致性。

© 北美放射学会，2021

本文提供在线补充材料。

另见本期 Wielpütz 的社论。