Pogarell Tobias, Bayerl Nadine, Wetzl Matthias, Roth Jan-Peter, Speier Christoph, Cavallaro Alexander, Uder Michael, Dankerl Peter
Department of Radiology, University Hospital Erlangen, Maximiliansplatz 3, 91054 Erlangen, Germany.
Medizinische Fakultät, Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU), Krankenhausstraße 12, 91054 Erlangen, Germany.
Diagnostics (Basel). 2021 Nov 15;11(11):2114. doi: 10.3390/diagnostics11112114.
To evaluate the reader's diagnostic performance against the ground truth with and without the help of a novel content-based image retrieval system (CBIR) that retrieves images with similar CT patterns from a database of 79 different interstitial lung diseases. We evaluated three novice readers' and three resident physicians' (with at least three years of experience) diagnostic performance evaluating 50 different CTs featuring 10 different patterns (e.g., honeycombing, tree-in bud, ground glass, bronchiectasis, etc.) and 24 different diseases (sarcoidosis, UIP, NSIP, Aspergillosis, COVID-19 pneumonia etc.). The participants read the cases first without assistance (and without feedback regarding correctness), and with a 2-month interval in a random order with the assistance of the novel CBIR. To invoke the CBIR, a ROI is placed into the pathologic pattern by the reader and the system retrieves diseases with similar patterns. To further narrow the differential diagnosis, the readers can consult an integrated textbook and have the possibility of selecting high-level semantic features representing clinical information (chronic, infectious, smoking status, etc.). We analyzed readers' accuracy without and with CBIR assistance and further tested the hypothesis that the CBIR would help to improve diagnostic performance utilizing Wilcoxon signed rank test. The novice readers demonstrated an unassisted accuracy of 18/28/44%, and an assisted accuracy of 84/82/90%, respectively. The resident physicians demonstrated an unassisted accuracy of 56/56/70%, and an assisted accuracy of 94/90/96%, respectively. For each reader, as well as overall, Sign test demonstrated statistically significant ( < 0.01) difference between the unassisted and the assisted reads. For students and physicians, Chi²-test and Mann-Whitney-U test demonstrated statistically significant ( < 0.01) difference for unassisted reads and statistically insignificant ( > 0.01) difference for assisted reads. The evaluated CBIR relying on pattern analysis and featuring the option to filter the results of the CBIR by predominant characteristics of the diseases via selecting high-level semantic features helped to drastically improve novices' and resident physicians' accuracy in diagnosing interstitial lung diseases in CT.
为了评估读者在有无新型基于内容的图像检索系统（CBIR）帮助下相对于真实情况的诊断性能，该系统可从包含79种不同间质性肺病的数据库中检索具有相似CT模式的图像。我们评估了三位新手读者和三位住院医师（至少有三年经验）的诊断性能，他们对50种不同的CT进行评估，这些CT具有10种不同模式（如蜂窝状、树芽征、磨玻璃影、支气管扩张等）以及24种不同疾病（结节病、寻常型间质性肺炎、非特异性间质性肺炎、曲霉病、新冠肺炎肺炎等）。参与者首先在无协助的情况下（且无关于正确性的反馈）阅读病例，并在间隔两个月后以随机顺序在新型CBIR的协助下阅读。为调用CBIR，读者将感兴趣区域（ROI）放置在病理模式中，系统会检索具有相似模式的疾病。为进一步缩小鉴别诊断范围，读者可查阅一本综合教科书，并有可能选择代表临床信息（慢性、感染性、吸烟状况等）的高级语义特征。我们分析了读者在无CBIR协助和有CBIR协助时的准确性，并利用Wilcoxon符号秩检验进一步检验了CBIR有助于提高诊断性能的假设。新手读者无协助时的准确率分别为18%/28%/44%，有协助时的准确率分别为84%/82%/90%。住院医师无协助时的准确率分别为56%/56%/70%，有协助时的准确率分别为94%/90%/96%。对于每位读者以及总体而言，符号检验表明无协助阅读和有协助阅读之间存在统计学显著差异（<0.01）。对于学生和医师，卡方检验和曼-惠特尼-U检验表明无协助阅读存在统计学显著差异（<0.01），而有协助阅读无统计学显著差异（>0.01）差异。所评估的基于模式分析且具有通过选择高级语义特征按疾病主要特征过滤CBIR结果选项的CBIR，有助于大幅提高新手和住院医师在CT诊断间质性肺病方面的准确性。
