Lange Marcia, Boddu Priyanka, Singh Ayushi, Gross Benjamin D, Mei Xueyan, Liu Zelong, Bernheim Adam, Chung Michael, Huang Mingqian, Masseaux Joy, Dua Sakshi, Platt Samantha, Sivakumar Ganesh, DeMarco Cody, Lee Justine, Fayad Zahi A, Yang Yang, Padilla Maria, Jacobi Adam
Icahn School of Medicine at Mount Sinai, One Gustave L. Levy Place, New York, NY 10029, United States of America.
Department of Diagnostic, Molecular, and Interventional Radiology, Icahn School of Medicine at Mount Sinai, One Gustave L. Levy Place, New York, NY 10029, United States of America.
Clin Imaging. 2023 May;97:14-21. doi: 10.1016/j.clinimag.2022.12.010. Epub 2023 Jan 2.
Interpretation of high-resolution CT images plays an important role in the diagnosis and management of interstitial lung diseases. However, interreader variation may exist due to varying levels of training and expertise. This study aims to evaluate interreader variation and the role of thoracic radiology training in classifying interstitial lung disease (ILD).
This is a retrospective study where seven physicians (radiologists, thoracic radiologists, and a pulmonologist) classified the subtypes of ILD of 128 patients from a tertiary referral center, all selected from the Interstitial Lung Disease Registry which consists of patients from November 2014 to January 2021. Each patient was diagnosed with a subtype of interstitial lung disease by a consensus diagnosis from pathology, radiology, and pulmonology. Each reader was provided with only clinical history, only CT images, or both. Reader sensitivity and specificity and interreader agreements using Cohen's κ were calculated.
Interreader agreement based only on clinical history, only on radiologic information, or combination of both was most consistent amongst readers with thoracic radiology training, ranging from fair (Cohen's κ: 0.2-0.46), moderate to almost perfect (Cohen's κ: 0.55-0.92), and moderate to almost perfect (Cohen's κ: 0.53-0.91) respectively. Radiologists with any thoracic training showed both increased sensitivity and specificity for NSIP as compared to other radiologists and the pulmonologist when using only clinical history, only CT information, or combination of both (p < 0.05).
Readers with thoracic radiology training showed the least interreader variation and were more sensitive and specific at classifying certain subtypes of ILD.
Thoracic radiology training may improve sensitivity and specificity in classifying ILD based on HRCT images and clinical history.
高分辨率CT图像的解读在间质性肺疾病的诊断和管理中起着重要作用。然而，由于培训水平和专业知识的不同，读者之间可能存在差异。本研究旨在评估读者间的差异以及胸部放射学培训在间质性肺疾病（ILD）分类中的作用。
这是一项回顾性研究，七名医生（放射科医生、胸部放射科医生和一名肺科医生）对一家三级转诊中心128例患者的ILD亚型进行分类，所有患者均选自2014年11月至2021年1月的间质性肺疾病登记处。通过病理学、放射学和肺科的共识诊断，每位患者被诊断为一种间质性肺疾病亚型。每位读者仅获得临床病史、仅获得CT图像或两者都有。计算读者的敏感性、特异性以及使用科恩κ系数的读者间一致性。
仅基于临床病史、仅基于放射学信息或两者结合的读者间一致性在接受胸部放射学培训的读者中最为一致，分别为一般（科恩κ系数：0.2 - 0.46）、中等至几乎完美（科恩κ系数：0.55 - 0.92）和中等至几乎完美（科恩κ系数：0.53 - 0.91）。与其他放射科医生和肺科医生相比，接受过任何胸部培训的放射科医生在仅使用临床病史、仅使用CT信息或两者结合时，对非特异性间质性肺炎（NSIP）的敏感性和特异性均有所提高（p < 0.05）。
接受胸部放射学培训的读者在读者间差异最小，并且在对某些ILD亚型进行分类时更敏感和特异。
胸部放射学培训可能会提高基于高分辨率CT图像和临床病史对ILD进行分类的敏感性和特异性。
