Department of Respiratory and Critical Care Medicine, Nanjing Drum Tower Hospital, The Affiliated Hospital of Nanjing University Medical School, Nanjing, Jiangsu, China.
Nanjing Institute of Respiratory Diseases, Nanjing, Jiangsu, China.
BMJ Open Respir Res. 2024 Mar 9;11(1):e002226. doi: 10.1136/bmjresp-2023-002226.
Acute exacerbation of idiopathic pulmonary fibrosis (AE-IPF) is the primary cause of death in patients with IPF, characterised by diffuse, bilateral ground-glass opacification on high-resolution CT (HRCT). This study proposes a three-dimensional (3D)-based deep learning algorithm for classifying AE-IPF using HRCT images.
A novel 3D-based deep learning algorithm, SlowFast, was developed by applying a database of 306 HRCT scans obtained from two centres. The scans were divided into four separate subsets (training set, n=105; internal validation set, n=26; temporal test set 1, n=79; and geographical test set 2, n=96). The final training data set consisted of 1050 samples with 33 600 images for algorithm training. Algorithm performance was evaluated using accuracy, sensitivity, specificity, positive predictive value, negative predictive value, receiver operating characteristic (ROC) curve and weighted κ coefficient.
The accuracy of the algorithm in classifying AE-IPF on the test sets 1 and 2 was 93.9% and 86.5%, respectively. Interobserver agreements between the algorithm and the majority opinion of the radiologists were good (κw=0.90 for test set 1 and κw=0.73 for test set 2, respectively). The ROC accuracy of the algorithm for classifying AE-IPF on the test sets 1 and 2 was 0.96 and 0.92, respectively. The algorithm performance was superior to visual analysis in accurately diagnosing radiological findings. Furthermore, the algorithm's categorisation was a significant predictor of IPF progression.
The deep learning algorithm provides high auxiliary diagnostic efficiency in patients with AE-IPF and may serve as a useful clinical aid for diagnosis.
特发性肺纤维化（IPF）的急性加重（AE-IPF）是 IPF 患者死亡的主要原因，其特征是高分辨率 CT（HRCT）上弥漫性双侧磨玻璃影。本研究提出了一种基于三维（3D）的深度学习算法，用于对 HRCT 图像进行 AE-IPF 分类。
通过应用来自两个中心的 306 例 HRCT 扫描数据库，开发了一种新的基于 3D 的深度学习算法 SlowFast。扫描分为四个独立的子集（训练集，n=105；内部验证集，n=26；时间测试集 1，n=79；和地理测试集 2，n=96）。最终的训练数据集包含 1050 个样本，共 33600 张图像用于算法训练。使用准确性、敏感性、特异性、阳性预测值、阴性预测值、受试者工作特征（ROC）曲线和加权κ系数评估算法性能。
算法在测试集 1 和 2 上分类 AE-IPF 的准确率分别为 93.9%和 86.5%。算法与放射科医生多数意见之间的观察者间一致性良好（测试集 1 为κw=0.90，测试集 2 为κw=0.73）。算法在测试集 1 和 2 上分类 AE-IPF 的 ROC 准确性分别为 0.96 和 0.92。与视觉分析相比，该算法在准确诊断影像学发现方面具有更高的辅助诊断效率。此外，该算法的分类是 IPF 进展的一个重要预测因素。
深度学习算法在 AE-IPF 患者中提供了较高的辅助诊断效率，可作为一种有用的临床辅助诊断工具。
