Performance of a deep learning-based lung nodule detection system as an alternative reader in a Chinese lung cancer screening program

• Published in: European journal of radiology 2022-01, Vol.146, p.110068-110068, Article 110068
• Main Authors: Cui, Xiaonan, Zheng, Sunyi, Heuvelmans, Marjolein A., Du, Yihui, Sidorenkov, Grigory, Fan, Shuxuan, Li, Yanju, Xie, Yongsheng, Zhu, Zhongyuan, Dorrius, Monique D., Zhao, Yingru, Veldhuis, Raymond N.J., de Bock, Geertruida H., Oudkerk, Matthijs, van Ooijen, Peter M.A., Vliegenthart, Rozemarijn, Ye, Zhaoxiang
• Format: Article
• Language: English
• Subjects: Artificial intelligence; China - epidemiology; Computed tomography; Computer-assisted diagnosis; Deep Learning; Early Detection of Cancer; Humans; Lung - diagnostic imaging; Lung Neoplasms - diagnostic imaging; Pulmonary nodules; Radiographic Image Interpretation, Computer-Assisted; Reproducibility of Results; Sensitivity and Specificity; Solitary Pulmonary Nodule - diagnostic imaging; Tomography, X-Ray Computed
• ISSN: 0720-048X; 1872-7727
• DOI: 10.1016/j.ejrad.2021.110068

To evaluate the performance of a deep learning-based computer-aided detection (DL-CAD) system in a Chinese low-dose CT (LDCT) lung cancer screening program. One-hundred-and-eighty individuals with a lung nodule on their baseline LDCT lung cancer screening scan were randomly mixed with screenees without nodules in a 1:1 ratio (total: 360 individuals). All scans were assessed by double reading and subsequently processed by an academic DL-CAD system. The findings of double reading and the DL-CAD system were then evaluated by two senior radiologists to derive the reference standard. The detection performance was evaluated by the Free Response Operating Characteristic curve, sensitivity and false-positive (FP) rate. The senior radiologists categorized nodules according to nodule diameter, type (solid, part-solid, non-solid) and Lung-RADS. The reference standard consisted of 262 nodules ≥ 4 mm in 196 individuals; 359 findings were considered false positives. The DL-CAD system achieved a sensitivity of 90.1% with 1.0 FP/scan for detection of lung nodules regardless of size or type, whereas double reading had a sensitivity of 76.0% with 0.04 FP/scan (P = 0.001). The sensitivity for detection of nodules ≥ 4 - ≤ 6 mm was significantly higher with DL-CAD than with double reading (86.3% vs. 58.9% respectively; P = 0.001). Sixty-three nodules were only identified by the DL-CAD system, and 27 nodules only found by double reading. The DL-CAD system reached similar performance compared to double reading in Lung-RADS 3 (94.3% vs. 90.0%, P = 0.549) and Lung-RADS 4 nodules (100.0% vs. 97.0%, P = 1.000), but showed a higher sensitivity in Lung-RADS 2 (86.2% vs. 65.4%, P