TY - JOUR
T1 - Performance of a deep learning-based lung nodule detection system as an alternative reader in a Chinese lung cancer screening program
AU - Cui, Xiaonan
AU - Zheng, Sunyi
AU - Heuvelmans, Marjolein A.
AU - Du, Yihui
AU - Sidorenkov, Grigory
AU - Fan, Shuxuan
AU - Li, Yanju
AU - Xie, Yongsheng
AU - Zhu, Zhongyuan
AU - Dorrius, Monique D.
AU - Zhao, Yingru
AU - Veldhuis, Raymond N.J.
AU - de Bock, Geertruida H.
AU - Oudkerk, Matthijs
AU - van Ooijen, Peter M.A.
AU - Vliegenthart, Rozemarijn
AU - Ye, Zhaoxiang
N1 - Funding Information:
This work was supported by a grant from Ministry of Science and Technology of the People’s Republic of China, National Key R&D Program of China (no.2018YFC1315600 no.2017FYC1308700 and no.2016YFE0103000), the Royal Netherlands Academy of Arts and Sciences (grant number. PSA_SA_BD_01), and the University Medical Center Groningen PhD Scholarship program.
Publisher Copyright:
© 2021
PY - 2022/1
Y1 - 2022/1
N2 - Objective: 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. Materials and methods: 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. Results: 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 < 0.001). Conclusions: The DL-CAD system can accurately detect pulmonary nodules on LDCT, with an acceptable false-positive rate of 1 nodule per scan and has higher detection performance than double reading. This DL-CAD system may assist radiologists in nodule detection in LDCT lung cancer screening.
AB - Objective: 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. Materials and methods: 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. Results: 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 < 0.001). Conclusions: The DL-CAD system can accurately detect pulmonary nodules on LDCT, with an acceptable false-positive rate of 1 nodule per scan and has higher detection performance than double reading. This DL-CAD system may assist radiologists in nodule detection in LDCT lung cancer screening.
KW - Artificial intelligence
KW - Computed tomography
KW - Computer-assisted diagnosis
KW - Early detection of cancer
KW - Pulmonary nodules
KW - UT-Hybrid-D
KW - 2023 OA procedure
UR - http://www.scopus.com/inward/record.url?scp=85120502946&partnerID=8YFLogxK
U2 - 10.1016/j.ejrad.2021.110068
DO - 10.1016/j.ejrad.2021.110068
M3 - Article
AN - SCOPUS:85120502946
SN - 0720-048X
VL - 146
JO - European journal of radiology
JF - European journal of radiology
M1 - 110068
ER -