Eui Jin Hwang1, Jin Mo Goo2,3, Hyae Young Kim4, Soon Ho Yoon1, Gong Yong Jin5, Jaeyoun Yi6, Yeol Kim7. 1. Department of Radiology and Institute of Radiation Medicine, Seoul National University College of Medicine, 101 Daehak-ro, Jongno-gu, Seoul, 03080, South Korea. 2. Department of Radiology and Institute of Radiation Medicine, Seoul National University College of Medicine, 101 Daehak-ro, Jongno-gu, Seoul, 03080, South Korea. jmgoo@plaza.snu.ac.kr. 3. Cancer Research Institute, Seoul National University, Seoul, South Korea. jmgoo@plaza.snu.ac.kr. 4. Department of Radiology, National Cancer Center, Goyang, South Korea. 5. Department of Radiology, Jeonbuk National University Hospital, Jeonju, South Korea. 6. Coreline Soft Inc., Seoul, South Korea. 7. National Cancer Control Institute, National Cancer Center, Goyang, South Korea.
Abstract
OBJECTIVES: To evaluate the degree of variability in computer-assisted interpretation of low-dose chest CTs (LDCTs) among radiologists in a nationwide lung cancer screening (LCS) program, through comparison with a retrospective interpretation from a central laboratory. MATERIALS AND METHODS: Consecutive baseline LDCTs (n = 3353) from a nationwide LCS program were investigated. In the institutional reading, 20 radiologists in 14 institutions interpreted LDCTs using computer-aided detection and semi-automated segmentation systems for lung nodules. In the retrospective central review, a single radiologist re-interpreted all LDCTs using the same system, recording any non-calcified nodules ≥ 3 mm without arbitrary rejection of semi-automated segmentation to minimize the intervention of radiologist's discretion. Positive results (requiring additional follow-up LDCTs or diagnostic procedures) were initially classified by the lung CT screening reporting and data system (Lung-RADS) during the interpretation, while the classifications based on the volumetric criteria from the Dutch-Belgian lung cancer screening trial (NELSON) were retrospectively applied. Variabilities in positive rates were assessed with coefficients of variation (CVs). RESULTS: In the institutional reading, positive rates by the Lung-RADS ranged from 7.5 to 43.3%, and those by the NELSON ranged from 11.4 to 45.0% across radiologists. The central review exhibited higher positive rates by Lung-RADS (20.0% vs. 27.3%; p < .001) and the NELSON (23.1% vs. 37.0%; p < .001), and lower inter-institution variability (CV, 0.30 vs. 0.12, p = .003 by Lung-RADS; CV, 0.25 vs. 0.12, p = .014 by the NELSON) compared to the institutional reading. CONCLUSION: Considerable inter-institution variability in the interpretation of LCS results is caused by different usage of the computer-assisted system. KEY POINTS: • Considerable variability existed in the interpretation of screening LDCT among radiologists partly from the different usage of the computerized system. • A retrospective reading of low-dose chest CTs in the central laboratory resulted in reduced variability but an increased positive rate.
OBJECTIVES: To evaluate the degree of variability in computer-assisted interpretation of low-dose chest CTs (LDCTs) among radiologists in a nationwide lung cancer screening (LCS) program, through comparison with a retrospective interpretation from a central laboratory. MATERIALS AND METHODS: Consecutive baseline LDCTs (n = 3353) from a nationwide LCS program were investigated. In the institutional reading, 20 radiologists in 14 institutions interpreted LDCTs using computer-aided detection and semi-automated segmentation systems for lung nodules. In the retrospective central review, a single radiologist re-interpreted all LDCTs using the same system, recording any non-calcified nodules ≥ 3 mm without arbitrary rejection of semi-automated segmentation to minimize the intervention of radiologist's discretion. Positive results (requiring additional follow-up LDCTs or diagnostic procedures) were initially classified by the lung CT screening reporting and data system (Lung-RADS) during the interpretation, while the classifications based on the volumetric criteria from the Dutch-Belgian lung cancer screening trial (NELSON) were retrospectively applied. Variabilities in positive rates were assessed with coefficients of variation (CVs). RESULTS: In the institutional reading, positive rates by the Lung-RADS ranged from 7.5 to 43.3%, and those by the NELSON ranged from 11.4 to 45.0% across radiologists. The central review exhibited higher positive rates by Lung-RADS (20.0% vs. 27.3%; p < .001) and the NELSON (23.1% vs. 37.0%; p < .001), and lower inter-institution variability (CV, 0.30 vs. 0.12, p = .003 by Lung-RADS; CV, 0.25 vs. 0.12, p = .014 by the NELSON) compared to the institutional reading. CONCLUSION: Considerable inter-institution variability in the interpretation of LCS results is caused by different usage of the computer-assisted system. KEY POINTS: • Considerable variability existed in the interpretation of screening LDCT among radiologists partly from the different usage of the computerized system. • A retrospective reading of low-dose chest CTs in the central laboratory resulted in reduced variability but an increased positive rate.
Entities:
Keywords:
Early detection of cancer; Image interpretation; Lung neoplasms; Tomography, X-Ray computed
Authors: Andrea N Burnett-Hartman; Nikki M Carroll; Stacey A Honda; Caroline Joyce; Nandita Mitra; Christine Neslund-Dudas; Oluwatosin Olaiya; Katharine A Rendle; Mitchell D Schnall; Anil Vachani; Debra P Ritzwoller Journal: Ann Am Thorac Soc Date: 2022-03