Keywords:
Artificial Intelligence, Lung, Oncology, CAD, CT, Neural networks, Cancer
Authors:
J. Murchison, G. Ritchie, D. Senyszak, E. J. R. Van Beek; Edinburgh/UK
DOI:
10.26044/ecr2019/C-3686
Results
A total of 337 CT scans from 314 subjects (173 women,
164 men) with a total of 470 pulmonary nodules (largest axial diameter between ≥3mm and ≤30mm) were included in this study.
The mean age of all the subjects was 63 ± 7 years (range 32-88 years).
Details regarding the number of CT scans and nodules per group are described in table 1.
The mean largest axial diameter of all nodules in groups 1 to 5 was 7.68 ± 3.50 mm (range: 3.42 - 28.45 mm) and the mean volume was 198 ± 333 mm3 (range: 21 - 2797 mm3).
The CAD software was able to successfully segment 95% of the total 428 nodules between ≥3mm and ≤30mm in groups 1-3 and 5.
The average inter-reader dice coefficient was 0.83 (95% CI: 0.39,
0.96) which was 0.86 (95% CI: 0.51,
0.95) for CAD alone (p<0.01).
The inter-reader geometric mean diameter discrepancy was 1.15 (95% CI: 1.00,
1.58) which was 1.17 (95% CI: 1.01,
1.69) for CAD alone.
The inter-reader geometric mean volumetric discrepancy was 1.39 (95% CI: 1.01,
3.19) which was 1.38 (95% CI: 1.01,
3.38) for CAD alone.