Computer-aided detection (CAD) of solid pulmonary nodules in chest x-ray equivalent ultralow dose chest CT - first in-vivo results at dose levels of 0.13Â mSv

- Computer-aided detection (CAD) of solid pulmonary nodules was compared in 202 patients in standard dose and ultralow dose CT.
- The per-nodule sensitivity of CAD was 70% in standard dose CT and 68% in ultralow dose CT.
- The per-nodule sensitivity of CAD in standard dose CT was similar to ultralow dose CT in all size subgroups (all p > 0.05).
- Adding CAD markings in ultralow dose CT significantly improved the sensitivity of two radiologists from 77% to 88% and from 66% to 79%, respectively.
- CAD can serve as an excellent second reader for nodule detection in CT even at dose levels similar to chest X-ray.

ObjectivesTo determine the value of computer-aided detection (CAD) for solid pulmonary nodules in ultralow radiation dose single-energy computed tomography (CT) of the chest using third-generation dual-source CT at 100 kV and fixed tube current at 70 mAs with tin filtration.Methods202 consecutive patients undergoing clinically indicated standard dose chest CT (1.8 ± 0.7 mSv) were prospectively included and scanned with an additional ultralow dose CT (0.13 ± 0.01 mSv) in the same session. Standard of reference (SOR) was established by consensus reading of standard dose CT by two radiologists. CAD was performed in standard dose and ultralow dose CT with two different reconstruction kernels. CAD detection rate of nodules was evaluated including subgroups of different nodule sizes (<5, 5-7, >7 mm). Sensitivity was further analysed in multivariable mixed effects logistic regression.ResultsThe SOR included 279 solid nodules (mean diameter 4.3 ± 3.4 mm, range 1-24 mm). There was no significant difference in per-nodule sensitivity of CAD in standard dose with 70% compared to 68% in ultralow dose CT both overall and in different size subgroups (all p > 0.05). CAD led to a significant increase of sensitivity for both radiologists reading the ultralow dose CT scans (all p < 0.001). In multivariable analysis, the use of CAD (p < 0.001), and nodule size (p < 0.0001) were independent predictors for nodule detection, but not BMI (p = 0.933) and the use of contrast agents (p = 0.176).ConclusionsComputer-aided detection of solid pulmonary nodules using ultralow dose CT with chest X-ray equivalent radiation dose has similar sensitivities to those from standard dose CT. Adding CAD in ultralow dose CT significantly improves the sensitivity of radiologists.