To explore the value of the third generation dual-source computed tomography (CT) convolution kernel in display of pulmonary ground-glass nodule (GGN) in transverse image reconstruction. Methods: A total of 52 lung adenocarcinoma patients with lung CT data were selected from February 2018 to January 2019 for this study. The pulmonary CT data were reconstructed by convolutional nucleus B157, Br54, and Br49. The signal-to-noise ratio (SNR), the contrast-to-noise ratio (CNR), and the standard deviation (SD) of the image at the GGN were used as the objective evaluation standard of image quality. Subjective image quality was scored by 2 radiologists from 3 aspects (overall image quality, noise, and lesion outline). Results: Objective image quality evaluation, SNR and CNR of reconstructed convolution kernel Br49 (SNR: 11.36±5.39, CNR: 7.19±4.29), Br54 (SNR: 8.30±3.35, CNR: 5.09±2.86) are greater than those of Bl57 (SNR: 4.18±2.10, CNR: 3.25±1.78; all P<0.01). SD of reconstructed convolution kernel Br49 (61.80±20.17) and Br54 (80.45±20.31) is smaller than that of Bl57 (137.92±31.11, both P<0.01). In the subjective image quality evaluation, the overall image quality score 5.0(4.5, 5.0) of Br54 was higher than that of all other images [Br49: 3.0(3.0, 4.0), Bl57: 3.0(3.0, 3.5); both P<0.05]. The Br54 image showed that the lesion contour ability score 5.0(4.0, 5.0) was higher than all other images [Br49: 4.0(4.0, 5.0), Bl57: 3.0(3.0, 3.0); both P<0.05]; Br49 image noise score 3.0(3.0, 3.0) is the lowest one [Br54 4.0(4.0, 4.0), Bl57 5.0(5.0, 5.0); both P<0.05]. Conclusion: The reasonable selection of CT convolution kernel plays an important role in the subjective and objective image quality of GGN. It is suggested that Br54 should be used as the reconstruction of convolutional kernel in pulmonary ground glass nodules, which is helpful for doctors to find and diagnose GGN.