Fig. 2From: Application of a deep learning image reconstruction (DLIR) algorithm in head CT imaging for children to improve image quality and lesion detectionAn infant with fever for 18 days and diagnosis of purulent meningitis. The scanning tube current was 150 mA, CTDI = 15.26 mGy, DLP = 183.21 mGy cm, A–D were 5 mm images with FBP, 50%ASIR-V, 100%ASIR-V and DL-H, respectively, E–H were 0.625 mm images. It can be observed that with the increase of ASIR-V weight, the noise of both the thick images and thin images decreased, but the blurred margins in 100% ASIR-V images were more pronounced (white arrows), and the subjective scores for the edges of gray and white matters were not improved. While the noise in DL-H images was reduced, the sharpness of edge maintained compared to FBP images, which is more suitable for observationBack to article page