Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2025 Aug;43(8):1365-1371.
doi: 10.1007/s11604-025-01775-9. Epub 2025 Apr 7.

Improving image quality on pediatric and neonatal radiography using AI-based compensation for image degradation

So Ode  1 , Atsuko Fujikawa  2 , Atsushi Hiroishi  2 , Yuki Saito  2 , Takao Tanuma  3 , Daigo Suzuki  3 , Yuichi Sasaki  3 , Hidefumi Mimura  2
Affiliations

Improving image quality on pediatric and neonatal radiography using AI-based compensation for image degradation

So Ode et al. Jpn J Radiol. 2025 Aug.

Abstract

Purpose: To evaluate the impact of an AI-based, noise reduction technique for compensation of image degradation on pediatric and neonatal chest and abdomen radiography using a visual grading analysis.

Materials and methods: Forty-six consecutive cases of pediatric and neonatal chest X-rays were identified for the quality evaluation. The images underwent AI-based noise reduction processing (Intelligent NR, Canon Inc.). All the images were randomized, and were evaluated from 1 to 4 for image quality by three board-certified radiologists in consensus. A score of "1" indicated the desired anatomy or features were not seen, "2" indicated quality between one and three, "3" indicated adequate quality, and "4" indicated higher than required image quality. A Wilcoxon signed rank test was used to assess the significant difference between images from conventional noise reduction versus those from the AI-based noise reduction.

Results: The images processed with the INR(Intelligent NR) noise reduction had a higher image quality than the conventionally processed images, with a significant difference between the two groups (p < 0.05).

Conclusion: The AI-based noise reduction technique improved the image quality of pediatric and neonatal chest and abdominal radiography significantly.

Keywords: Artificial intelligence; Noise reduction; Pediatric radiology; Radiography.

PubMed Disclaimer

Figures

Fig. 1
Fig. 1
Study design for the evaluation of image quality for each group
Fig. 2
Fig. 2
Examples of VGA scoring for processed images. Chest VGA score 3 (a). Processed by conventional algorithm. Granular noise is seen in the soft tissue and lung fields. Bone cortex and diaphragmatic margins are partially obscured. VGA score 4 (b). Processed by Intelligent NR(INR). Soft tissue, lung fields, bone cortex, and diaphragm are all clearly delineated. Abdominal VGA score 2 (c). Processed by conventional algorithm. Strong granular noise is seen in the soft tissues over a wide area, with obscured borders of the bone cortex and intestinal wall, and obscured bone beam structures. VGA score 3 (d). Processed by conventional algorithm. Granular noise is present, but only partially obscuring the bony structures and intestinal wall delineation. VGA score 4 (e). Processed by INR. Graininess is not prominent and soft tissues, bowel wall, bony structures, and diaphragm are clearly defined
Fig. 3
Fig. 3
Frequency of VGA scores for each group
Fig.4
Fig.4
Difference in VGA scores between each noise reduction algorithm
Fig. 5
Fig. 5
The differences in the image quality between each process on the same image. Compared to conventional noise reduction (a), INR (b) shows improvement in granular noise in the chest and abdomen, and clarification of lung fields, soft tissue, intestinal wall, bone cortex and trabecular structures
Fig. 6
Fig. 6
The differences in image quality between each process in each areas of the same image. In contrast to the conventional process (a, c, e, g), INR (b, d, f, h) shows a clearer lung pattern, a marked reduction in the mottled noise signal in the upper abdomen, and clearer bone cortex and trabecular structures
See this image and copyright information in PMC

References

    1. Garmer M, Hennigs SP, Jäger HJ, Schrick F, van de Loo T, Jacobs A, et al. Digital radiography versus conventional radiography in chest imaging: diagnostic performance of a large-area silicon flat-panel detector in a clinical CT-controlled study. AJR Am J Roentgenol. 2000;174(1):75–80. - PubMed
    1. European Commission (2000) European guidelines on quality criteria for diagnostic radiographic images in paediatrics. European Commission, Luxembourg Available via https://publications.europa.eu/en/publication-detail/-/publication/47eb6.... Accessed 31 Dec 2023
    1. European Commission (2018) Radiation Protection No. 185: European guidelines on diagnostic reference levels for paediatric imaging. European Commission, Luxembourg Available via http://www.eurosafeimaging.org/wp/wp-content/uploads/2018/09/rp_185.pdf. Accessed 31 Dec 2023
    1. Precht H, Waaler D, Outzen CB, Brock Thorsen JB, Steen T, Hellfritzsch MB, et al. Does software optimization influence the radiologists’ perception in low dose paediatric pelvic examinations? Radiography (Lond). 2019;25(2):143–7. - PubMed
    1. Oh S, Kim JH, Yoo SY, Jeon TY, Kim YJ. Evaluation of the image quality and dose reduction in digital radiography with an advanced spatial noise reduction algorithm in pediatric patients. Eur Radiol. 2021;31(12):8937–46. - PubMed

LinkOut - more resources