Deep Learning-Enhanced Low-Dose CT Reconstruction for Pediatric Chest Imaging: Diagnostic Accuracy and Radiation Dose Optimization

Abstract

The aim of this study is to investigate the performance of the deep learning aided low-dose CT reconstruction in children's chest imaging from diagnostic accuracy to dose optimization. A total of 120 children aged 1–15 years were randomly allocated into two groups, one in the conventional low dose CT (LdCT) and the other in deep learning enhanced reconstruction (DLER) group. The radiation dosages were assessed by the CTDI volume and DLP; image quality by the signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR); image noise by the image noise; and diagnostic confidence score measured by the radiologist. A deep learning method found the average reduction of radiation to be 38% and DLP was reduced to 69 mGy·cm compared to 112 mGy·cm in the results. Objective image quality significantly improved as SNR increased from 18.4 to 27.9, CNR increased from 14.7 to 23.2 and image noise decreased by 46% with SNR increasing. Subjective analysis of the pictures identified as good or excellent, using deep learning versus conventional CT images, yielded 92% for the DL images to 63% for the CT images. The diagnostic sensitivities also increased from 86% to 96%, the diagnostic specificity from 84% to 94% and the diagnostic accuracy from 85% to 95% was significantly enhanced. All these major outcomes were significantly different between the groups (p < 0.05). The deep learning-based low-dose CT reconstruction technique was a very promising method for low radiation dose, and there was good reliability for the thorax, which could be applied to pediatrics.

References

[1] H. Li, Y. Zhang, S. Hua, R. Sun, Y. Zhang, Z. Yang, and J. Sun, "Deep Learning Image Reconstruction (DLIR) Algorithm to Maintain High Image Quality and Diagnostic Accuracy in Quadruple-low CT Angiography of Children with Pulmonary Sequestration: A Case Control Study," Academic Radiology, vol. 32, no. 7, pp. 4197–4205, 2025.

[2] A. Clement David-Olawade, D. B. Olawade, L. Vanderbloemen, O. B. Rotifa, S. C. Fidelis, E. Egbon, and S. Boussios, "AI-driven advances in low-dose imaging and enhancement—a review," Diagnostics, vol. 15, no. 6, p. 689, 2025.

[3] L. R. Koetzier, D. Mastrodicasa, T. P. Szczykutowicz, N. R. van der Werf, A. S. Wang, V. Sandfort, and M. J. Willemink, "Deep learning image reconstruction for CT: technical principles and clinical prospects," Radiology, vol. 306, no. 3, e221257, 2023.

[4] Z. Zhou, A. Inoue, C. W. Cox, C. H. McCollough, and L. Yu, "Deep learning-based volume of interest imaging in helical CT for image quality improvement and radiation dose reduction," British Journal of Radiology, vol. 98, no. 1175, pp. 1880–1889, 2025.

[5] J. Li, Y. Xia, G. Sun, M. Xu, X. Lin, S. Jiang, and L. Fan, "Deep learning-based image reconstruction algorithm for lung diffusion weighted imaging: improved image quality and diagnostic performance," Chinese Journal of Academic Radiology, vol. 7, no. 4, pp. 348–357, 2024.

[6] W. Kazimierczak, K. Kędziora, J. Janiszewska-Olszowska, N. Kazimierczak, and Z. Serafin, "Noise-optimized CBCT imaging of temporomandibular joints—the impact of AI on image quality," Journal of Clinical Medicine, vol. 13, no. 5, p. 1502, 2024.

[7] X. Jiang, Z. Hu, S. Wang, and Y. Zhang, "Deep learning for medical image-based cancer diagnosis," Cancers, vol. 15, no. 14, p. 3608, 2023.

[8] F. A. A. Slimani, "Lung Disease Classification with Deep Learning Enhanced CNN Architecture in Chest X-Ray Imaging," Journal of Imaging Informatics in Medicine, pp. 1–24, 2025.

[9] N. S. Joos, S. Afat, M. D. Nickel, E. Weiland, J. Herrmann, S. Ursprung, and S. Gassenmaier, "Application of thin-slice and accelerated T1-weighted GRE sequences in 1.5 T abdominal magnetic resonance imaging using deep learning image reconstruction," Journal of Medical Imaging, vol. 12, no. 6, 064005, 2025.

[10] A. Wang, Z. Ma, T. Wang, R. Chen, Y. Xi, Q. Wu, and L. Zang, "Deep Learning–Assisted Automated Diagnosis of Osteoporosis Based on Computed Tomography Scans: Systematic Review and Meta-Analysis," Journal of Medical Internet Research, vol. 27, e77155, 2025.

[11] S. S. Y. Chan, "Deep Learning-Based Prediction of Daily Delivered Dose for Advanced Lung Cancer Radiotherapy," Doctoral dissertation, 2025.

[12] Y. Yan, D. A. Alexander, B. P. Bednarz, L. F. Bronk, H. Chen, D. J. Gladstone, and F. Guan, "Innovative approaches in precision radiation oncology: advanced imaging technologies and challenges which shape the future of radiation therapy," Frontiers in Medicine, vol. 12, 1686593, 2025.

[13] T. Nozaki, M. Hashimoto, D. Ueda, S. Fujita, Y. Fushimi, K. Kamagata, and S. Naganawa, "Recent topics in musculoskeletal imaging focused on clinical applications of AI: How should radiologists approach and use AI?," La radiologia medica, vol. 130, no. 5, pp. 587–597, 2025.

[14] D. Bannur, M. G. Cerdas, A. Z. Saeed, B. Imam, R. S. Thandi, P. Reddy, and M. P. Reddy, "Efficiency of Artificial Intelligence in Three-Dimensional Reconstruction of Medical Imaging," Cureus, vol. 17, no. 11, 2025.

[15] J. Hu, L. Li, Q. Zhang, W. Wei, G. Huang, J. Liu, and N. Zhang, "Image quality restoration in 15‐s breath‐hold PET using a diffusion‐based neural network," Medical Physics, vol. 53, no. 3, e70361, 2026.

[16] B. Omarov, "Deep Learning in Biomedical Image and Signal Processing: A Survey," Computers, Materials, & Continua, vol. 85, no. 2, p. 2195, 2025.

[17] Y. Lei, C. Niu, J. Zhang, G. Wang, and H. Shan, "CT image denoising and deblurring with deep learning: current status and perspectives," IEEE Transactions on Radiation and Plasma Medical Sciences, vol. 8, no. 2, pp. 153–172, 2023.

[18] E. Fakhar, A. J. Esfahani, E. Saeedzadeh, and N. Banaee, "Deep learning-based organ-at-risk segmentation, registration and dosimetry on cone beam computed tomography images in radiation therapy: A comprehensive review," Journal of Cancer Research and Therapeutics, vol. 21, no. 3, pp. 523–537, 2025.

[19] Y. Li, K. Ye, S. Liu, Y. Zhang, D. Jin, C. Jiang, and H. Yuan, "Deep learning-enhanced opportunistic osteoporosis screening in 100 kV low-voltage chest CT: a novel way toward bone mineral density measurement and radiation dose reduction," Academic Radiology, 2025.

[20] X. Shen, J. Xiong, S. Wang, G. Hu, H. Liu, and S. Zhang, "Application of machine learning in osteoporosis screening: a narrative review," npj Digital Medicine, 2026.

[21] O. A. Malik, "Agentic AI deployment in infrastructure-limited environments: Observability gaps, failure modes, and AI governance primitives," Journal of Engineering and Computational Intelligence Review, vol. 4, no. 1, pp. 1–11, 2026.

[22] D. Mohiuddin, “Adaptive Marketing Systems and Consumer Feedback Loops: Implications for Market Development in Emerging Economies,” Journal of Business Insight and Innovation, vol. 5, no. 1, pp. 37–48, 2026. [Online]. Available: https://insightfuljournals.com/index.php/JBII/article/view/64

[23] D. Mohiuddin, “HR Tech Adoption in Digital Banking: Implications for Workforce Development and Financial Sector Growth in Emerging Economies,” Journal of Business Insight and Innovation, vol. 4, no. 2, pp. 77–90, 2025. [Online]. Available: https://insightfuljournals.com/index.php/JBII/article/view/63

[24] D. Mohiuddin and D. N. Farhan, “Artificial Intelligence in Marketing: Ethical Challenges and Solutions for Consumers and Society,” Journal of Business Insight and Innovation, vol. 4, no. 1, pp. 73–87, 2025. [Online]. Available: https://insightfuljournals.com/index.php/JBII/article/view/69

[25] D. Mohiuddin, “Algorithmic Hyper-Personalization: The Double-Edged Sword of Predictive Personalization – An Empirical Investigation,” Journal of Engineering and Computational Intelligence Review, vol. 2, no. 2, pp. 82–94, 2024. [Online]. Available: https://jecir.com/index.php/jecir/article/view/34

[26] D. Mohiuddin, “Consumer Perceptions and Trust in AI-Generated Advertising: An Experimental Study in the Pakistani Context,” Apex Journal of Social Sciences, vol. 3, no. 1, pp. 53–68, 2024. [Online]. Available: https://apexjss.com/index.php/AJSS/article/view/24

[27] D. Mohiuddin, A. A. Zaveri, I. Ahmed, and M. Umar, “A systematic literature review of multi-channel analytics linked to POS and connected to food businesses in the UK,” in 2026 International Conference on AI Innovations and Industry (ICAIII), 2026, pp. 1–6. doi: 10.1109/ICAIII69475.2026.11521642.

[28] D. Mohiuddin, M. H. Tariq, and A. Tahir, “The Impact of Generative AI on Personalized Content Marketing in E-Commerce,” Inverge Journal of Social Sciences, vol. 4, no. 1, pp. 162–188, 2025. doi: 10.63544/ijss.v4i1.288.

[29] M. Asif and M. Bashir, “Augmentation or Anxiety? The Mediating Role of Employee Trust in the Relationship Between Generative AI Implementation, Job Crafting, and Productivity,” The Critical Review of Social Sciences Studies, vol. 4, no. 1, pp. 4550–4583, 2026, doi: 10.59075/mrqkn978.

[30] M. Rafiq-uz-Zaman and M. Asif, “Mechanisms of exclusion: Power, structure, and the persistence of gender inequality,” Qualitative Research Journal for Social Studies, vol. 3, no. 1, pp. 690–703, 2026, doi: 10.63878/qrjs921.

[31] S. Ahmed and M. Asif, “Comparative analysis of attitudes toward climate change policies across urban and rural populations,” Pakistan Journal of Social Science Review, vol. 5, no. 1, pp. 747–769, 2026, doi: 10.5281/zenodo.18457821.

[32] S. Ahmed and M. Asif, “Public opinion on the effectiveness of local government anti-corruption measures: A multi-city survey analysis,” International Journal of Social Sciences Bulletin, vol. 4, no. 1, pp. 1189–1201, 2026, doi: 10.5281/zenodo.18412790.

[33] M. Asif and S. Ullah, “Determinants of support for federalism vs. centralization: A survey of public opinion in Punjab and Khyber Pakhtunkhwa (KP),” Social Science Review Archives, vol. 4, no. 1, pp. 2791–2807, 2026, doi: 10.70670/sra.v4i1.1843.

[34] M. Asif and S. Ullah, “Performance voting vs. identity voting: An analysis of electoral behaviour in Pakistani districts,” Journal of Applied Linguistics and TESOL (JALT), vol. 9, no. 1, pp. 213–226, 2026, doi: 10.63878/cjssr.v4i1.2079.

[35] M. Asif and M. Rafiq-uz-Zaman, “The silent disengagement: A quantitative analysis of leadership, recognition, and workload as predictors of quiet quitting among knowledge workers,” Al-AASAR Journal, vol. 3, no. 1, pp. 271–303, 2026, doi: 10.63878/aaj1525.

[36] M. Asif, “Financial performance of startups linked to universities: Evidence from developing economies,” Journal of Applied Linguistics and TESOL, vol. 8, no. 3, pp. 2736–2763, 2025, doi: 10.63878/jalt2003.