magazinelogo

Advances in Computer and Communication

ISSN Online: 2767-2875 CODEN: ACCDC3
Frequency: quarterly Email: acc@hillpublisher.com
Total View: 1271286 Downloads: 256940 Citations: 204 (From Dimensions)
ArticleOpen Access http://dx.doi.org/10.26855/acc.2026.06.010

Neural Network-based Modeling for Effective Dose Estimation to Support Optimization in Adult CT Imaging: A Retrospective Cross-sectional Study in Ugandan Radiology

Gertrude Ayugi*, Bosco Oruru, Hadijja Ndagire

Department of Physics, School of Physical Sciences, College of Natural Sciences, Makerere University, Kampala 7062, Uganda.

*Corresponding author: Gertrude Ayugi

Published: June 30, 2026

Abstract

This study addresses the critical issue of effective dose estimation and optimization in adult computed tomography (CT) imaging within Ugandan radiology practices. The primary objective is to develop a data-driven neural network model capable of accurately predicting effective doses based on comprehensive CT scan parameters and patient-specific factors such as kVp, mAs, CTDI, DLP, patient weight, and scan length. Data were collected from two distinct imaging centers in Kampala, Uganda: Center A and Center B, each equipped with different CT scanner technologies. Center A’s dataset was utilized for model development, while Center B’s dataset served for independent validation. Key CT parameters and patient characteristics were systematically analyzed. The neural network architecture was optimized through rigorous training and validation processes to ensure robust performance. Statistical analyses included correlation coefficients between predicted and actual doses, mean absolute error (MAE), and root mean square error (RMSE) to evaluate model accuracy. Results demonstrate the model’s capability to accurately estimate effective doses across different CT scanner technologies, highlighting its utility in optimizing patient safety and radiation exposure in resource-limited settings. The findings underscore the significance of tailored dose optimization strategies in Ugandan radiology practice, particularly in the absence of established local dose reference levels (DRLs).

Keyword

Computed tomography; dosimetry; dose optimization; neural network

References

[1] McCollough CH. Computed tomography technology–and dose–in the 21st century. Health Phys. 2019;116(2):157-162.

[2] Brenner DJ, Hall EJ. Computed tomography—an increasing source of radiation exposure. N Engl J Med. 2007;357(22):2277-2284.

https://doi.org/10.1056/NEJMra072149

[3] Thakur Y, McLaughlin PD, Mayo JR. Strategies for radiation dose optimization. Curr Radiol Rep. 2013;1:1-10.

https://doi.org/10.1007/s40134-013-0007-y

[4] UNSCEAR. Sources and effects of ionizing radiation. Annex D: Medical radiation exposures. New York: United Nations; 2008.

[5] Berrington de González A, Mahesh M, Kim KP, Bhargavan M, Lewis R, Mettler F, Land C. Projected cancer risks from computed tomographic scans performed in the United States in 2007. Arch Intern Med. 2009;169(22):2071-2077. 

https://doi.org/10.1001/archinternmed.2009.440

[6] Hall EJ, Brenner DJ. Cancer risks from diagnostic radiology. Br J Radiol. 2008;81(965):362-378.
https://doi.org/10.1259/bjr/01948454

[7] National Research Council (US), Committee on Health Effects of Exposure to Low Levels of Ionizing Radiations (BEIR VII). Health Risks from Exposure to Low Levels of Ionizing Radiation: BEIR VII Phase 2. Washington, DC: National Academies Press; 2006.
https://doi.org/10.17226/11340

[8] Söderberg M, Gunnarsson M. Automatic exposure control in computed tomography: an evaluation of systems from different manufacturers. Acta Radiol. 2010;51(6):625-634.
https://doi.org/10.3109/02841851003698206

[9] Sakhnini L. CT radiation dose optimization and reduction for routine head, chest and abdominal CT examination. Radiol Diagn Imaging. 2018;2(1):1-4.
https://doi.org/10.15761/RDI.1000120

[10] Dawd JE, Özsahin DU, Özsahin I. A review of diagnostic reference levels in computed tomography. Curr Med Imaging. 2022;18(5): 623-632.
https://doi.org/10.2174/1573405617666210913093839

[11] Dose MQ. Determination of diagnostic reference level (DRL) in common computed tomography examinations with the modified quality control-based dose survey method in four university centers: a comparison of methods. J Biomed Phys Eng. 2021;11(4): 447-458.
https://doi.org/10.31661/jbpe.v0i0.2105-1322

[12] Paulo G, Damilakis J, Tsapaki V, Schegerer AA, Repussard J, Jaschke W, et al. Diagnostic reference levels based on clinical indications in computed tomography: a literature review. Insights Imaging. 2020;11:58. 

https://doi.org/10.1186/s13244-020-00899-y

[13] Allisy-Roberts P, Williams J. Chapter 7: Computed tomography. In: Allisy-Roberts P, Williams J, editors. Farr's Physics for Medical Imaging. 2nd ed. Philadelphia: W.B. Saunders; 2008. p. 103-119.
https://doi.org/10.1016/B978-0-7020-2844-1.50011-9

[14] Bashir U. CT dose index [Internet]. Radiopaedia.org; 2023. Available from:
https://doi.org/10.53347/rID-18981

[15] Goldman LW. Principles of CT: radiation dose and image quality. J Nucl Med Technol. 2007;35(4):213-225.

https://doi.org/10.2967/jnmt.106.037846

[16] International Commission on Radiological Protection (ICRP). The 2007 recommendations of the ICRP. ICRP Publication 103. Ann ICRP. 2007;37(2-4):1-332.
https://doi.org/10.1016/j.icrp.2007.10.003

[17] Korir GK, Wambani JS, Korir IK, Tries MA, Boen PK. National diagnostic reference level initiative for computed tomography examinations in Kenya. Radiat Prot Dosimetry. 2016;168(1):55-63.
https://doi.org/10.1093/rpd/ncv020

[18] Muhogora W, Rehani MM. Review of the current status of radiation protection in diagnostic radiology in Africa. J Med Imaging. 2017;4(3):031202.
https://doi.org/10.1117/1.JMI.4.3.031202

[19] Kawooya MG, Kisembo HN, Remedios D, Malumba R, del Rosario Perez M, Ige T, et al. An Africa point of view on quality and safety in imaging. Insights Imaging. 2022;13:9.
https://doi.org/10.1186/s13244-022-01203-w

[20] Higley KA, Kocher DC, Real AG, Chambers DB. Relative biological effectiveness and radiation weighting factors in the context of animals and plants. Ann ICRP. 2012;41(3-4):233-245.
https://doi.org/10.1016/j.icrp.2012.06.014

[21] Bielajew A. The Monte Carlo simulation of radiation transport. In: Handbook of Radiotherapy Physics: Theory and Practice. Boca Raton: CRC Press; 2007. p. 75-87.
https://doi.org/10.1201/9781420012026.ch5

[22] Liang Y, Muhammad W, Hart GR, Nartowt BJ, Chen ZJ, Yu JB, et al. A general-purpose Monte Carlo particle transport code based on inverse transform sampling for radiotherapy dose calculation. Sci Rep. 2020;10:2979. 

https://doi.org/10.1038/s41598-020-66844-7

[23] Geleijns J, Wondergem J. X-ray imaging and the skin: radiation biology, patient dosimetry and observed effects. Radiat Prot Dosimetry. 2005;114(1-4):121-125.
https://doi.org/10.1093/rpd/nch544

[24] Jaschke W, Schmuth M, Trianni A, Bartal G. Radiation-induced skin injuries to patients: what the interventional radiologist needs to know. Cardiovasc Intervent Radiol. 2017;40(8):1131-1140. https://doi.org/10.1007/s00270-017-1674-5

[25] Brenner D, Huda W. Effective dose: a useful concept in diagnostic radiology. Radiat Prot Dosimetry. 2008;128(4):503-508.

https://doi.org/10.1093/rpd/ncn056

[26] Huda W, Ogden KM. Computing effective doses to pediatric patients undergoing body CT examinations. Pediatr Radiol. 2008;38(4):415-423.
https://doi.org/10.1007/s00247-007-0766-3

[27] Woo JKH, Chiu RYW, Thakur Y, Mayo JR. Risk–benefit analysis of pulmonary CT angiography in patients with suspected pulmonary embolus. AJR Am J Roentgenol. 2012;198(6):1332-1339.
https://doi.org/10.2214/AJR.10.6329

[28] Elsie KM, Rosemary B, Grace MK, Aloysius Gonzaga M, Clark R, Pitcher R, et al. An audit of registered radiology equipment resources in Uganda. Pan Afr Med J. 2020;37:295.
https://doi.org/10.11604/pamj.2020.37.295.22046

[29] Ojara ED. Gov't to install CT scan machines in all regional referral hospitals in Uganda [Internet]. Cross Border Network; 2021 [cited 2023 Jul 24]. Available from:
https://crossbordernet.org/govt-to-install-ct-scan-machines-in-all-regional-referral-hospitals/

[30] Ayugi G, Oruru B, Kiragga F, Kisembo H, Kyagulanyi H. Establishment of computed tomography diagnostic reference levels on paediatric patients in Uganda. J Med Diagn Methods. 2018;7:189-192. https://doi.org/10.4172/2168-9784.1000274

[31] Erem G, Ameda F, Otike C, Olwit W, Mubuuke AG, Schandorf C, et al. Adult computed tomography examinations in Uganda: towards determining the national diagnostic reference levels. BMC Med Imaging. 2022;22:12. 

https://doi.org/10.1186/s12880-022-00838-x

[32] Kiragga F, Erem G, Kisembo H, Mayanja JMK, Nankya E, Nalwoga K, et al. Typical diagnostic reference levels of common indications for computed tomography scans among adult patients in Uganda: a cross-sectional study [Preprint]. Research Square; 2023.
https://doi.org/10.21203/rs.3.rs-2683913/v1

[33] Kisembo H. A survey of paediatric CT radiation doses in two selected hospitals in Kampala, Uganda: a radiation safety concern. Int J Cancer Ther Oncol. 2015;3(3):3327.
 https://doi.org/10.14319/ijcto.33.27

[34] De Mattia C, Campanaro F, Rottoli F, Colombo PE, Pola A, Vanzulli A, et al. Patient organ and effective dose estimation in CT: comparison of four software applications. Eur Radiol Exp. 2020;4:3.https://doi.org/10.1186/s41747-019-0130-5

[35] Fu W, Ria F, Segars WP, Choudhury KR, Wilson JM, Kapadia AJ, Samei E. Patient-informed organ dose estimation in clinical CT: implementation and effective dose assessment in 1048 clinical patients. AJR Am J Roentgenol. 2021;216(4):824-834.

https://doi.org/10.2214/AJR.19.22482

[36] Wu M, Yin Z, De Man B. Model-based dose reconstruction for CT dose estimation. Med Phys. 2017;44(2):e255-e263.

https://doi.org/10.1002/mp.12409

[37] Haykin S. Neural Networks: A Comprehensive Foundation. 2nd ed. Upper Saddle River: Prentice Hall; 1999.

[38] Meineke A, Rubbert C, Sawicki LM, Thomas C, Klosterkemper Y, Appel E, et al. Potential of a machine-learning model for dose optimization in CT quality assurance. Eur Radiol. 2019;29(7):3705-3713.
https://doi.org/10.1007/s00330-019-6013-6

[39] Rukundo W, Shiokawa K, Elsaid A, AbuElezz OA, Mahrous AM. A machine learning approach for total electron content (TEC) prediction over the northern anomaly crest region in Egypt. Adv Space Res. 2023;72(3):790-804.

https://doi.org/10.1016/j.asr.2022.10.052

[40] Yotov K, Hadzhikolev E, Hadzhikoleva S. Determining the number of neurons in artificial neural networks for approximation, trained with algorithms using the Jacobi matrix. TEM J. 2020;9(4):1320-1329.
https://doi.org/10.18421/TEM94-02

[41] Pripp AH. Why the p-value is significant. Tidsskr Nor Legeforen. 2015;135(16):1462.

[42] International Atomic Energy Agency. Quality Assurance Programme for Computed Tomography: Diagnostic and Therapy Applications. Human Health Series No. 29. Vienna: IAEA; 2012.

[43] Smith-Bindman R, Lipson J, Marcus R, et al. Radiation dose associated with common computed tomography examinations and the associated lifetime attributable risk of cancer. Arch Intern Med. 2009;169(22):2078-2086. 

https://doi.org/10.1001/archinternmed.2009.427

[44] Yang K, Ganguli S, DeLorenzo MC, Zheng H, Li X, Liu B, et al. Procedure-specific CT dose and utilization factors for CT-guided interventional procedures. Radiology. 2018;289(1):150-157.
https://doi.org/10.1148/radiol.2018172945

Copyright

© 2026 by the author(s).
This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution-NonCommercial-NoDerivatives (CC BY-NC-ND) license, which permits non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited and is not modified or adapted.
https://creativecommons.org/licenses/by-nc-nd/4.0/

How to cite this paper

Neural Network-based Modeling for Effective Dose Estimation to Support Optimization in Adult CT Imaging: A Retrospective Cross-sectional Study in Ugandan Radiology

How to cite this paper: Gertrude Ayugi, Bosco Oruru, Hadijja Ndagire. (2026) Neural Network-based Modeling for Effective Dose Estimation to Support Optimization in Adult CT Imaging: A Retrospective Cross-sectional Study in Ugandan Radiology. Advances in Computer and Communication7(2), 111-121.

DOI: http://dx.doi.org/10.26855/acc.2026.06.010