Deep learning algorithm for CT scanning in ankle trauma: Technical principles and prospects for reducing effective radiation dose

Zhang, M.; Lei, M.; Lin, F.; Chen, Y.; Xie, Y.; Liu, J.; Chen, J.; Wang, H.; Xiao, M.

doi:10.61882/ijrr.23.3.39

[Home ] [Archive]

International Journal of Radiation Research

Main Menu

Home

IJRR Information

For Authors

For Reviewers

Subscription

News & Events

Web Mail

Search in website

Receive site information

ISSN

Hard Copy 2322-3243

Online 2345-4229

Online Submission

Now you can send your articles to IJRR office using the article submission system.

Volume 23, Issue 3 (7-2025) Int J Radiat Res 2025, 23(3): 813-817 | Back to browse issues page

‎ 10.61882/ijrr.23.3.39

Mendeley

Zotero

RefWorks

Zhang M, Lei M, Lin F, Chen Y, Xie Y, Liu J, et al . Deep learning algorithm for CT scanning in ankle trauma: Technical principles and prospects for reducing effective radiation dose. Int J Radiat Res 2025; 23 (3) :813-817
URL: http://ijrr.com/article-1-6683-en.html

Deep learning algorithm for CT scanning in ankle trauma: Technical principles and prospects for reducing effective radiation dose

M. Zhang

, M. Lei

, F. Lin

, Y. Chen

, Y. Xie

, J. Liu

, J. Chen

, H. Wang

, M. Xiao

Department of Radiology, Zhuhai Hospital, Guangdong Provincial Hospital of Traditional Chinese Medicine, 53 Jingle Road, Zhuhai City, Guangdong Province, China , xmqzhuhai@163.com

Abstract: (180 Views)

Background: This study aims to compare the image quality and effective dose (ED) of deep learning algorithm computer tomography (DLA-CT) with standard CT (SD-CT) in managing ankle trauma. Materials and Methods: In this prospective study, 88 patients underwent random allocation to either the SD-CT group (utilizing a tube voltage of 120KV and an automatic tube current milliampere setting) or the DLA-CT group (employing automatic tube voltage and current adjustments). Senior radiologists assessed objective image quality using parameters such as noise, signal-to-noise ratio (SNR), and contrast-to-noise ratio (CNR). The influence of subjective image quality and its impact on treatment plans were evaluated using a 5-point Likert scale, with scores of 3 or higher indicating acceptable image quality and adherence to treatment plan requirements. Dose length product (DLP) (mGy×cm) was automatically recorded by the scanner software, DLP×k. Results: Objective image quality with DLA-CT was found to be inferior to that obtained with SD-CT (P<0.001). No significant differences were noted in subjective image quality scores between the two groups (P =0.60). Additionally, both subjective image quality scores and the effect of image quality on treatment decisions were scored at 3 or higher. The ED was significantly reduced by 48.83% in the DLA-CT group compared to the SD-CT group (21.42±2.62 µSv and 10.96±1.12 µSv, respectively, P=0.001). Conclusion: DLA-CT proves effective in the management of ankle trauma, significantly reducing ED while meeting clinical diagnostic and treatment standards.

Keywords: Deep learning algorithm, ankle fracture, computer tomography, low radiation dose.

Full-Text [PDF 809 kb] (87 Downloads)

Type of Study: Short Report | Subject: Radiation Biology

References

1. Martijn HA, Lambers KTA, Dahmen J, et al. (2021) High incidence of (osteo)chondral lesions in ankle fractures. Knee Surg Sports Traumatol Arthrosc, 29(5): 1523-1534. [DOI:10.1007/s00167-020-06187-y]

2. Xue P, Chen X, Chen S, et al. (2021) The value of CT 3D reconstruction in the classification and nursing effect evaluation of ankle fracture. J Healthc Eng, 2021: 9596518. [DOI:10.1155/2021/9596518]

3. Cuddy K, Khatib B, Bell RB, et al. (2018) Use of intraoperative computed tomography in craniomaxillofacial trauma surgery. J Oral Maxillofac Surg, 76(5): 1016-1025. [DOI:10.1016/j.joms.2017.12.004]

4. Azman RR, Shah MNM, Ng KH (2019) Radiation safety in emergency medicine: Balancing the benefits and risks. Korean J Radiol, 20(3): 399-404. [DOI:10.3348/kjr.2018.0416]

5. Shinde PP and Shah S (2018) A review of machine learning and deep learning applications[C]//2018 Fourth international conference on computing communication control and automation (ICCUBEA). IEEE, 4: 1-6. [DOI:10.1109/ICCUBEA.2018.8697857]

6. Handelman GS, Kok HK, Chandra RV, et al. (2018) eDoctor: machine learning and the future of medicine. Journal of Internal Medicine, 284(6): 603-619. [DOI:10.1111/joim.12822]

7. Lee YW, Choi JW, Shin EH (2021) Machine learning model for predicting malaria using clinical information. Computers in Biology and Medicine, 129: 104151. [DOI:10.1016/j.compbiomed.2020.104151]

8. Sultan AS, Elgharib MA, Tavares T, et al. (2020) The use of artificial intelligence, machine learning and deep learning in oncologic histopathology. J Oral Pathol Med, 49(9): 849-856. [DOI:10.1111/jop.13042]

9. Ranganathan DG (2021). A study to find facts behind preprocessing on deep learning algorithms. Journal of Innovative Image Processing, 3(1): 66-74. [DOI:10.36548/jiip.2021.1.006]

10. Oh JH, Kim HG, Lee KM (2023) Developing and evaluating deep learning algorithms for object detection: key points for achieving superior model performance. Korean Journal of Radiology, 24(7): 698-714. [DOI:10.3348/kjr.2022.0765]

11. Achuthan S, Chatterjee R, Kotnala S, et al. (2022) Leveraging deep learning algorithms for synthetic data generation to design and analyze biological networks. J Biosci, 47: 43. [DOI:10.1007/s12038-022-00278-3]

12. Zhang M, Lei M, Zhang J, et al. (2022) Feasibility study of three-dimensional printing knee model using the ultra-low-dose CT scan for preoperative planning and simulated surgery. Insights Imaging, 13(1): 151. [DOI:10.1186/s13244-022-01291-8]

13. Lei M, Zhang M, Luo N, et al. (2022) The clinical performance of ultra-low-dose shoulder CT scans: The assessment on image and physical 3D printing models. PLoS One, 17(9): e0275297. [DOI:10.1371/journal.pone.0275297]

14. Weinrich JM, Well L, Regier M, et al. (2018) MDCT in suspected lumbar spine fracture: comparison of standard and reduced dose settings using iterative reconstruction. Clin Radiol, 73(7): 675.e9-675.e15. [DOI:10.1016/j.crad.2018.02.015]

15. Lei M, Zhang M, Li H, et al. (2022) The diagnostic performance of ultra-low-dose 320-row detector CT with different reconstruction algorithms on limb joint fractures in the emergency department. Jpn J Radiol, 40(10): 1079-1086. [DOI:10.1007/s11604-022-01290-1]

16. Xiao M, Zhang M, Lei M, et al. (2023) Diagnostic accuracy of ultra-low-dose CT compared to standard-dose CT for identification of non-displaced fractures of the shoulder, knee, ankle, and wrist. Insights Imaging, 14(1): 40. [DOI:10.1186/s13244-023-01389-7]

17. Jin L, Ge X, Lu F, et al. (2018) Low-dose CT examination for rib fracture evaluation: A pilot study. Medicine, 97(30): e11624. [DOI:10.1097/MD.0000000000011624]

18. Murphy MC, Gibney B, Walsh J, et al. (2022) Ultra-low-dose cone-beam CT compared to standard dose in the assessment for acute fractures. Skeletal Radiology, 51(1): 153-159. [DOI:10.1007/s00256-021-03825-5]

19. Alagic Z, Bujila R, Enocson A, et al. (2020) Ultra-low-dose CT for extremities in an acute setting: initial experience with 203 subjects. Skeletal radiology, 49(4): 531-539. [DOI:10.1007/s00256-019-03309-7]

20. Elegbede A, Diaconu S, Dreizin D, et al. (2020) Low-dose computed tomographic scans for postoperative evaluation of craniomaxillofacial fractures: A pilot clinical study. Plastic and Reconstructive Surgery,146(2): 366-370. [DOI:10.1097/PRS.0000000000007017]

21. Goetti R, Leschka S, Desbiolles L, et al. (2010) Quantitative computed tomography liver perfusion imaging using dynamic spiral scanning with variable pitch: feasibility and initial results in patients with cancer metastases. Invest Radiol, 45(7): 419-26. [DOI:10.1097/RLI.0b013e3181e1937b]

22. Tang S, Zhang G, Chen Z, et al. (2021) Application of prospective ECG-gated multiphase scanning for coronary CT in children with different heart rates. Jpn J Radiol, 39(10): 946-955. [DOI:10.1007/s11604-021-01133-5]

23. Yang Z and Liu Z (2020) The efficacy of 18F-FDG PET/CT-based diagnostic model in the diagnosis of colorectal cancer regional lymph node metastasis. Saudi J Biol Sci, 27(3): 805-811. [DOI:10.1016/j.sjbs.2019.12.017]

24. Wang X, Zhang J, Yang S, et al. (2023) A generalizable and robust deep learning algorithm for mitosis detection in multicenter breast histopathological images. Med Image Anal, 84: 102703. [DOI:10.1016/j.media.2022.102703]

25. Sakai Y, Hida T, Matsuura Y, et al. (2023) Impact of a new deep-learning-based reconstruction algorithm on image quality in ultra-high-resolution CT: clinical observational and phantom studies. Br J Radiol, 96(1141): 20220731. [DOI:10.1259/bjr.20220731]

26. Lee KH, Lee JM, Moon SK, et al. (2012) Attenuation-based automatic tube voltage selection and tube current modulation for dose reduction at contrast-enhanced liver CT. Radiology, 265(2): 437-47. [DOI:10.1148/radiol.12112434]

27. Lv P, Zhou Z, Liu J, et al. (2019) Can virtual monochromatic images from dual-energy CT replace low-kVp images for abdominal contrast-enhanced CT in small- and medium-sized patients? Eur Radiol, 29(6): 2878-2889. [DOI:10.1007/s00330-018-5850-z]

28. Gokalp G (2019) Low kilovolt" prospective ECG-triggering" vs." retrospective ECG-gating" coronary CTA: comparison of image quality and radiation dose. International Journal of Radiation Research, 17(2): 209-216.

29. Xiao M, Zhang M, Liu J, et al. (2017) Iterative reconstruction combined with low dose CT in diagnosis of lumbar intervertebral disc hernia. Chinese Journal of Medical Imaging Technology, 33(3): 458-461.

30. Papadakis AE and Damilakis J (2019) Automatic tube current modulation and tube voltage selection in pediatric computed tomography: A phantom study on radiation dose and image quality. Invest Radiol, 54(5): 265-272. [DOI:10.1097/RLI.0000000000000537]

31. Euler A, Taslimi T, Eberhard M, et al. (2021) Computed tomography angiography of the aorta-optimization of automatic tube voltage selection settings to reduce radiation dose or contrast medium in a prospective randomized trial. Invest Radiol, 56(5): 283-291. [DOI:10.1097/RLI.0000000000000740]

Send email to the article author

Rights and permissions
	This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

Persian site map - English site map - Created in 0.05 seconds with 50 queries by YEKTAWEB 4722