Automatic Diagnosis of Traumatic Brain Injury Using Deep Learning with CT scan Images

Document Type : Original Paper

Authors

1 Associate Professor of Emergency medicine, Department of Emergency Medicine, Faculty of Medicine, Mashhad University of Medical Sciences, Mashhad, Iran

2 Assistant professor of Emergency medicine, Department of Emergency Medicine, Faculty of Medicine, Mashhad University of Medical Sciences, Mashhad, Iran

3 Master of Biomedical Engineering, Clinical Research Development Unit ,Shahid Hasheminejad Hospital, Medical Sciences University Of Mashhad, Mashhad,Iran

10.22038/ijmp.2025.78206.2392

Abstract

Introduction: Traumatic brain injury (TBI) results from external mechanical forces to the head, leading to brain dysfunction. The severity of injury significantly impacts patient health outcomes. Rapid and accurate diagnosis is essential for timely clinical intervention. Computed Tomography (CT) scans are currently the primary imaging modality for identifying intracranial injuries. However, manual analysis of CT images is time-consuming and highly dependent on radiologists’ expertise.
Material and Methods: This study proposes an automated approach for detecting intracranial hemorrhage and skull fractures using Convolutional Neural Networks (CNNs). CT scan images containing various pathologies were collected from the Picture Archiving and Communication System (PACS). The dataset was divided into two classes: pathological and non-pathological. Images were resized to 128 × 128 pixels to reduce computational complexity and split into training (90%) and validation (10%) sets. Pre-trained ResNet18 and ResNet34 models were employed for classification. Evaluation metrics such as accuracy, precision, recall, and F-score were computed using a confusion matrix.
Results: The CNN model achieved an accuracy of 0.94, a precision of 1.0, and a recall of 0.88 in classifying CT images.
Conclusion: These findings indicate that CNN-based models can assist radiologists in faster and more consistent diagnosis of traumatic brain injuries. Further improvements may be achieved by increasing dataset size, refining preprocessing steps, and applying advanced optimization techniques to enhance generalization and robustness.

Keywords

Main Subjects

References

  1. Noor NS, Ibrahim H. Machine learning algorithms and quantitative electroencephalography predictors for outcome prediction in traumatic brain injury: A systematic review. IEEE Access. 2020 Jun 1;8:102075-92.
  2. Raj R, Luostarinen T, Pursiainen E, Posti JP, Takala RS, Bendel S, et al. Machine learning-based dynamic mortality prediction after traumatic brain injury. Scientific reports. 2019 Nov 27;9(1):17672.
  3. GBD 2019 Dementia Collaborators. The burden of dementia due to Down syndrome, Parkinson’s disease, stroke, and traumatic brain injury: a systematic analysis for the Global Burden of Disease Study 2019. Neuroepidemiology. 2021 Jun 28;55(4):286-96.
  4. Stubbs JL, Thornton AE, Sevick JM, Silverberg ND, Barr AM, Honer WG, et al. Traumatic brain injury in homeless and marginally housed individuals: a systematic review and meta-analysis. The Lancet Public Health. 2020 Jan 1;5(1):e19-32.
  5. De Geus EQ, Milders MV, Van Horn JE, Jonker FA, Fassaert T, Hutten JC, et al. Acquired brain injury and interventions in the offender population: a systematic review. Frontiers in psychiatry. 2021 May 7;12:658328.
  6. Ponsford J, Fleminger S. Long term outcome of traumatic brain injury. British Medical Journal. 2005;331(7530):1419-20.
  7. Williams WH, Evans JJ. Brain injury and emotion: An overview to a special issue on biopsychosocial approaches in neurorehabilitation. Neuropsychological rehabilitation. 2003 Jan 1;13(1-2):1-1.
  8. Mohd Noor NS, Ibrahim H. Predicting outcomes in patients with traumatic brain injury using machine learning models. InIntelligent Manufacturing and Mechatronics: Proceedings of the 2nd Symposium on Intelligent Manufacturing and Mechatronics–SympoSIMM 2019, 8 July 2019, Melaka, Malaysia 2020 (pp. 12-20). Springer Singapore.
  9. Kuang Z, Deng X, Yu L, Zhang H, Lin X, Ma H. Skull R-CNN: A CNN-based network for the skull fracture detection. InMedical Imaging with Deep Learning 2020 Sep 21 (pp. 382-392). PMLR.
  10. Rajaei F, Cheng S, Williamson CA, Wittrup E, Najarian K. AI-based decision support system for traumatic brain injury: a survey. Diagnostics. 2023 May 5;13(9):1640.
  11. Shao H, Zhao H. Automatic analysis of a skull fracture based on image content. InThird International Symposium on Multispectral Image Processing and Pattern Recognition 2003 Sep 25 (Vol. 5286, pp. 741-746). SPIE.
  12. Chilamkurthy S, Ghosh R, Tanamala S, Biviji M, Campeau NG, Venugopal VK, et al. Deep learning algorithms for detection of critical findings in head CT scans: a retrospective study. The Lancet. 2018 Dec 1;392(10162):2388-96.
  13. Hale AT, Stonko DP, Lim J, Guillamondegui OD, Shannon CN, Patel MB. Using an artificial neural network to predict traumatic brain injury. Journal of Neurosurgery: Pediatrics. 2018 Nov 2;23(2):219-26.
  14. Albert B, Zhang J, Noyvirt A, Setchi R, Sjaaheim H, Velikova S, et al. Automatic EEG processing for the early diagnosis of traumatic brain injury. Procedia Computer Science. 2016 Jan 1;96:703-12.
  15. Ellethy H, Chandra SS, Nasrallah FA. The detection of mild traumatic brain injury in paediatrics using artificial neural networks. Computers in Biology and Medicine. 2021 Aug 1;135:104614.
  16. Sinha M, Kennedy CS, Ramundo ML. Artificial neural network predicts CT scan abnormalities in pediatric patients with closed head injury. Journal of Trauma and Acute Care Surgery. 2001 Feb 1;50(2):308-12.
  17. Grewal M, Srivastava MM, Kumar P, Varadarajan S. Radnet: Radiologist level accuracy using deep learning for hemorrhage detection in ct scans. In2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018) 2018 Apr 4 (pp. 281-284). IEEE.
  18. Mansour RF, Aljehane NO. An optimal segmentation with deep learning based inception network model for intracranial hemorrhage diagnosis. Neural Computing and Applications. 2021 Oct;33(20):13831-43.
  19. Nag MK, Gupta A, Hariharasudhan AS, Sadhu AK, Das A, Ghosh N. Quantitative analysis of brain herniation from non-contrast CT images using deep learning. Journal of Neuroscience Methods. 2021 Feb 1;349:109033.
  20. Aghazadeh BS, Khaleghi M, Pidaparti R, Najarian K. Intracranial pressure (ICP) level estimation using textural features of brain CT images. Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization. 2013 Sep 1;1(3):130-7.
  21. Chen W, Belle A, Cockrell C, Ward KR, Najarian K. Automated midline shift and intracranial pressure estimation based on brain CT images. Journal of visualized experiments: JoVE. 2013(74).
  22. Tu KC, Eric Nyam TT, Wang CC, Chen NC, Chen KT, Chen CJ, et al. A computer-assisted system for early mortality risk prediction in patients with traumatic brain injury using artificial intelligence algorithms in emergency room triage. Brain sciences. 2022 May 7;12(5):612.
  23. Shahraki G, Irankhah E. Diagnosis of epilepsy disease with MRI images analysis and EEG signal processing. InProceedings of the 2nd International Conference on Electronics, Biomedical Engineering, and Health Informatics: ICEBEHI 2021, 3–4 November, Surabaya, Indonesia 2022 Jun 25 (pp. 529-545). Singapore: Springer Nature Singapore.
  24. Hassanipour S, Ghaem H, Arab-Zozani M, Seif M, Fararouei M, Abdzadeh E, et al. Comparison of artificial neural network and logistic regression models for prediction of outcomes in trauma patients: A systematic review and meta-analysis. Injury. 2019 Feb 1;50(2):244-50.
  25. Rau CS, Kuo PJ, Chien PC, Huang CY, Hsieh HY, Hsieh CH. Mortality prediction in patients with isolated moderate and severe traumatic brain injury using machine learning models. PloS one. 2018 Nov 9;13(11):e0207192.
  26. Abujaber A, Fadlalla A, Gammoh D, Abdelrahman H, Mollazehi M, El-Menyar A. Prediction of in-hospital mortality in patients with post traumatic brain injury using National Trauma Registry and Machine Learning Approach. Scandinavian journal of trauma, resuscitation and emergency medicine. 2020 Dec;28:1-0.
  27. Gu J, Wang Z, Kuen J, Ma L, Shahroudy A, Shuai B, et al. Recent advances in convolutional neural networks. Pattern recognition. 2018 May 1;77:354-77.
  28. Venkatesan R, Li B. Convolutional neural networks in visual computing: a concise guide. CRC Press; 2017 Oct 23.
  29. Chen L, Cruz A, Ramsey S, Dickson CJ, Duca JS, Hornak V, et al. Hidden bias in the DUD-E dataset leads to misleading performance of deep learning in structure-based virtual screening. PloS one. 2019 Aug 20;14(8):e0220113.
  30. Krishna ST, Kalluri HK. Deep learning and transfer learning approaches for image classification. International Journal of Recent Technology and Engineering (IJRTE). 2019 Feb;7(5S4):427-32.
  31. Chen Z, Jiang Y, Zhang X, Zheng R, Qiu R, Sun Y, et al. ResNet18DNN: prediction approach of drug-induced liver injury by deep neural network with ResNet18. Briefings in Bioinformatics. 2022 Jan;23(1):bbab503.
  32. Hasnain M, Pasha MF, Ghani I, Imran M, Alzahrani MY, Budiarto R. Evaluating trust prediction and confusion matrix measures for web services ranking. Ieee Access. 2020 May 13;8:90847-61.
  33. Pappu S, Lerma J, Khraishi T. Brain CT to assess intracranial pressure in patients with traumatic brain injury. Journal of Neuroimaging. 2016 Jan;26(1):37-40.
  34. Subaar C, Addai FT, Addison EC, Christos O, Adom J, Owusu-Mensah M, et al. Investigating the detection of breast cancer with deep transfer learning using ResNet18 and ResNet34. Biomedical Physics & Engineering Express. 2024 Apr 18;10(3):035029.

 

Iranian Journal of Medical Physics
Volume 22, Issue 2
March and April 2025
Pages 105-113

Files

History

  • Receive Date: 14 March 2024
  • Revise Date: 02 July 2025
  • Accept Date: 22 April 2025

Share

How to cite

Statistics