Automated Traumatic Bleeding Detection in Whole-Body CT Using 3D Object Detection Model
Source abstract
Abstract
Traumatic injury remains a major cause of death worldwide, with bleeding being one of its most critical and life-threatening consequences. Whole-body computed tomography (WBCT) has become a standard diagnostic method in trauma settings; however, timely interpretation remains challenging for acute care physicians. In this study, we propose a new automated method for detecting traumatic bleeding in CT images using a three-dimensional object detection model enhanced with an atrous spatial pyramid pooling (ASPP) module. Furthermore, we incorporate a false positive (FP) reduction approach based on multi-organ segmentation, as developed in our previous study. The proposed method was evaluated on a multi-institutional dataset of delayed-phase contrast-enhanced CT images using a six-fold cross-validation approach. It achieved a maximum sensitivity of 90.0% with 587.3 FPs per case and a sensitivity of 70.0% with 46.9 FPs per case, outperforming previous segmentation-based methods. In addition, the average processing time was reduced to 4.2 ± 1.1 min. These results suggest that the proposed method enables rapid and accurate bleeding detection, demonstrating its potential for clinical application in emergency trauma care.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Medical Imaging and Analysis · Trauma and Emergency Care Studies · Artificial Intelligence in Healthcare and Education
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Medical Engineering, Graduate School of Science and Engineering, Chiba University, 1-33 Yayoi-cho, Inage-ku, Chiba 263-8522, Japan
Department of Emergency and Critical Care Medicine, Chiba University Graduate School of Medicine, 1-8-1, Inohana, Chuo-ku, Chiba 260-8677, Japan
Center for Frontier Medical Engineering, Chiba University, 1-33 Yayoi-cho, Inage-ku, Chiba 263-8522, Japan
Funding
JST SPRING
References (37)
Show source-provided references
1. Murao, S., Yamakawa, K., Kabata, D., Kinoshita, T., Umemura, Y., Shintani, A., and Fujimi, S. (2021). Effect of earlier door-to-CT and door-to-bleeding control in severe blunt trauma: A retrospective cohort study. J. Clin. Med., 10.10.3390/jcm10071522 ↗
2. World Health Organization (2025, June 10). Injuries and Violence. Available online: https://www.who.int/news-room/fact-sheets/detail/injuries-and-violence.
3. Predicting early death in patients with traumatic bleeding: Development and validation of prognostic model10.1136/bmj.e5166 ↗
4. A meta-analysis of the efficacy of whole-body computed tomography imaging in the management of trauma and injury10.1016/j.injury.2017.06.003 ↗
5. The importance of immediate total-body CT scanning10.1016/S0140-6736(17)30232-5 ↗
6. Computer-aided diagnosis: How to move from the laboratory to the clinic10.1148/radiol.11091710 ↗
7. AI-Based Computer-aided diagnosis (AI-CAD): The latest review to read first10.1007/s12194-019-00552-4 ↗
8. A fully automated rib fracture detection system on chest CT images and its impact on radiologist Performance10.1007/s00256-021-03709-8 ↗
9. Ukai, K., Rahman, R., Yagi, N., Hayashi, K., Maruo, A., Muratsu, H., and Kobashi, S. (2021). Detecting pelvic fracture on 3D-CT using deep convolutional neural networks with multi-orientated slab images. Sci. Rep., 11.10.1038/s41598-021-91144-z ↗
10. Deep learning algorithms for detection of critical findings in head CT scans: A retrospective study10.1016/S0140-6736(18)31645-3 ↗
11. Improving sensitivity on identification and delineation of intracranial hemorrhage lesion using cascaded deep learning models10.1007/s10278-018-00172-1 ↗
12. Burduja, M., Ionescu, R.T., and Verga, N. (2020). Accurate and efficient intracranial hemorrhage detection and subtype classification in 3D CT scans with convolutional and long short-term memory neural networks. Sensors, 20.10.3390/s20195611 ↗
13. A deep learning algorithm for automatic detection and classification of acute intracranial hemorrhages in head CT scans10.1016/j.nicl.2021.102785 ↗
14. Alis, D., Alis, C., Yergin, M., Topel, C., Asmakutlu, O., Bagcilar, O., Senli, Y.D., Ustundag, A., Salt, V., and Dogan, S.N. (2022). A joint convolutional-recurrent neural network with an attention mechanism for detecting intracranial hemorrhage on noncontrast head CT. Sci. Rep., 12.10.1038/s41598-022-05872-x ↗
15. Sanner, A.P., Grauhan, N.F., Brockmann, M.A., Othman, A.E., and Mukhopadhyay, A. (2024). detection of intracranial hemorrhage for trauma patients. Lecture Notes in Computer Science, Proceedings of the 27th International Conference on Pattern Recognition, Kolkata, India, 1–5 December 2024, Springer.10.1007/978-3-031-78341-8_1 ↗
16. An automatic detection approach of traumatic bleeding based on 3D CNN networks10.1587/transfun.2020IMP0014 ↗
17. Traumatic bleeding detection based on fusion of 3D shape and local texture features
18. Nurfauzi, R., Baba, A., Nakada, T., Nakaguchi, T., and Nomura, Y. (2025). Automated detection of traumatic bleeding in CT images using 3D U-Net# and multi-organ segmentation. Biomed. Phys. Eng. Express, 11.10.1088/2057-1976/adae14 ↗
19. The application of deep learning in abdominal trauma diagnosis by CT imaging10.1186/s13017-024-00546-7 ↗
20. Intracranial aneurysm detection: An object detection perspective10.1007/s11548-024-03132-z ↗
21. DeepLab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs10.1109/TPAMI.2017.2699184 ↗
22. Novel platform for development, training, and validation of computer-assisted detection/diagnosis software10.1007/s11548-020-02132-z ↗
23. TotalSegmentator: Robust segmentation of 104 anatomic structures in CT images10.1148/ryai.230024 ↗
24. He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27–30). Deep residual learning for image recognition. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.10.1109/CVPR.2016.90 ↗
25. Redmon, J., Divvala, S., Girshick, R., and Farhadi, A. (2016, January 27–30). You only look once: Unified, real-time object detection. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.10.1109/CVPR.2016.91 ↗
26. Ronneberger, O., Fischer, P., and Brox, T. (2015). U-net: Convolutional networks for biomedical image segmentation. Lecture Notes in Computer Science, Proceedings of the Medical Image Computing and Computer-Assisted Intervention–MICCAI 2015: 18th International Conference, Munich, Germany, 5–9 October 2015, Springer. Proceedings, Part III 18.
27. Neubeck, A., and Van Gool, L. (2006, January 20–24). Efficient non-maximum suppression. Proceedings of the 18th International Conference on Pattern Recognition (ICPR’06), Hong Kong, China.10.1109/ICPR.2006.479 ↗
28. Observer studies involving detection and localization: Modeling, analysis, and validation10.1118/1.1769352 ↗
29. Samuelson, F.W., and Petrick, N. (2006, January 6–9). Comparing image detection algorithms using resampling. Proceedings of the IEEE International Symposium on Biomedical Imaging (ISBI), Arlington, VA, USA.
30. Computer-aided detection of lung nodules: A review10.1117/1.JMI.6.2.020901 ↗
31. Artificial intelligence-based computer-aided diagnosis for breast cancer detection on digital mammography in Hong Kong
32. REACT-2 study group. Immediate total-body CT scanning versus conventional imaging and selective CT scanning in patients with severe trauma (REACT-2): A randomised controlled trial10.1016/S0140-6736(16)30932-1 ↗
33. Whole-body CT in patients with multiple traumas: Factors leading to missed injury10.1148/radiol.2018180492 ↗
34. An ASER AI/ML expert panel formative user research study for an interpretable interactive splenic AAST grading graphical user interface prototype10.1007/s10140-024-02202-8 ↗
35. Automated detection and classification of adrenal masses on CT using two annotation methods: Segmentation vs. bounding box10.1016/j.ejrai.2025.100003 ↗
36. Zhong, Y., Xu, Z., Han, C., Liu, Z., and Wang, Y. (2025). Bounding boxes for weakly-supervised breast cancer segmentation in DCE-MRI. Biomed. Signal Process. Control., 105.10.1016/j.bspc.2025.107656 ↗
37. Kalantar, R., Hindocha, S., Hunter, B., Sharma, B., Khan, N., Koh, D.-M., Ahmed, M., Aboagye, E.O., Lee, R.W., and Blackledge, M.D. (2023). Non-contrast CT synthesis using patch-based cycle-consistent generative adversarial network (Cycle-GAN) for radiomics and deep learning in the era of COVID-19. Sci. Rep., 13.10.1038/s41598-023-36712-1 ↗