Deep Learning-Based Detection and Classification of Blunt Abdominal Trauma

Huawei Lin; Zeyuan Zhang; Longlong Zou; Chunlei Yang

doi:10.62051/ijcsit.v6n1.05

Authors

Huawei Lin
Zeyuan Zhang
Longlong Zou
Chunlei Yang

DOI:

https://doi.org/10.62051/ijcsit.v6n1.05

Keywords:

Deep learning, Blunt abdominal trauma detection, Computer-aided diagnosis and treatment system, Image detection, Image classification

Abstract

Traumatic injuries are the leading cause of death in the first four decades of human life and represent a major global public health issue. It is estimated that over 5 million people die from traumatic injuries each year worldwide. Among these, blunt abdominal trauma (BAT) accounts for approximately 75% of all blunt injuries, making it the most common type. However, in the early stages, there may be few or no obvious signs indicating serious intra-abdominal injuries, which makes assessment particularly challenging and requires a high index of clinical suspicion. In such cases, accurate and timely diagnosis of traumatic injuries is crucial. According to extensive literature research, traditional medical image classification methods often rely on manually designed feature extraction and classifiers. These methods tend to perform poorly when dealing with complex medical images. In contrast, deep learning techniques, based on end-to-end learning, can automatically learn feature representations and classification models directly from raw image data, offering better generalization performance than traditional approaches. Furthermore, there is currently a lack of computer-aided diagnosis (CAD) systems specifically designed for the detection and classification of CT images related to blunt abdominal trauma (BAT). Based on this observation, this study proposes the development of a deep learning-based CAD system aimed at supporting the diagnosis and classification of CT images for BAT.

Downloads

Download data is not yet available.

References

[1] Smith, J., Caldwell, E., D’Amours, S., Jalaludin, B., & Sugrue, M. (2005). Abdominal trauma: a disease in evolution. ANZ journal of surgery, 75(9), 790-794.

[2] Larsen, J. W., Søreide, K., Søreide, J. A., Tjosevik, K., Kvaløy, J. T., & Thorsen, K. (2022). Epidemiology of abdominal trauma: an age-and sex-adjusted incidence analysis with mortality patterns. Injury, 53(10), 3130-3138.

[3] Yanar, H., Ertekin, C., Taviloglu, K., Kabay, B., Bakkaloglu, H., & Guloglu, R. (2008). Nonoperative treatment of multiple intra-abdominal solid organ injury after blunt abdominal trauma. Journal of Trauma and Acute Care Surgery, 64(4), 943-948.

[4] Tataria, M., Nance, M. L., Holmes IV, J. H., Miller III, C. C., Mattix, K. D., Brown, R. L., ... & Brundage, S. I. (2007). Pediatric blunt abdominal injury: age is irrelevant and delayed operation is not detrimental. Journal of Trauma and Acute Care Surgery, 63(3), 608-614.

[5] Stassen, N. A., Bhullar, I., Cheng, J. D., Crandall, M., Friese, R., Guillamondegui, O., ... & Kerwin, A. (2012). Nonoperative management of blunt hepatic injury: an Eastern Association for the Surgery of Trauma practice management guideline. Journal of Trauma and Acute Care Surgery, 73(5), S288-S293.

[6] Stassen, N. A., Bhullar, I., Cheng, J. D., Crandall, M. L., Friese, R. S., Guillamondegui, O. D., ... & Kerwin, A. J. (2012). Selective nonoperative management of blunt splenic injury: an Eastern Association for the Surgery of Trauma practice management guideline. Journal of Trauma and Acute Care Surgery, 73(5), S294-S300.

[7] Stuhlfaut, J. W., Anderson, S. W., & Soto, J. A. (2007, April). Blunt abdominal trauma: current imaging techniques and CT findings in patients with solid organ, bowel, and mesenteric injury. In Seminars in Ultrasound, CT and MRI (Vol. 28, No. 2, pp. 115-129). WB Saunders.

[8] Soto, J. A., & Anderson, S. W. (2012). Multidetector CT of blunt abdominal trauma. Radiology, 265(3), 678-693.

[9] Van Schuppen, J., Olthof, D. C., Wilde, J. C. H., Beenen, L. F. M., van Rijn, R. R., & Goslings, J. C. (2014). Diagnostic accuracy of a step-up imaging strategy in pediatric patients with blunt abdominal trauma. European journal of radiology, 83(1), 206-211.

[10] Pinto, A., Reginelli, A., Pinto, F., Lo Re, G., Midiri, F., Muzj, C., ... & Brunese, L. (2016). Errors in imaging patients in the emergency setting. The British journal of radiology, 89(1061), 20150914.

[11] Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems, 25.

[12] He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 770-778).

[13] Tan, M., & Le, Q. (2019, May). Efficientnet: Rethinking model scaling for convolutional neural networks. In International conference on machine learning (pp. 6105-6114). PMLR.

[14] Litjens, G., Kooi, T., Bejnordi, B. E., Setio, A. A. A., Ciompi, F., Ghafoorian, M., ... & Sánchez, C. I. (2017). A survey on deep learning in medical image analysis. Medical image analysis, 42, 60-88.

[15] Dhungel, N., Carneiro, G., & Bradley, A. P. (2017). A deep learning approach for the analysis of masses in mammograms with minimal user intervention. Medical image analysis, 37, 114-128.

[16] Zhang, Y., & Yang, Q. (2018). An overview of multi-task learning. National Science Review, 5(1), 30-43.

[17] Liu, S., Johns, E., & Davison, A. J. (2019). End-to-end multi-task learning with attention. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (pp. 1871-1880).

[18] Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., ... & Polosukhin, I. (2017). Attention is all you need. Advances in neural information processing systems, 30.

[19] Panayides, A. S., Amini, A., Filipovic, N. D., Sharma, A., Tsaftaris, S. A., Young, A., ... & Pattichis, C. S. (2020). AI in medical imaging informatics: current challenges and future directions. IEEE journal of biomedical and health informatics, 24(7), 1837-1857.

[20] Sogancioglu, E., Murphy, K., Th. Scholten, E., Boulogne, L. H., Prokop, M., & van Ginneken, B. (2022). Automated estimation of total lung volume using chest radiographs and deep learning. Medical Physics, 49(7), 4466-4477.

[21] Liu, M. Z., Swintelski, C., Sun, S., Siddique, M., Desperito, E., Jambawalikar, S., & Ha, R. (2022). Weakly supervised deep learning approach to breast MRI assessment. Academic Radiology, 29, S166-S172.

[22] Fu, Z., Zhang, J., Luo, R., Sun, Y., Deng, D., & Xia, L. (2022). TF-Unet: An automatic cardiac MRI image segmentation method. Math. Biosci. Eng, 19(5), 5207-5222.

[23] Dreizin, D., Cheng, C. T., Liao, C. H., Jindal, A., & Colak, E. (2025). Artificial intelligence for abdominopelvic trauma imaging: trends, gaps, and future directions. Abdominal Radiology, 1-16.

[24] Ganesan, J., Azar, A. T., Kamal, N. A., & Shaikh, A. (2024). The AI Revolution: Deep Learning’s Role in Abdominal Trauma Detection. In International Conference on Advanced Intelligent Systems and Informatics (pp. 303-316). Springer, Cham.

[25] Chen, E. L., Chung, P. C., Chen, C. L., Tsai, H. M., & Chang, C. I. (1998). An automatic diagnostic system for CT liver image classification. IEEE transactions on biomedical engineering, 45(6), 783-794.

[26] Zhang, Y., & Yang, Q. (2018). An overview of multi-task learning. National Science Review, 5(1), 30-43.

[27] Tan, M., & Le, Q. (2019, May). Efficientnet: Rethinking model scaling for convolutional neural networks. In International conference on machine learning (pp. 6105-6114). PMLR.

[28] Woo, S., Park, J., Lee, J. Y., & Kweon, I. S. (2018). Cbam: Convolutional block attention module. In Proceedings of the European conference on computer vision (ECCV) (pp. 3-19).

[29] Lin, T. Y., Dollár, P., Girshick, R., He, K., Hariharan, B., & Belongie, S. (2017). Feature pyramid networks for object detection. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 2117-2125).

[30] Lin, T. Y., Goyal, P., Girshick, R., He, K., & Dollár, P. (2017). Focal loss for dense object detection. In Proceedings of the IEEE international conference on computer vision (pp. 2980-2988).

[31] Chen, Z., Badrinarayanan, V., Lee, C. Y., & Rabinovich, A. (2018, July). Gradnorm: Gradient normalization for adaptive loss balancing in deep multitask networks. In International conference on machine learning (pp. 794-803). PMLR.

[32] Rudie, J. D., Lin, H. M., Ball, R. L., Jalal, S., Prevedello, L. M., Nicolaou, S., ... & Dataset Annotator Group. (2024). The rsna abdominal traumatic injury ct (ratic) dataset. Radiology: Artificial Intelligence, 6(6), e240101.