Decision Support System to triage of liver trauma

TL;DR

This study tackles the urgent need for rapid, accurate triage of liver trauma in CT scans by adopting a Pix2Pix GAN-based segmentation approach. Leveraging two datasets—open 3DIRCAD and the Shahid Rajaee trauma collection—the method achieves high Dice scores for liver bleeding and laceration detection on standard data ($ ext{Liver} ightarrow97\%$, $ ext{Liver Laceration} ightarrow93\%$) and strong intra-domain results on trauma CTs ($ ext{Liver} ightarrow96.3\%$, $ ext{Liver Laceration} ightarrow90\%$). Cross-domain evaluation shows the model maintains meaningful performance on unseen real-world data ($ ext{Liver} ightarrow80\%$, $ ext{Laceration} ightarrow74\%$), suggesting practical generalization. The work also demonstrates the potential to extend to other organs (kidneys, spleen) via transfer learning, positioning the approach as a pragmatic tool for rapid trauma assessment in emergency settings.

Abstract

Trauma significantly impacts global health, accounting for over 5 million deaths annually, which is comparable to mortality rates from diseases such as tuberculosis, AIDS, and malaria. In Iran, the financial repercussions of road traffic accidents represent approximately 2% of the nation's Gross National Product each year. Bleeding is the leading cause of mortality in trauma patients within the first 24 hours following an injury, making rapid diagnosis and assessment of severity crucial. Trauma patients require comprehensive scans of all organs, generating a large volume of data. Evaluating CT images for the entire body is time-consuming and requires significant expertise, underscoring the need for efficient time management in diagnosis. Efficient diagnostic processes can significantly reduce treatment costs and decrease the likelihood of secondary complications. In this context, the development of a reliable Decision Support System (DSS) for trauma triage, particularly focused on the abdominal area, is vital. This paper presents a novel method for detecting liver bleeding and lacerations using CT scans, utilising the GAN Pix2Pix translation model. The effectiveness of the method is quantified by Dice score metrics, with the model achieving an accuracy of 97% for liver bleeding and 93% for liver laceration detection. These results represent a notable improvement over current state-of-the-art technologies. The system's design integrates seamlessly with existing medical imaging technologies, making it a practical addition to emergency medical services. This research underscores the potential of advanced image translation models like GAN Pix2Pix in improving the precision and speed of medical diagnostics in critical care scenarios.

Figures (9)

• Figure 1: The architecture of the generator.
• Figure 2: The architecture of the discriminator.
• Figure 3: Preprocessing result
• Figure 4: Applying model trained by 3DIRCAD for liver segmentation to Rajaee dataset.
• Figure 5: Applying model trained by 3DIRCAD for liver tumor or cyst to Rajaee dataset for laceration.