The Focused Assessment with Sonography in Trauma (FAST) enables rapid point-of-care screening for internal hemorrhage by detecting free fluid, but its accuracy is highly operator-dependent and prone to missed diagnoses in emergency settings. While deep learning–based AI assistance can address these limitations, most existing models rely on computationally intensive networks, restricting deployment on resource-limited bedside devices. Thus, developing a lightweight architecture for free fluid detection is essential for clinical translation. We propose a lightweight model based on YOLOX, incorporating a dual-stream fusion (DSF) backbone to preserve spatial details while reducing computation, and a global fusion feedback (GFF) neck to enhance efficient multi-scale feature fusion. We also built a dedicated dataset using ultrasound images from rabbits with active liver hemorrhage to better mimic in vivo sonographic features of free fluid. Compared with mainstream detectors, our method achieves the lowest FLOPs and parameter count while maintaining superior precision, recall, and F1-score. Ablation studies validate that DSF improves accuracy and reduces complexity, and GFF further lowers computational costs with minimal performance tradeoff. The proposed approach enables fast, accurate free fluid detection on constrained bedside devices, advancing intelligent point-of-care trauma assessment.
Yang et al. (Wed,) studied this question.