Enhancing Surgical Guidance: Deep Learning-Based Liver Vessel Segmentation in Real-Time Ultrasound Video Frames.

Simple Summary: In liver surgery, the complex and individualized nature of liver vascular anatomy makes planning and execution challenging. Traditional 2D intraoperative ultrasonography (IOUS) often suffers from interpretability issues due to noise and artifacts. This paper introduces an AI-based model, the "2D-weighted U-Net model," designed to enhance real-time IOUS navigation by accurately segmenting key blood vessels, including the inferior vena cava, hepatic veins, portal vein, and its major branches. Our deep learning model demonstrated high performance, with Dice scores ranging from 0.84 to 0.96 across different vessels. This advancement promises improved precision in liver resection procedures and sets the stage for future development of real-time multi-label segmentation for broader liver vasculature. Background/Objectives: In the field of surgical medicine, the planning and execution of liver resection procedures present formidable challenges, primarily attributable to the intricate and highly individualized nature of liver vascular anatomy. In the current surgical milieu, intraoperative ultrasonography (IOUS) has become indispensable; however, traditional 2D ultrasound imaging's interpretability is hindered by noise and speckle artifacts. Accurate identification of critical structures for preservation during hepatectomy requires advanced surgical skills. Methods: An AI-based model that can help detect and recognize vessels including the inferior vena cava (IVC); the right (RHV), middle (MHV), and left (LVH) hepatic veins; the portal vein (PV) and its major first and second order branches the left portal vein (LPV), right portal vein (RPV), and right anterior (RAPV) and posterior (RPPV) portal veins, for real-time IOUS navigation can be of immense value in liver surgery. This research aims to advance the capabilities of IOUS-guided interventions by applying an innovative AI-based approach named the "2D-weigthed U-Net model" for the segmentation of multiple blood vessels in real-time IOUS video frames. Results: Our proposed deep learning (DL) model achieved a mean Dice score of 0.92 for IVC, 0.90 for RHV, 0.89 for MHV, 0.86 for LHV, 0.95 for PV, 0.93 for LPV, 0.84 for RPV, 0.85 for RAPV, and 0.96 for RPPV. Conclusion: In the future, this research will be extended for real-time multi-label segmentation of extended vasculature in the liver, followed by the translation of our model into the surgical suite. [ABSTRACT FROM AUTHOR]