Laparoscopic ultrasound-guided superselective portal vein injection combined with real-time indocyanine green fluorescence imaging and navigation for accurate resection of localized intrahepatic bile duct dilatation: a case report

Background Primary intrahepatic bile duct dilatation can be very harmful to patients although it belongs to benign biliary disease. It can occur in any part of the liver, intraoperative laparoscopic ultrasound (LUS) guidance combine with real-time indocyanine green (ICG) fluorescence navigation are the means of choice for accurate surgical resection. Case presentation Herein we reported a 43-year-old female patient presented with repeated right upper abdominal pain and distension for 3 years and aggravated for half a year, without fever and jaundice. A diagnosis of localized bile duct dilatation with lithiasis in segment 4 (S4) was made on the basis of preoperative imaging. Correspondingly, we selected to perform a laparoscopic surgery with LUS guided real time ICG fluorescence imaging (ICG-FI) and navigation to make the operation more simply and accurately, as well as to retain normal tissues in a certain extent. Laparoscopic resection of S4b and partial S4a was successfully performed, without any complications. Conclusion Laparoscopic anatomical surgery for intrahepatic bile duct dilatation is a technically challenging operation. The combined use of preoperative three-dimensional computerized tomography (CT) planning, intraoperative LUS guided super-selection, ICG hepatic segment staining and real-time fluorescence navigation could help surgeons accurately complete the segmentectomy or subsegmentectomy with minimized trauma and maximized liver tissue preservation.

Vessel segmentation for automatic registration of untracked laparoscopic ultrasound to CT of the liver

Purpose: Registration of Laparoscopic Ultrasound (LUS) to a pre-operative scan such as Computed Tomography (CT) using blood vessel information has been proposed as a method to enable image-guidance for laparoscopic liver resection. Currently, there are solutions for this problem that can potentially enable clinical translation by bypassing the need for a manual initialisation and tracking information. However, no reliable framework for the segmentation of vessels in 2D untracked LUS images has been presented. Methods: We propose the use of 2D UNet for the segmentation of liver vessels in 2D LUS images. We integrate these results in a previously developed registration method, and show the feasibility of a fully automatic initialisation to the LUS to CT registration problem without a tracking device. Results: We validate our segmentation using LUS data from 6 patients. We test multiple models by placing patient datasets into different combinations of training, testing and hold-out, and obtain mean Dice scores ranging from 0.543 to 0.706. Using these segmentations, we obtain registration accuracies between 6.3 and 16.6 mm in 50% of cases. Conclusions: We demonstrate the first instance of deep learning (DL) for the segmentation of liver vessels in LUS. Our results show the feasibility of UNet in detecting multiple vessel instances in 2D LUS images, and potentially automating a LUS to CT registration pipeline.