Real-Time Ultrasound Guided Abdominal Interventions Without a Tracking Device

This project aims to improve the ability of clinicians to diagnose and treat cancer, focussing on two specific procedures: laparoscopic liver resection and needle biopsy of the pancreas. Currently, both procedures require a high level of skill, resulting in a shortage of trained personnel, longer waiting lists and consequently delayed diagnosis or treatment, which is critical for the patient.

Ultrasound imaging is commonly used to guide a variety of procedures. In laparoscopic liver resection for example, the surgeon will use ultrasound imaging to locate major blood vessels, and plan ahead. In endoscopic biopsy, the endoscopist will use ultrasound to navigate towards the pancreas and locate a specific tumour.

However, both of these procedures are difficult, and carry the risk of mistakes. The ultrasound images are 2-dimensional (2D), and it is difficult to understand the location and orientation of the ultrasound image, with respect to the patient's anatomy. In addition, current research methods use expensive tracking devices and the software is difficult to use, so such methods cannot be commercialised or widely adopted, as they simply aren't user friendly.

We will develop new technology that will align 2D ultrasound images with 3-dimensional (3D) pre-operative scan data such as Magnetic Resonance (MR), or Computed Tomography (CT). This will give the clinician a much wider context, improve their understanding of the location and orientation of the ultrasound probe, and enable quicker procedures. In the longer term, this will make the procedure easier and quicker to perform, allowing more patients to be examined quicker.

The increase awareness and 3D context may potentially lead to fewer mistakes, and lower risk, although this is harder to demonstrate.

To achieve this goal, we will exploit recent advances in machine learning to produce an algorithm that is reliable, robust and fast. New software will display the 2D ultrasound image, alongside the 3D scan and show the location of the ultrasound probe. We will deliver a method that does not require any extra equipment, does not hinder the clinical workflow, and does not require the clinician to interact with the software as it will be automatic and hands-free.

In the longer term, these methods will be applicable to other ultrasound-based procedures in laparoscopy, endoscopy, fetal surgery, robotic surgery and beyond. The benefit to the general public will be faster and safer procedures, and the technology will enable more clinicians to perform these procedures, resulting in shorter waiting lists, and earlier treatment for the patient.