Real-Time Ultrasound Guided Abdominal Interventions Without a Tracking Device
Lead Research Organisation:
University College London
Department Name: Medical Physics and Biomedical Eng
Abstract
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.
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.
Planned Impact
In the UK there are approximately 10,000 new cases per year of pancreatic cancer and 5,000 for liver cancer. Management and treatment of cancer is one of the biggest challenges in medicine worldwide, and costs the UK economy over £15bn per year over all cancers. The predicted rise in the cost of cancer care requires new technology for earlier diagnosis and more effective treatment.
In this project, we will develop image-guidance systems that will make ultrasound biopsy of the pancreas, and ultrasound guidance during liver surgery, quicker, safer and easier to perform. Currently, 2-dimensional (2D) ultrasound is difficult to use, requiring very highly trained staff, which consequently results in a skills shortage in the NHS, and longer waiting lists for the patient. Patients often have a 3-dimensional Magnetic Resonance (MR) or Computed Tomography (CT) scan, which are used for diagnosis and treatment planning. Our aim is to produce software that can align ultrasound with MR/CT images, and thereby provide complementary information to the clinician which will make treatment or diagnostic procedures quicker, safer and easier to perform. The proposed technology could be applied in a wide variety of clinical procedures.
Early diagnosis can help reduce treatment costs and minimise the impact on the active workforce, resulting in earlier return to a normal life, and return to work. Early diagnosis is associated with increased survival. In this grant proposal, we have a focus on biopsy of pancreatic cancer. There is a current problem in the NHS in that many pancreatic cysts are found by incidental, non cancer-related imaging. However, only 20% of detected cysts will become cancerous. But there are not enough endoscopists to perform enough biopsies, resulting in lack of treatment, or over treatment. The proposed technology will make pancreatic biopsy easier to perform, for lesser trained staff, helping reduce the burden on the NHS and providing earlier diagnosis for patients.
Ultrasound imaging is also used to administer treatment. However, high-risk procedures carry the risk of major injury or death. In laparoscopic (keyhole) liver surgery, ultrasound is used to detect major blood vessels. However, some cancers are not visible in ultrasound imaging, but are visible on MR/CT scans. By providing both types of images in a navigation system, the surgeon can make better, more informed decisions. Laparoscopic surgery has been shown to reduce complications and enable faster recovery for the patient. But currently only 10% of liver surgery patients can be offered it, due to the complexity of the surgery. The technology we propose in this grant will enable more surgeons to attempt more liver surgery laparoscopically, resulting in better quality of life for patients.
In summary, the overall impact is:
1. For the patient, earlier diagnosis, or safer treatment, improved survival rate or quality of life.
2. For the NHS, reduce costs, reduced complications, reduce skills shortage, enable lesser trained staff to adopt new techniques, and increased workload.
3. For society, earlier return to work.
In this project, we will develop image-guidance systems that will make ultrasound biopsy of the pancreas, and ultrasound guidance during liver surgery, quicker, safer and easier to perform. Currently, 2-dimensional (2D) ultrasound is difficult to use, requiring very highly trained staff, which consequently results in a skills shortage in the NHS, and longer waiting lists for the patient. Patients often have a 3-dimensional Magnetic Resonance (MR) or Computed Tomography (CT) scan, which are used for diagnosis and treatment planning. Our aim is to produce software that can align ultrasound with MR/CT images, and thereby provide complementary information to the clinician which will make treatment or diagnostic procedures quicker, safer and easier to perform. The proposed technology could be applied in a wide variety of clinical procedures.
Early diagnosis can help reduce treatment costs and minimise the impact on the active workforce, resulting in earlier return to a normal life, and return to work. Early diagnosis is associated with increased survival. In this grant proposal, we have a focus on biopsy of pancreatic cancer. There is a current problem in the NHS in that many pancreatic cysts are found by incidental, non cancer-related imaging. However, only 20% of detected cysts will become cancerous. But there are not enough endoscopists to perform enough biopsies, resulting in lack of treatment, or over treatment. The proposed technology will make pancreatic biopsy easier to perform, for lesser trained staff, helping reduce the burden on the NHS and providing earlier diagnosis for patients.
Ultrasound imaging is also used to administer treatment. However, high-risk procedures carry the risk of major injury or death. In laparoscopic (keyhole) liver surgery, ultrasound is used to detect major blood vessels. However, some cancers are not visible in ultrasound imaging, but are visible on MR/CT scans. By providing both types of images in a navigation system, the surgeon can make better, more informed decisions. Laparoscopic surgery has been shown to reduce complications and enable faster recovery for the patient. But currently only 10% of liver surgery patients can be offered it, due to the complexity of the surgery. The technology we propose in this grant will enable more surgeons to attempt more liver surgery laparoscopically, resulting in better quality of life for patients.
In summary, the overall impact is:
1. For the patient, earlier diagnosis, or safer treatment, improved survival rate or quality of life.
2. For the NHS, reduce costs, reduced complications, reduce skills shortage, enable lesser trained staff to adopt new techniques, and increased workload.
3. For society, earlier return to work.
Organisations
Publications
Bonmati E
(2022)
Voice-Assisted Image Labeling for Endoscopic Ultrasound Classification Using Neural Networks.
in IEEE transactions on medical imaging
Dowrick T
(2023)
Evaluation of a calibration rig for stereo laparoscopes.
in Medical physics
Enkaoua A
(2023)
Image-guidance in endoscopic pituitary surgery: an in-silico study of errors involved in tracker-based techniques
in Frontiers in Surgery
Fu Y
(2023)
A Recycling Training Strategy for Medical Image Segmentation with Diffusion Denoising Models
in Machine Learning for Biomedical Imaging
Li Q
(2023)
Long-term Dependency for 3D Reconstruction of Freehand Ultrasound Without External Tracker.
in IEEE transactions on bio-medical engineering
Description | Context Aware Augmented Reality for Endonasal Endoscopic Surgery |
Amount | £1,109,056 (GBP) |
Funding ID | EP/W00805X/1 |
Organisation | Engineering and Physical Sciences Research Council (EPSRC) |
Sector | Public |
Country | United Kingdom |
Start | 04/2022 |
End | 10/2025 |
Title | PROBE POSE DETERMINATION |
Description | A computer-implemented method for determining a pose of a probe with respect to volumetric scan data is provided. The method comprises receiving image data obtained from a first probe and a second probe. The method also comprises determining, using a machine learning algorithm, a pose of at least one of the first probe and the second probe relative to the volumetric scan data, from the image data. The first probe is or comprises a video camera. The second probe is located at least partially within the field of view of the video camera. |
IP Reference | WO2024028600 |
Protection | Patent / Patent application |
Year Protection Granted | 2024 |
Licensed | Commercial In Confidence |
Impact | Work is ongoing. |
Title | ULTRASOUND REGISTRATION |
Description | The invention relates to registration of ultrasound scan data with volumetric scan data. More specifically, the invention relates to registration of laparoscopic ultrasound scan data with CT or MRI scan data. |
IP Reference | 1910756.4 |
Protection | Patent application published |
Year Protection Granted | 2020 |
Licensed | No |
Impact | Further funding. |
Title | Fan-Slicer: A Pycuda Package for Fast Reslicing of Ultrasound Shaped Planes |
Description | Fan-Slicer (https://github.com/UCL/fan-slicer) is a Python package that enables the fast sampling (slicing) of 2D ultrasound-shaped images from a 3D volume. To increase sampling speed, CUDA kernel functions are used in conjunction with the Pycuda package. The main features include functions to generate images from both 3D surface models and 3D volumes. Additionally, the package also allows for the sampling of images from curvilinear (fan shaped planes) and linear (rectangle shaped planes) ultrasound transducers. Potential uses of Fan-slicer include the generation of large datasets of 2D images from 3D volumes and the simulation of intra-operative data among others. |
Type Of Technology | Software |
Year Produced | 2023 |
Open Source License? | Yes |
Impact | Just released |
URL | https://doi.org/10.5334/jors.422 |
Description | Science of Surgery Open Day |
Form Of Engagement Activity | Participation in an open day or visit at my research institution |
Part Of Official Scheme? | No |
Geographic Reach | Local |
Primary Audience | Public/other audiences |
Results and Impact | Team member Dr Joao Ramalhinho participated in several public engagement activities organised by the Wellcome/EPSRC Centre for Interventional and Surgical Sciences (WEISS). These include the WEISS Science of Surgery open day, where Dr Ramalhinho presented the SnappySonic Ultrasound Simulator. |
Year(s) Of Engagement Activity | 2019 |
URL | https://www.ucl.ac.uk/interventional-surgical-sciences/science-surgery |
Description | Science of Surgery Open Day 2022, 2023 |
Form Of Engagement Activity | Participation in an open day or visit at my research institution |
Part Of Official Scheme? | No |
Geographic Reach | Local |
Primary Audience | Public/other audiences |
Results and Impact | Various teams of researchers presented display stands, illustrating novel, interesting, or fun ideas based around surgery and science. The idea was to spark discussions with the general public. For school children, the aim was also to hopefully inspire them to consider science as an interesting topic. |
Year(s) Of Engagement Activity | 2022,2023,2024 |
URL | https://www.ucl.ac.uk/interventional-surgical-sciences/science-surgery |