Self Learning Surgical Planning

Brief description of the context of the research including potential impact

Computer assisted image guidance has enabled the advancement of minimally invasive cancer procedures. For instance, ultrasound is used for prostate biopsy to help locate tumours and guide the placement of biopsy needles. However, up to 20% of clinically significant prostate tumours can still be missed due to imprecise planning and delivery. Laparoscopic liver resection could benefit patients with primary or metastatic liver cancer, but only 5-30% undergo this due to high risks faced when lesions are close to major vascular structures.

Surgical planning can address the challenges faced during these procedures, such as precise targeting of the tumours and navigation of instruments. Currently, this is limited to identifying pathology and anatomy on pre-operative images, which help clinicians plan their strategy. However, actions taken intra-operatively are subject to non-trivial human interpretation, such as hand-eye coordination and interpretation of guidance images. These suffer from inter-operator variability, due to clinicians' varying years of experience.

Reinforcement learning (RL) is a promising field in machine learning, in which the overall aim is to learn suitable actions to take in a given situation, to maximise a reward. This enables the learning of complex tasks, making it suited for surgical planning.

This project will explore a new trial-and-error paradigm to investigate the best intra-procedural actions by using pre-operative planning images. Deep RL will be utilised to train intelligent agents that predict the best "actionable" suggestions. This brings the benefit of improving outcomes, reducing postoperative complications and enabling faster recovery. The overall impact of this research will enable better healthcare through improved efficacy. It has potential to be used for other surgical interventions beyond prostate and liver cancer.

Aims and Objectives

The overall goal is to develop a self-learning surgical planning system that can optimise intra-operative actions. This aims to improve current surgical planning strategies.

The project will involve constructing an RL environment using clinical data and example expert actions. Different types of rewards, actions and interactions with the environment will be explored. Finally, RL algorithms will be implemented to learn optimal actions in given situations, to be applied to target clinical applications of prostate and liver cancer procedures.

Novelty of Research Methodology

This project aims to develop the first self-learned surgical planning system. The impact of applying RL to enhance surgical planning will be explored. This will determine if clinicians can benefit from optimising intra-operative actions prior to procedures. This project aims to reduce operator subjectivity and assist clinicians through complex tasks, which are known to be underperformed by current surgical planning approaches.

Alignment to EPSRC's strategies and research areas

This project will make use of novel computational and imaging methods to implement algorithms to guide surgeons through complex decision-making processes. This aligns with multiple discipline areas defined by EPSRC, including Artificial Intelligence Technologies, Human-Computer Interaction and Medical Imaging.

This project also addresses multiples challenges in the Healthcare Technologies Grand Challenges. These include Frontiers of Physical Intervention and Optimising Treatment through the development of RL intelligent agents that can improve both image-guided biopsy, focal therapy and laparoscopic liver surgery, as well as Novel Imaging Technologies by improving the automation and precision of current imaging methods for navigation and targeting.

Any companies or collaborators involved

N/A

The critical mass of scientists and engineers that i4health will produce will ensure the UK's continued standing as a world-leader in medical imaging and healthcare technology research. In addition to continued academic excellence, they will further support a future culture of industry and entrepreneurship in healthcare technologies driven by highly trained engineers with deep understanding of the key factors involved in delivering effective translatable and marketable technology. They will achieve this through high quality engineering and imaging science, a broad view of other relevant technological areas, the ability to pinpoint clinical gaps and needs, consideration of clinical user requirements, and patient considerations. Our graduates will provide the drive, determination and enthusiasm to build future UK industry in this vital area via start-ups and spin-outs adding to the burgeoning community of healthcare-related SMEs in London and the rest of the UK. The training in entrepreneurship, coupled with the vibrant environment we are developing for this topic via unique linkage of Engineering and Medicine at UCL, is specifically designed to foster such outcomes. These same innovative leaders will bolster the UK's presence in medical multinationals - pharmaceutical companies, scanner manufacturers, etc. - and ensure the UK's competitiveness as a location for future R&D and medical engineering. They will also provide an invaluable source of expertise for the future NHS and other healthcare-delivery services enabling rapid translation and uptake of the latest imaging and healthcare technologies at the clinical front line. The ultimate impact will be on people and patients, both in the UK and internationally, who will benefit from the increased knowledge of health and disease, as well as better treatment and healthcare management provided by the future technologies our trainees will produce.

In addition to impact in healthcare research, development, and capability, the CDT will have major impact on the students we will attract and train. We will provide our talented cohorts of students with the skills required to lead academic research in this area, to lead industrial development and to make a significant impact as advocates of the science and engineering of their discipline. The i4health CDT's combination of the highest academic standards of research with excellent in-depth training in core skills will mean that our cohorts of students will be in great demand placing them in a powerful position to sculpt their own careers, have major impact within our discipline, while influencing the international mindset and direction. Strong evidence demonstrates this in our existing cohorts of students through high levels of conference podium talks in the most prestigious venues in our field, conference prizes, high impact publications in both engineering, clinical, and general science journals, as well as post-PhD fellowships and career progression. The content and training innovations we propose in i4health will ensure this continues and expands over the next decade.