In this section

Cognitive Vision in Robotic Surgery

The Cognitive Vision in Robotic Surgery Lab is developing computer vision and AI techniques for intraoperative navigation and real-time tissue characterisation.

Head of Group

Dr Stamatia (Matina) Giannarou

411 Bessemer Building
South Kensington Campus

+44 (0) 20 7594 8904

What we do

Surgery is undergoing rapid changes driven by recent technological advances and our on-going pursuit towards early intervention and personalised treatment. We are developing computer vision and Artificial Intelligence techniques for intraoperative navigation and real-time tissue characterisation during minimally invasive and robot-assisted operations to improve both the efficacy and safety of surgical procedures. Our work will revolutionize the treatment of cancers and pave the way for autonomous robot-assisted interventions.

Why it is important?

With recent advances in medical imaging, sensing, and robotics, surgical oncology is entering a new era of early intervention, personalised treatment, and faster patient recovery. The main goal is to completely remove cancerous tissue while minimising damage to surrounding areas. However, achieving this can be challenging, often leading to imprecise surgeries, high re-excision rates, and reduced quality of life due to unintended injuries. Therefore, technologies that enhance cancer detection and enable more precise surgeries may improve patient outcomes.

How can it benefit patients?

Our methods aim to ensure patients receive accurate and timely surgical treatment while reducing surgeons' mental workload, overcoming limitations, and minimizing errors. By improving tumor excision, our hybrid diagnostic and therapeutic tools will lower recurrence rates and enhance survival outcomes. More complete tumor removal will also reduce the need for repeat procedures, improving patient quality of life, life expectancy, and benefiting society and the economy.

Meet the team

Dr Stamatia Giannarou
Senior Lecturer

Dr Po Wen Lo
Research Associate

Mr Alfie Roddan
Research Postgraduate

Mr Alistair G Weld
Research Postgraduate

Mr Chi Xu
Research Assistant

Mr Haozheng Xu
Research Assistant in Surgical Robot Vision

Mr Yihang Zhou
Research Assistant

Citation

BibTex format

@article{Tukra:2024:10.1049/htl2.12067,
author = {Tukra, S and Xu, H and Xu, C and Giannarou, S},
doi = {10.1049/htl2.12067},
journal = {Healthcare Technology Letters},
pages = {108--116},
title = {Generalizable stereo depth estimation with masked image modelling},
url = {http://dx.doi.org/10.1049/htl2.12067},
volume = {11},
year = {2024}
}

Download

RIS format (EndNote, RefMan)

TY  - JOUR
AB  - Generalizable and accurate stereo depth estimation is vital for 3D reconstruction, especially in surgery. Supervised learning methods obtain best performance however, limited ground truth data for surgical scenes limits generalizability. Self-supervised methods don't need ground truth, but suffer from scale ambiguity and incorrect disparity prediction due to inconsistency of photometric loss. This work proposes a two-phase training procedure that is generalizable and retains the high performance of supervised methods. It entails: (1) performing self-supervised representation learning of left and right views via masked image modelling (MIM) to learn generalizable semantic stereo features (2) utilizing the MIM pre-trained model to learn robust depth representation via supervised learning for disparity estimation on synthetic data only. To improve stereo representations learnt via MIM, perceptual loss terms are introduced, which improve the model's stereo representations learnt by explicitly encouraging the learning of higher scene-level features. Qualitative and quantitative performance evaluation on surgical and natural scenes shows that the approach achieves sub-millimetre accuracy and lowest errors respectively, setting a new state-of-the-art. Despite not training on surgical nor natural scene data for disparity estimation.
AU  - Tukra,S
AU  - Xu,H
AU  - Xu,C
AU  - Giannarou,S
DO  - 10.1049/htl2.12067
EP  - 116
PY  - 2024///
SN  - 2053-3713
SP  - 108
TI  - Generalizable stereo depth estimation with masked image modelling
T2  - Healthcare Technology Letters
UR  - http://dx.doi.org/10.1049/htl2.12067
UR  - http://hdl.handle.net/10044/1/109378
VL  - 11
ER  -