Building Healthcare Applications with LiDAR - Real-Time Tissue Identification for Surgery

In this work, we explored the use of an industrial precision handheld Laser Line Probe (LLP) with 25-micron accuracy to extract tissue viscoelastic information, with the goal of identifying healthy and cancerous tissue in real-time. This would contribute to significantly improved surgical outcomes, with scalability to resource limited environments. Reliable simulation of intraoperative palpation was achieved by keeping the LLP constant and during direct probing of a liver high fidelity tissue model. This produced a point cloud which emulated time-series data with the scan line progressively forming a depression. By extracting physical and 3D point cloud features, we trained a Random Forest model capable of classifying biophantom and non-organic samples with a <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\mathbf{9 6 \%}$</tex> 10-fold cross-validation accuracy. Clinical Relevance-There is a recognised need for real-time, point-of-procedure tissue identification during resective tumour surgery; this is made more significant by the need to account for the tissue shifting during tumour surgery in areas such as the liver and brain. This challenge with immobilisation and 'shift' leads to preoperative imaging -used to localise tumours such as MRI or CT scans- being rendered inaccurate or misleading.