Abstract
Abstract The distinction between malignant and benign tumors is essential to the treatment of cancer. The tissue's elasticity can be used as an indicator for the required tissue characterization. Optical coherence elastography (OCE) probes have been proposed for needle insertions but have so far lacked the necessary load sensing capabilities. We present a novel OCE needle probe that provides simultaneous optical coherence tomography (OCT) imaging and load sensing at the needle tip. We demonstrate the application of the needle probe in indentation experiments on gelatin phantoms with varying gelatin concentrations. We further implement two deep learning methods for the end-toend sample characterization from the acquired OCT data. We report the estimation of gelatin sample weight ratios [wt%] in unseen samples with a mean error of 1.21 ± 0.91 wt%. Both evaluated deep learning models successfully provide sample characterization with different advantages regarding the accuracy and inference time.
Highlights
The response to mechanical stress significantly varies for different tissue types and cancerous tissues exhibit different elasticities compared to their healthy counterpart [5]
An image Mi ∈ Rnxm assembled from a temporal sequence n of consecutive Axial scans (A-scans) Ai ∈ Rm was directly mapped to the gelatin weight ratio of the imaged sample under load
A convolutional gated recurrent unit processed the sequential A-scans iteratively and produced a feature vector containing the temporal information of Mi
Summary
The response to mechanical stress significantly varies for different tissue types and cancerous tissues exhibit different elasticities compared to their healthy counterpart [5]. Tissue elasticity can serve as a biomarker for tissue characterization. Image-based elastography has been proposed for the measurement of elasticity in biological tissue by mapping local deformations to an applied mechanical load. Optical coherence elastography (OCE) has gained attention as. We present a novel compression-based OCE needle-probe with simultaneous load sensing and imaging capabilities. We further propose the direct tissue characterization for compression-based OCE via deep learning and demonstrate our methods on tissue mimicking gelatin gels.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
