Layer thickness prediction and tissue classification in two-layered tissue structures using diffuse reflectance spectroscopy

Freija Geldof,Theo J M Ruers,Benno H W Hendriks,Henricus J C M Sterenborg,Behdad Dashtbozorg

doi:10.1038/s41598-022-05751-5

Abstract

During oncological surgery, it can be challenging to identify the tumor and establish adequate resection margins. This study proposes a new two-layer approach in which diffuse reflectance spectroscopy (DRS) is used to predict the top layer thickness and classify the layers in two-layered phantom and animal tissue. Using wavelet-based and peak-based DRS spectral features, the proposed method could predict the top layer thickness with an accuracy of up to 0.35 mm. In addition, the tissue types of the first and second layers were classified with an accuracy of 0.95 and 0.99. Distinguishing multiple tissue layers during spectral analyses results in a better understanding of more complex tissue structures encountered in surgical practice.

Highlights

IntroductionIt can be challenging to identify the tumor and establish adequate resection margins
During oncological surgery, it can be challenging to identify the tumor and establish adequate resection margins
This study aims to use diffuse reflectance spectroscopy (DRS) to predict the top layer thickness in two-layered tissue structures and classify the tissue type of both layers

Summary

Introduction

It can be challenging to identify the tumor and establish adequate resection margins. Examples include hyperspectral imaging[14,15], elastic scattering spectroscopy[16,17], and Raman s pectroscopy[18,19] Common advantages of these optical techniques are that they are fast, non-invasive, and do not require administration of contrast agents. DRS has been successfully evaluated for detection of cancer in b reast20,21,29, colorectal[30,31,32,33,34], head and neck22,35,36, liver23,24, lung[25,26], and b rain[27,28] tissue, in both ex vivo and in vivo studies These studies showed that tumor tissue could be discriminated from healthy tissue with classification accuracies of 0.77–1.00, suggesting this technique has a great potential for real-time tissue assessment during surgery. The measured tissue is often inhomogeneous and may consist of several layers, which decreases the performance of current analytical models, such as described by Farrell et al.[37,38]

Objectives

Methods

Results

Discussion

Conclusion