Rapid and accurate determination of tissue optical properties using least-squares support vector machines

Abstract

Diffuse reflectance spectroscopy (DRS) has been extensively applied for the characterization of biological tissue, especially for dysplasia and cancer detection, by determination of the tissue optical properties. A major challenge in performing routine clinical diagnosis lies in the extraction of the relevant parameters, especially at high absorption levels typically observed in cancerous tissue. Here, we present a new least-squares support vector machine (LS-SVM) based regression algorithm for rapid and accurate determination of the absorption and scattering properties. Using physical tissue models, we demonstrate that the proposed method can be implemented more than two orders of magnitude faster than the state-of-the-art approaches while providing better prediction accuracy. Our results show that the proposed regression method has great potential for clinical applications including in tissue scanners for cancer margin assessment, where rapid quantification of optical properties is critical to the performance.

Selective sampling using confocal Raman spectroscopy provides enhanced specificity for urinary bladder cancer diagnosis

“…A likelihood ratio test was used to determine the PCs most significant for diagnosis. Also, a standard leave-one-out cross-validation protocol [27] was used for the logistic regression analysis. In this protocol, the data from a particular tissue site is eliminated, and logistic regression is used to form a decision line that classifies the remaining tissue sites maximizing agreement with the histopathology diagnoses.…”

Nanoparticle-free tissue-mimicking phantoms with intrinsic scattering

“…Detecting clinical-level changes in the parameters of bodily fluids, such as intracranial cerebrospinal fluid pressure [1], blood glucose levels [2,3], microvasculature blood flow rates [4] as well as the parameters of the blood itself [5][6][7] are of great importance and are extensively studied. Optical phantoms are used mainly for calibration and development of these optical measurement and imaging systems [8,9]. They serve as reference standards for comparison of devices and techniques as well as for studying light transport in complex, often multi-layered tissues or organs with internal vasculature [10,11].…”

Joint derivation method for determining optical properties based on steady-state spatially resolved diffuse reflectance measurement at small source-detector separations and large reduced albedo range: theory and simulation

“…[9][10][11][12] Estimations of optical properties based on spatially resolved diffuse reflectance measurements, which is also called the inverse problem, can be cataloged into two types according to the dependence of the knowledge of the light propagation in biological tissues. One type of the inverse problem, which needs a priori knowledge including partial least square (PLS), 13 neural networks (NN) 14,15 support vector machines (SVM), 16 and look-up table (LUT) approach. 17,18 However, PLS does not provide accurate predictions, as it is unable to account for the intrinsic nonlinear relationships in light transport problems.…”

“…17,18 The new SVM-based regression algorithm for determining the absorption and reduced scattering coefficients can be implemented rapidly and provide more accurate predictions than LUT. 16 Though the methods of NN, LUT, and SVM can obtain good prediction accuracy, they all need high quality calibration sets, i.e., requiring a lot of premodeling work.…”