Application of Transfer Learning for Rapid Calibration of Spatially-resolved Diffuse Reflectance Probes for Extraction of Tissue Optical Properties

Abstract

AbstractSignificanceTreatment planning for light-based therapies including photodynamic therapy requires tissue optical property knowledge. These are recoverable with spatially-resolved diffuse reflectance spectroscopy (DRS), but requires precise source-detector separation (SDS) determination and time-consuming simulations.AimAn artificial neural network (ANN) to map from DRS at short SDS to optical properties was created. This trained ANN was adapted to fiber-optic probes with varying SDS using transfer learning.ApproachAn ANN mapping from measurements to Monte Carlo simulation to optical properties was created with one fiber-optic probe. A second probe with different SDS was used for transfer learning algorithm creation. Data from a third were used to test this algorithm.ResultsThe initial ANN recovered absorber concentration with RMSE=0.29 µM (7.5% mean error) and µs’at 665 nm (µs,665’) with RMSE=0.77 cm-1(2.5% mean error). For probe-2, transfer learning significantly improved absorber concentration (0.38 vs. 1.67 µM, p=0.0005) and µs,665’(0.71 vs. 1.8 cm-1, p=0.0005) recovery. A third probe also showed improved absorber (0.7 vs. 4.1 µM, p<0.0001) and µs,665’(1.68 vs. 2.08 cm-1, p=0.2) recovery.ConclusionsA data-driven approach to optical property extraction can be used to rapidly calibrate new fiber-optic probes with varying SDS, with as few as three calibration spectra.