A compact 2D photonic crystal biosensor for optical detection of glioblastoma brain tissues enhanced by neural networks

Abstract

Abstract In this work, a compact optical sensor based on a two-dimensional photonic crystal is proposed for detecting glioblastoma and pre-tumor brain tissues. The sensor uses a hexagonal lattice of silicon rods in air with a ring resonator structure at its center. The designed device is small in size and operates around the wavelength of 1.55 micrometers. By adjusting the structural parameters, a high-quality factor of 4777 and a figure of merit of 2333 are obtained. The sensor also shows a high sensitivity of 933 nanometers per refractive index unit and a very small detection limit of 4.2 × 10⁻⁵. The optical response remains stable when the temperature changes from 25 °C to 40 °C, showing good thermal performance. An artificial neural network (ANN) is employed for intelligent classification of the sensor response, assigning each measurement to tumor or pre-tumor tissue. The comparison with recent optical sensors confirms that the proposed design achieves better accuracy, higher quality, and smaller footprint. These results demonstrate the strong potential of the proposed sensor as a computational proof-of-concept for high-accuracy discrimination between tumorous and peritumorous brain tissues.