Combined Mueller matrix imaging and artificial intelligence classification framework for Hepatitis B detection

Abstract

. Significance: The combination of polarized imaging with artificial intelligence (AI) technology has provided a powerful tool for performing an objective and precise diagnosis in medicine. Aim: An approach is proposed for the detection of hepatitis B (HB) virus using a combined Mueller matrix imaging technique and deep learning method. Approach: In the proposed approach, Mueller matrix imaging polarimetry is applied to obtain Mueller matrix images of 138 HBsAg-containing (positive) serum samples and 136 HBsAg-free (negative) serum samples. The kernel estimation density results show that, of the 16 Mueller matrix elements, elements and provide the best discriminatory power between the positive and negative samples. Results: As a result, and are taken as the inputs to five different deep learning models: Xception, VGG16, VGG19, ResNet 50, and ResNet150. It is shown that the optimal classification accuracy (94.5%) is obtained using the VGG19 model with element as the input. Conclusions: Overall, the results confirm that the proposed hybrid Mueller matrix imaging and AI framework provides a simple and effective approach for HB virus detection.

Analysis of polarization features of human breast cancer tissue by Mueller matrix visualization

“…For the calibration process, a standard mirror (BB1-E02, Thorlabs, Inc.) was captured and calculated the Mueller matrix images with an accuracy of 10−2 (see Ref. 30). After calibration, the polarimeter system was conducted the experiments.…”

“…23,24 The present study analyzes the polarization features of human breast cancer tissue utilizing a polarimetric imaging system based on a charge-coupled device (CCD) camera. [25][26][27][28][29][30] In the proposed approach, the backscattered light from the breast tissue is captured by the camera and processed by the Stokes-Mueller method to determine the Mueller matrix image and corresponding optical properties of the sample. The sample is then classified into one of four different classes, namely normal, cancer benign, or cancer malignant (grade 2 or 3) based on an analysis of the average intensity of the Mueller matrix elements, the analysis of variance (ANOVA) test results, and the frequency distribution histograms (FDHs) of the pixel intensity.…”