A novel method of artificial intelligence (AI) classification is proposed for hepatitis B virus (HBV) detection based on the Mueller matrix imaging system. The feasibility of the proposed technique is demonstrated by measuring the optical properties of non-infected and infected HBV blood samples. Furthermore, different AI classifier techniques namely Yolo5, Yolo5-Restnet101, Yolo5-EfficientnetB0, and Yolo5-MobilenetV2 have been employed to classify the HBV samples. The results show that the proposed method provides 99% accuracy for HBV classification. In general, the proposed technique provides reliable and simple devices for HBV diagnosis applications.
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 4 × 4 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 M22 and M33 provide the best discriminatory power between the positive and negative samples.Results: As a result, M22 and M33 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 M22 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.
Significance: The Mueller matrix decomposition method is widely used for the analysis of biological samples. However, its presumed sequential appearance of the basic optical effects (e.g., dichroism, retardance, and depolarization) limits its accuracy and application.
Aim: An approach is proposed for detecting and classifying human melanoma and non-melanoma skin cancer lesions based on the characteristics of the Mueller matrix elements and a random forest (RF) algorithm.
Approach: In the proposal technique, 669 data points corresponding to the 16 elements of the Mueller matrices obtained from 32 tissue samples with squamous cell carcinoma (SCC), basal cell carcinoma (BCC), melanoma, and normal features are input into an RF classifier as predictors.
Results: The results show that the proposed model yields an average precision of 93%. Furthermore, the classification results show that for biological tissues, the circular polarization properties (i.e., elements m44, m34, m24, and m14 of the Mueller matrix) dominate the linear polarization properties (i.e., elements m13, m31, m22, and m41 of the Mueller matrix) in determining the classification outcome of the trained classifier.
Conclusions: Overall, our study provides a simple, accurate, and cost-effective solution for developing a technique for classification and diagnosis of human skin cancer.
Neuroblastoma has been considered as one of the most common extracranial solid tumors of childhood. In this study, we propose a non-invasive diagnostic measurement in evaluating the malignant level of neuroblastoma utilizing the Mueller matrix decomposition to extract effective optical parameters. The results showed a significant difference in optical properties between good and bad prognosis neuroblastoma samples.
A novel optical polarimetry technique for performing non-invasive glucose monitoring is proposed. In the proposed approach, a differential Mueller matrix polarimetry technique is used to extract the optical rotation angle and depolarization index of the sample. The glucose concentration of the sample is detected by sensing the change in the polarization plane of the incident light as it passes through the sample. The feasibility of the proposed technique is demonstrated by measuring the glucose contents of phantom solutions with known glucose concentrations in the range of 0~500 mg/dL by using two different Stokes-Mueller matrix polarimetric measurement systems. The practical applicability of the proposed technique is confirmed by measuring the glucose concentration of mice.
A novel technique based on optical coherence tomography (OCT) for noninvasive glucose monitoring is proposed. The feasibility of the proposed technique is demonstrated by detecting the glucose concentration of aqueous solution ranging from 0-4000 mg/dL with 0.02% lipofundin. The practical applicability of the proposed technique is demonstrated by detecting the glucose concentration of the human fingertip tissue based on the oral glucose tolerance test (OGTT).
A method is proposed for determining the glucose concentration on the human fingertip by extracting two optical parameters, namely the optical rotation angle and the depolarization index, using a Mueller optical coherence tomography technique and a genetic algorithm. The feasibility of the proposed method is demonstrated by measuring the optical rotation angle and depolarization index of aqueous glucose solutions with low and high scattering, respectively. It is shown that for both solutions, the optical rotation angle and depolarization index vary approximately linearly with the glucose concentration. As a result, the ability of the proposed method to obtain the glucose concentration by means of just two optical parameters is confirmed. The practical applicability of the proposed technique is demonstrated by measuring the optical rotation angle and depolarization index on the human fingertip of healthy volunteers under various glucose conditions.
A novel method for surface plasmon resonance (SPR) enhanced circular dichroism (CD), circular birefringence (CB), and degree of polarization (Dep) detection is proposed using Stokes-Mueller matrix polarimetry technique. The validity of the analytical model is confirmed by means of numerical simulations, and the simulation results show that the proposed detection method for CB and CD has a sensitivity of 10-5 RIU and 10-4 RIU (refractive index unit) for refractive indices in the range of 1.3~1.4, respectively. The practical feasibility of the proposed method is demonstrated by the experimental results for detecting the CB/CD/Dep with the glucose-chlorophyllin compound samples contained polystyrene microsphere particles. It is shown that the extracted CB value decreases linearly with glucose concentration over the considered range while the extracted CD value increases linearly with the chlorophyll concentration over the considered range. In general, the results obtained in this study show that the measured CB and CD response is highly sensitive to the polarization scanning angle. Consequently, the potential of Stokes-Mueller matrix polarimetry for highresolution in CB/CD/Dep detection is confirmed.
A novel of glucose sensing method based on differential Mueller matrix polarimetry is proposed. An analytical model is derived for extracting the optical rotation angle (γ) and degree of depolarization properties (Δ) of glucose sample with scattering affects. The practical feasibility of the proposed method is demonstrated by the experimental results for the sensitivity of the γ and Δ with the glucose samples with 2% phantom particles. The results show that the extracted valued of γ and Δ vary linearly with the glucose concentration over the measured range of 0 to 100 mg/dl with lowest increment of 20 mg/dl. In general, the proposed technique provides a reliable and simple method for low concentration of glucose sensing.
A surface plasmon resonance (SPR)-enhanced method is proposed for measuring the circular dichroism (CD), circular birefringence (CB), and degree of polarization (DOP) of turbid media using a Stokes–Mueller matrix polarimetry technique. The validity of the analytical model is confirmed by means of numerical simulations. The simulation results show that the proposed detection method enables the CD and CB properties to be measured with a resolution of 10−4 refractive index unit (RIU) and 10−5 RIU, respectively, for refractive indices in the range of 1.3 to 1.4. The practical feasibility of the proposed method is demonstrated by detecting the CB/CD/DOP properties of glucose–chlorophyllin compound samples containing polystyrene microspheres. It is shown that the extracted CB value decreases linearly with the glucose concentration, while the extracted CD value increases linearly with the chlorophyllin concentration. However, the DOP is insensitive to both the glucose concentration and the chlorophyllin concentration. Consequently, the potential of the proposed SPR-enhanced Stokes–Mueller matrix polarimetry method for high-resolution CB/CD/DOP detection is confirmed. Notably, in contrast to conventional SPR techniques designed to detect relative refractive index changes, the SPR technique proposed in the present study allows absolute measurements of the optical properties (CB/CD/DOP) to be obtained.
A high performance system for full Stokes vector measurements was developed. The proposed system comprised a polarization scanning generator (PSG) and a high accuracy polarization state analyzer (PSA) was proposed. The PSG generated full state of polarization of light by using voltage driven electro-optics modulator without using any mechanical moving parts. The PSA was employed to record the intensity of output polarized lights in a high speed manner. The accuracy of proposed system was 10-4 for all Stokes vector (S0, S1, S2, S3) measurements in the full state of polarization of lights. An application of proposed system for low concentration glucose in aqueous solution sensing with/without scattering effects was demonstrated. The sensitivity of the optical rotation angle of CB property to changes in the concentration of glucose sample was examined over the range from 0 to 0.5g/dl. The results confirm that the proposed system is able to detect glucose at fine concentration of 0.02g/dl. The linear variation of the optical rotation angle and different glucose concentration at different scattering effects was obtained. In general, the new measurement system proposed in this study provided a fast and reliable method to measure all Stokes vectors and its potential applications in biological sensing.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.