SignificanceBreast cancer ranks second in the world in terms of the number of women diagnosed. Effective methods for its early-stage detection are critical for facilitating timely intervention and lowering the mortality rate.AimPolarimetry provides much useful information on the structural properties of breast cancer tissue samples and is a valuable diagnostic tool. The present study classifies human breast tissue samples as healthy or cancerous utilizing a surface-illuminated backscatter polarization imaging technique.ApproachThe viability of the proposed approach is demonstrated using 95 breast tissue samples, including 35 healthy samples, 20 benign cancer samples, 20 grade-2 malignant samples, and 20 grade-3 malignant samples.ResultsThe observation results reveal that element m23 in the Mueller matrix of the healthy samples has a deeper color and greater intensity than that in the breast cancer samples. Conversely, element m32 shows a lighter color and reduced intensity. Finally, element m44 has a darker color in the healthy samples than in the cancer samples. The analysis of variance test results and frequency distribution histograms confirm that elements m23, m32, and m44 provide an effective means of detecting and classifying human breast tissue samples.ConclusionsOverall, the results indicate that surface-illuminated backscatter polarization imaging has significant potential as an assistive tool for breast cancer diagnosis and classification.
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.
Recently, backscattering polarization images have been used to explore the microstructures of biological tissues. A proposed study is presented for classifying different samples including a set of 7.4 pH Phosphate-buffered saline (PBS), plasma fibronectin (FN), fibronectin fibril assembly at 0.25 ml/h (FFN 25), and fibronectin fibril assembly at 0.48 ml/h (FFN 48) based on the Mueller matrix backscattering images. The research showed that the diagonal components values m22, m33, and m44 of PBS are considerably higher than those of the fibrillated fibronectin samples (i.e. FN, FFN 25 and FFN 48). In other words, PBS samples are more isotropic than the others whereas FFN 25 and FFN 48 are anisotropic. Furthermore, the frequency distribution histograms (FDHs) of all Mueller matrix elements are evaluated for yielding critical explicit structural information in the form of distinct values that may be used to distinguish four samples. The results also indicated that FFN 48 has the most noticeable depolarization properties. As a consequence, this approach has shown to be an effective method of assessing microstructural research.
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.
Liver cancer is currently ranked to be the sixth most common cancer worldwide. Indeed,
hepatocellular carcinoma (HCC) is the most frequent type of liver cancer. In this study, we
applied an optical polarization system utilizing the Stokes-Mueller matrix to differentiate the
HCC tissues with normal ones based on optical characteristics decomposed from the interaction
of cancerous and normal tissues with polarized light. Nine optical parameters from tissues were
extracted, specifically LB orientation angle (α), the LB phase retardance (β), the CB optical
rotation angle (γ), the LD orientation angle (θd), the linear dichroism (D), the circular
dichroism (R), the degrees of linear depolarization (e1 and e2), the degree of circular
depolarization (e3), and the depolarization index (Δ). The experimental results showed that the
orientation angle of linear birefringence (α), linear dichroism (D), and orientation angle of
linear dichroism (θd) have the differences between cancerous and normal tissues. It promises a
practical penetration to the optical characteristic of liver cancer based on Stokes-Mueller matrix
polarimetry.
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.
Skin cancer is one of the most common cancers, including melanoma and nonmelanoma cancer. Melanoma can be easily detected by the observation of abnormal moles, but nonmelanoma signs and symptoms are not apparent in the early stages. We use the Stokes–Mueller matrix decomposition method to detect nonmelanoma at the early stage by decomposing the characteristics of polarized light interacting with normal and cancerous tissues. With this decomposition method, we extract nine optical parameters from biological tissues, namely the LB orientation angle (α), the LB phase retardance (β), the CB optical rotation angle (γ), the LD orientation angle (θd), the linear dichroism (D), the circular dichroism (R), the degrees of linear depolarization (e1 and e2), the degree of circular depolarization (e3), and the depolarization index (Δ). The healthy skin and the induced nonmelanoma skin cancer of mice are analyzed and compared based on their optical parameters. We find distinctive ranges of values for normal skin tissue and nonmelanoma skin cancer, in which β and D in cancerous tissue are larger and nonmelanoma skin becomes less depolarized. This research creates an innovative solid foundation for the diagnosis of skin cancer in the future.
An analytical technique based on Stokes polarimetry and the Mueller matrix method is proposed for extracting the effective linear birefringence, linear dichroism, circular birefringence, circular dichroism, linear depolarization, and circular depolarization properties of turbid media. In contrast to existing analytical models, the model proposed extracts the effective parameters in a decoupled manner and considers not only the circular dichroism properties of the sample, but also the depolarization properties. The results show that the proposed method enables all of the effective parameters to be measured over the full range. Moreover, it is shown that the extracted value of the depolarization index is unaffected by the order in which the depolarizing Mueller matrix is decomposed during the extraction procedure. Finally, a method is proposed for calibrating the optical rotation angle of a polystyrene microsphere suspension containing dissolved D-glucose (C 6 H 12 O 6 ) powder in accordance with the distance between the sample and the detector. The experimental results show that the sensitivity of the resulting D-glucose measurement is equal to approximately 1.73 deg/M .
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.