Shedding the Polarized Light on Biological Tissues

Meglinski, Igor; Trifonyuk, L.; Bachinsky, V. T.; Vanchulyak, Oleh; Bodnar, B. M.; Sidor, M. I.; Dubolazov, Olexander V.; Ушенко, А. Г.; Ushenko, Yu. A.; Soltys, I. V.; Bykov, Alexander; Hogan, Benjamin T.; Novikova, Tatiana

doi:10.1007/978-981-10-4047-4

Cited by 15 publications

(8 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A generalization of the polarization interferometry scheme [34,35] is the Stokеs-polarimetric mapping scheme on the base of Mach-Zehnder interferometer, which is shown in Figure 1.…”

Section: The Experimental Setup and Measurement Methodologymentioning

confidence: 99%

“…In parallel, a large-scale selective analysis of the obtained biological object polarization maps under study is necessary. Currently, only the first largely empirical, insufficiently systematized steps in these directions have been made and a comparatively small number of relevant scientific publications are known [31][32][33][34][35].…”

Section: Introductionmentioning

confidence: 99%

“…• Polarization-interference registration of diffuse object field [31,32]; • Digital holographic reconstruction of polarizationinhomogeneous field complex amplitudes and calculation azimuth and ellipticity polarization maps [33][34][35].…”

Section: Introductionmentioning

confidence: 99%

“…• Scale-selective wavelet analysis of layered polarization maps [32,33]. • Statistical analysis of wavelet coefficients amplitudes distributions and determination markers, which are most diagnostically sensitive to changes in the biological layer polycrystalline architectonics [35].…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

3D digital polarization‐holographic wavelet histology in determining the duration of mechanical damage to the myocardium

Ushenko,

Zheng,

Litvinenko

et al. 2024

Journal of Biophotonics

View full text Add to dashboard Cite

We aimed developing and experimentally validating methods for 3D scale‐selective polarimetry of multiply scattered fields in diffuse myocardium layers for mechanical myocardial injury prescription histological differential diagnostics. We used the synthesis of diffuse object field polarization‐interference registration and polarization‐inhomogeneous field digital holographic reconstruction and layer‐by‐layer complex amplitudes distributions The method for selection single and diffuse object field multiply scattered components polarization maps is proposed. The conditions for eliminating the distorting influence of a depolarized background high level are found. On the basis of еру object field single scattered component polarization maps a large‐scale selective wavelet analysis the criteria (markers) for mechanical myocardial injury different prescription diagnosis was determinate. Excellent accuracy mechanical injury myocardium necrotic changes with different duration using polarization‐interference wavelet differentiation were achieved.This article is protected by copyright. All rights reserved.

show abstract

“…A generalization of the polarization interferometry scheme [34,35] is the Stokеs-polarimetric mapping scheme on the base of Mach-Zehnder interferometer, which is shown in Figure 1.…”

Section: The Experimental Setup and Measurement Methodologymentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

3D digital polarization‐holographic wavelet histology in determining the duration of mechanical damage to the myocardium

Ushenko,

Zheng,

Litvinenko

et al. 2024

Journal of Biophotonics

View full text Add to dashboard Cite

show abstract

“…This property has been extensively explored in a range of contexts including remote sensing, [13][14][15] optical metrology, [16][17][18] and biomedical diagnostics. [19][20][21] Our previous studies clearly demonstrated that simple (i.e., circularly) polarized light is able to distinguish different grades of cancer. 22 This motivated an investigation into the application of a promising wide-field polarimetric technique, namely Mueller matrix (MM) polarimetry.…”

Section: Introductionmentioning

confidence: 92%

Polarimetric imaging for cervical pre-cancer screening aided by machine learning: ex vivo studies

Robinson,

Hoong,

Kleijn

et al. 2023

J. Biomed. Opt.

Self Cite

View full text Add to dashboard Cite

.SignificanceWide-field imaging Mueller polarimetry is an optical imaging technique that has great potential to become a reliable, fast, non-contact in vivo imaging modality for the early detection of, e.g., deceases and tissue structural malformations, such as cervical intraepithelial neoplasia, in both clinical and low-resource settings. On the other hand, machine learning methods have established themselves as a superior solution in image classification and regression tasks. We combine Mueller polarimetry and machine learning, critically assess the data/classification pipeline, investigate the bias arising from training strategies, and demonstrate how higher levels of detection accuracy can be achieved.AimWe aim to automate/assist with diagnostic segmentation of polarimetric images of uterine cervix specimens.ApproachA comprehensive capture-to-classification pipeline is developed in house. Specimens are acquired and measured with imaging Mueller polarimeter and undergo histopathological classification. Subsequently, a labeled dataset is created within tagged regions of either healthy or neoplastic cervical tissues. Several machine learning methods are trained utilizing different training-test-set-split strategies, and their corresponding accuracies are compared.ResultsOur results include robust measurements of model performance with two approaches: a 90:10 training–test-set-split and leave-one-out cross-validation. By comparing the classifier’s accuracy directly with the ground truth obtained during histology analysis, we demonstrate how conventionally used shuffled split leads to an over-estimate of true classifier performance ( 0.964 ± 0.00 ) . The leave-one-out cross-validation, however, leads to more accurate performance ( 0.812 ± 0.21 ) with respect to newly obtained samples that were not used to train the models.ConclusionsCombination of Mueller polarimetry and machine learning is a powerful tool for the task of screening for pre-cancerous conditions in cervical tissue sections. Nevertheless, there is a inherent bias with conventional processes that can be addressed using more conservative classifier training approaches. This results in overall improvements of the sensitivity and specificity of the developed techniques for “unseen” images.

show abstract