Computational image translation from Mueller matrix polarimetry to bright‐field microscopy

Si, Lu; Li, Naiqi; Huang, Tongyu; Du, Shan; Dong, Yonggui; Ya, Yao; Ma, Hui

doi:10.1002/jbio.202100242

Cited by 6 publications

(2 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It was shown that machine learning approach (ML) can enhance the contrast in polarimetric images of tissue at micro-scale [72,73] and also help the diagnostic interpretation of the wide-field polarimetric images of brain tissue [74].…”

Section: Brain Fiber Tracking For Assisting Neurosurgerymentioning

confidence: 99%

Polarimetric techniques for the structural studies and diagnosis of brain

Rodríguez-Núñez

Novikova

2022

Advanced Optical Technologies

View full text Add to dashboard Cite

The polarimetric techniques are used in various biomedical applications for a non-contact and fast diagnosis of tissue that is known as optical biopsy approach. These optical modalities provide relevant information on micro-architecture of biological tissue and its alterations induced by different diseases, thus, helping in staging and precise delineation of the pathology zones. In this review, we summarize the work of different research groups on using polarized light for brain tissue studies. This includes the investigations of polarimetric properties of brain tissue (both scattering and optical anisotropy) for brain connectome reconstruction, the visualization of in-plane brain fiber tracts for brain tumor contrast enhancement during neurosurgery, and the histopathology analysis for disease staging in Alzheimer’s subjects. We discuss also further perspectives for the pre-clinical studies of brain with polarized light.

show abstract

Section: Brain Fiber Tracking For Assisting Neurosurgerymentioning

confidence: 99%

Polarimetric techniques for the structural studies and diagnosis of brain

Rodríguez-Núñez

Novikova

2022

Advanced Optical Technologies

View full text Add to dashboard Cite

show abstract

“…They have different imaging principles, and each has its advantages. In previous studies, we proposed a cross-modality transformation from MM microscopy images to bright-field microscopy images 23 based on a conditional generative adversarial network (cGAN) 24 without changing the optical path design. However, to obtain a MM image, four exposures of the dual division of the focal plane (DoFP) polarimeter-based system 25 are required, which will be affected by light intensity fluctuations and co-registration of polarimetric images for imaging quality 26 .…”

Section: Introductionmentioning

confidence: 99%

Deep-learning-based cross-modality translation from Stokes image to bright-field contrast

Wei,

Si,

Huang

et al. 2023

J. Biomed. Opt.

Self Cite

View full text Add to dashboard Cite

.SignificanceMueller matrix (MM) microscopy has proven to be a powerful tool for probing microstructural characteristics of biological samples down to subwavelength scale. However, in clinical practice, doctors usually rely on bright-field microscopy images of stained tissue slides to identify characteristic features of specific diseases and make accurate diagnosis. Cross-modality translation based on polarization imaging helps to improve the efficiency and stability in analyzing sample properties from different modalities for pathologists.AimIn this work, we propose a computational image translation technique based on deep learning to enable bright-field microscopy contrast using snapshot Stokes images of stained pathological tissue slides. Taking Stokes images as input instead of MM images allows the translated bright-field images to be unaffected by variations of light source and samples.ApproachWe adopted CycleGAN as the translation model to avoid requirements on co-registered image pairs in the training. This method can generate images that are equivalent to the bright-field images with different staining styles on the same region.ResultsPathological slices of liver and breast tissues with hematoxylin and eosin staining and lung tissues with two types of immunohistochemistry staining, i.e., thyroid transcription factor-1 and Ki-67, were used to demonstrate the effectiveness of our method. The output results were evaluated by four image quality assessment methods.ConclusionsBy comparing the cross-modality translation performance with MM images, we found that the Stokes images, with the advantages of faster acquisition and independence from light intensity and image registration, can be well translated to bright-field images.

show abstract