Mueller matrix describes the polarization properties of the samples comprehensively, characterizing microstructural information at subcellular-level. Mueller matrix microscopy is a promising non-invasive tool for pathological diagnosis, but it can be challenging to extract polarization parameters that correlate with pathological variation. In this study, we propose a polarization super-pixel based polarization feature extraction framework. Polarization super-pixels are able to represent the polarization features of the biological sample in a simple, compact, and comprehensive way, while reducing the data volume drastically. Using various pathological samples including breast cancer, liver cancer, and lung cancer, we show that polarization super-pixel approach greatly increases the efficiency and performance of the downstream supervised and unsupervised learning tasks, for cancerous tissue identification and microstructural composition analysis. We also propose the super-pixel based label spreading method, which iteratively propagates pathologist’s initial manual label of cancerous region to the entire field of view, highlighting the tissues with the same microstructural features.
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.
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.