Generating bright-field images of stained tissue slices from Mueller matrix polarimetric images with CycleGAN using unpaired dataset
Recently, Mueller matrix (MM) polarimetric imaging-assisted pathology detection methods are showing great potential in clinical diagnosis. However, since our human eyes cannot observe polarized light directly, it raises a notable challenge for interpreting the measurement results by pathologists who...
| Main Authors: | , , , , , |
|---|---|
| Format: | Journal article |
| Language: | English |
| Published: |
World Scientific Publishing
2024
|
| _version_ | 1811139675791818752 |
|---|---|
| author | Fan, J Zeng, N He, H He, C Liu, S Ma, H |
| author_facet | Fan, J Zeng, N He, H He, C Liu, S Ma, H |
| author_sort | Fan, J |
| collection | OXFORD |
| description | Recently, Mueller matrix (MM) polarimetric imaging-assisted pathology detection methods are showing great potential in clinical diagnosis. However, since our human eyes cannot observe polarized light directly, it raises a notable challenge for interpreting the measurement results by pathologists who have limited familiarity with polarization images. One feasible approach is to combine MM polarimetric imaging with virtual staining techniques to generate standardized stained images, inheriting the advantages of information-abundant MM polarimetric imaging. In this study, we develop a model using unpaired MM polarimetric images and bright-¯eld images for generating standard hematoxylin and eosin (H&E) stained tissue images. Compared with the existing polarization virtual staining techniques primarily based on the model training with paired images, the proposed Cycle-Consistent Generative Adversarial Networks (CycleGAN)based model simpli¯es data acquisition and data preprocessing to a great extent. The outcomes demonstrate the feasibility of training CycleGAN with unpaired polarization images and their corresponding bright-¯eld images as a viable approach, which provides an intuitive manner for pathologists for future polarization-assisted digital pathology. |
| first_indexed | 2024-09-25T04:09:52Z |
| format | Journal article |
| id | oxford-uuid:0680383b-29ff-43ca-9b17-3ccd6929d1c3 |
| institution | University of Oxford |
| language | English |
| last_indexed | 2024-09-25T04:09:52Z |
| publishDate | 2024 |
| publisher | World Scientific Publishing |
| record_format | dspace |
| spelling | oxford-uuid:0680383b-29ff-43ca-9b17-3ccd6929d1c32024-06-17T15:54:34ZGenerating bright-field images of stained tissue slices from Mueller matrix polarimetric images with CycleGAN using unpaired datasetJournal articlehttp://purl.org/coar/resource_type/c_dcae04bcuuid:0680383b-29ff-43ca-9b17-3ccd6929d1c3EnglishSymplectic ElementsWorld Scientific Publishing2024Fan, JZeng, NHe, HHe, CLiu, SMa, HRecently, Mueller matrix (MM) polarimetric imaging-assisted pathology detection methods are showing great potential in clinical diagnosis. However, since our human eyes cannot observe polarized light directly, it raises a notable challenge for interpreting the measurement results by pathologists who have limited familiarity with polarization images. One feasible approach is to combine MM polarimetric imaging with virtual staining techniques to generate standardized stained images, inheriting the advantages of information-abundant MM polarimetric imaging. In this study, we develop a model using unpaired MM polarimetric images and bright-¯eld images for generating standard hematoxylin and eosin (H&E) stained tissue images. Compared with the existing polarization virtual staining techniques primarily based on the model training with paired images, the proposed Cycle-Consistent Generative Adversarial Networks (CycleGAN)based model simpli¯es data acquisition and data preprocessing to a great extent. The outcomes demonstrate the feasibility of training CycleGAN with unpaired polarization images and their corresponding bright-¯eld images as a viable approach, which provides an intuitive manner for pathologists for future polarization-assisted digital pathology. |
| spellingShingle | Fan, J Zeng, N He, H He, C Liu, S Ma, H Generating bright-field images of stained tissue slices from Mueller matrix polarimetric images with CycleGAN using unpaired dataset |
| title | Generating bright-field images of stained tissue slices from Mueller matrix polarimetric images with CycleGAN using unpaired dataset |
| title_full | Generating bright-field images of stained tissue slices from Mueller matrix polarimetric images with CycleGAN using unpaired dataset |
| title_fullStr | Generating bright-field images of stained tissue slices from Mueller matrix polarimetric images with CycleGAN using unpaired dataset |
| title_full_unstemmed | Generating bright-field images of stained tissue slices from Mueller matrix polarimetric images with CycleGAN using unpaired dataset |
| title_short | Generating bright-field images of stained tissue slices from Mueller matrix polarimetric images with CycleGAN using unpaired dataset |
| title_sort | generating bright field images of stained tissue slices from mueller matrix polarimetric images with cyclegan using unpaired dataset |
| work_keys_str_mv | AT fanj generatingbrightfieldimagesofstainedtissueslicesfrommuellermatrixpolarimetricimageswithcycleganusingunpaireddataset AT zengn generatingbrightfieldimagesofstainedtissueslicesfrommuellermatrixpolarimetricimageswithcycleganusingunpaireddataset AT heh generatingbrightfieldimagesofstainedtissueslicesfrommuellermatrixpolarimetricimageswithcycleganusingunpaireddataset AT hec generatingbrightfieldimagesofstainedtissueslicesfrommuellermatrixpolarimetricimageswithcycleganusingunpaireddataset AT lius generatingbrightfieldimagesofstainedtissueslicesfrommuellermatrixpolarimetricimageswithcycleganusingunpaireddataset AT mah generatingbrightfieldimagesofstainedtissueslicesfrommuellermatrixpolarimetricimageswithcycleganusingunpaireddataset |