Unstained Tissue Imaging and Virtual Hematoxylin and Eosin Staining of Histologic Whole Slide Images

Koivukoski, Sonja; Khan, Umair; Ruusuvuori, Pekka; Latonen, Leena

doi:10.1016/j.labinv.2023.100070

Cited by 12 publications

(8 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Hence, we wanted to develop approaches using standard brightfield imaging for which the same microscopes and slide scanners could potentially be used as with chemically stained H&E slides. 28 Virtual staining methods working on the standard platform images have vast potential to streamline histopathological workflow without requiring additional equipment or other investments. Prior studies 24 , 26 , 28 , 40 using brightfield images for virtual H&E staining reported histology mainly at the macroscopic level.…”

Section: Discussionmentioning

confidence: 99%

“… 28 Virtual staining methods working on the standard platform images have vast potential to streamline histopathological workflow without requiring additional equipment or other investments. Prior studies 24 , 26 , 28 , 40 using brightfield images for virtual H&E staining reported histology mainly at the macroscopic level. We used imaging with 40× magnification producing high-level reproduction of histology at a microscopic level.…”

Section: Discussionmentioning

confidence: 99%

“…In a recent study, we used CycleGAN, 17 an unsupervised learning approach, to determine the optimal unstained tissue processing and imaging protocols and showed proof of principle that deparaffinized and, in some cases, still-in-paraffin tissue sections could be used to achieve meaningful histology with virtual H&E staining. 28 …”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

The effect of neural network architecture on virtual H&E staining: Systematic assessment of histological feasibility

Khan¹,

Koivukoski²,

Valkonen³

et al. 2023

Patterns

Self Cite

View full text Add to dashboard Cite

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

The effect of neural network architecture on virtual H&E staining: Systematic assessment of histological feasibility

Khan¹,

Koivukoski²,

Valkonen³

et al. 2023

Patterns

Self Cite

View full text Add to dashboard Cite

“…Prominent are CycleGANs (Cycle-Consistent Generative Adversarial Networks) and diffusion models. [21][22][23][24][25][26][27][28] CycleGANs are generative deep learning models that allow for cross modality translation. They have been used for the transformation of H&Estained slides into synthetic IHC-stained slides that mark specific proteins in tissues.…”

Section: Introductionmentioning

confidence: 99%

“…21,27,30 Despite advances in generative models, limitations persist in achieving synthetic biological images that look realistic, as assessed by rigorous metrics. [21][22][23][24][25][26][27][28][31][32][33] Issues such as the accurate representation of subtle or rare textures, cell arrangements, and tissue boundaries are areas of active research. 22,26 Here, we explore interpolation techniques, such as frame interpolation for large motion (FILM), to enhance the resolution of 3D biological images.…”

Section: Introductionmentioning

confidence: 99%

Generative interpolation and restoration of images using deep learning for improved 3D tissue mapping

Joshi,

Forjaz,

Sang Han

et al. 2024

Preprint

View full text Add to dashboard Cite

The development of novel imaging platforms has improved our ability to collect and analyze large three-dimensional (3D) biological imaging datasets. Advances in computing have led to an ability to extract complex spatial information from these data, such as the composition, morphology, and interactions of multi-cellular structures, rare events, and integration of multi-modal features combining anatomical, molecular, and transcriptomic (among other) information. Yet, the accuracy of these quantitative results is intrinsically limited by the quality of the input images, which can contain missing or damaged regions, or can be of poor resolution due to mechanical, temporal, or financial constraints. In applications ranging from intact imaging (e.g. light-sheet microscopy and magnetic resonance imaging) to sectioning based platforms (e.g. serial histology and serial cryo-electron microscopy), the quality and resolution of imaging data has become paramount. Here, we address these challenges by leveraging frame interpolation for large image motion (FILM), a generative AI model originally developed for temporal interpolation, for spatial interpolation of a range of 3D image types. Comparative analysis demonstrates the superiority of FILM over traditional linear interpolation to produce functional synthetic images, due to its ability to better preserve biological information including microanatomical features and cell counts, as well as image quality, such as contrast, variance, and luminance. FILM repairs tissue damages in images and reduces stitching artifacts. We show that FILM can decrease imaging time by synthesizing skipped images. We demonstrate the versatility of our method with a wide range of imaging modalities (histology, tissue-clearing/light-sheet microscopy, magnetic resonance imaging, cryo-electron microscopy), species (human, mouse), healthy and diseased tissues (pancreas, lung, brain), staining techniques (IHC, H&E), and pixel resolutions (8 nm, 2 μm, 1mm). Overall, we demonstrate the marked potential of generative AI in improving the resolution, throughput, and quality of biological image datasets, enabling improved 3D imaging.

show abstract

Boosting FFPE-to-HE Virtual Staining with Cell Semantics from Pretrained Segmentation Model

Hu,

Peng,

et al. 2024

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Unstained Tissue Imaging and Virtual Hematoxylin and Eosin Staining of Histologic Whole Slide Images

Cited by 12 publications

References 39 publications

The effect of neural network architecture on virtual H&E staining: Systematic assessment of histological feasibility

The effect of neural network architecture on virtual H&E staining: Systematic assessment of histological feasibility

Generative interpolation and restoration of images using deep learning for improved 3D tissue mapping

Boosting FFPE-to-HE Virtual Staining with Cell Semantics from Pretrained Segmentation Model

Contact Info

Product

Resources

About