Mode-mapping qOBM microscopy to virtual hematoxylin and eosin (H&amp;E) histology via deep learning

Abraham, Tanishq; Costa, Paloma Casteleiro; Filan, Caroline; Robles, Francisco E.; Levenson, Richard M.

doi:10.1117/12.2622160

Cited by 3 publications

(4 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The automated selection of targets for high-resolution analysis in fixed samples enormously reduces storage efforts and makes the observation of rare phenotypes with increased statistical sampling possible [40]. For example, when coupled to artificial intelligence, the approach can have a big impact in the contribution of microscopy to pathology [41][42][43][44]. In basic biomedical research, the presented methodologies are now gaining an increasing space with event-driven acquisitions [40,[45][46][47].…”

Section: Discussionmentioning

confidence: 99%

From Cell Populations to Molecular Complexes: Multiplexed Multimodal Microscopy to Explore p53-53BP1 Molecular Interaction

Pelicci,

Furia,

Pelicci

et al. 2024

IJMS

View full text Add to dashboard Cite

Surpassing the diffraction barrier revolutionized modern fluorescence microscopy. However, intrinsic limitations in statistical sampling, the number of simultaneously analyzable channels, hardware requirements, and sample preparation procedures still represent an obstacle to its widespread diffusion in applicative biomedical research. Here, we present a novel pipeline based on automated multimodal microscopy and super-resolution techniques employing easily available materials and instruments and completed with open-source image-analysis software developed in our laboratory. The results show the potential impact of single-molecule localization microscopy (SMLM) on the study of biomolecules’ interactions and the localization of macromolecular complexes. As a demonstrative application, we explored the basis of p53-53BP1 interactions, showing the formation of a putative macromolecular complex between the two proteins and the basal transcription machinery in situ, thus providing visual proof of the direct role of 53BP1 in sustaining p53 transactivation function. Moreover, high-content SMLM provided evidence of the presence of a 53BP1 complex on the cell cytoskeleton and in the mitochondrial space, thus suggesting the existence of novel alternative 53BP1 functions to support p53 activity.

show abstract

Section: Discussionmentioning

confidence: 99%

From Cell Populations to Molecular Complexes: Multiplexed Multimodal Microscopy to Explore p53-53BP1 Molecular Interaction

Pelicci,

Furia,

Pelicci

et al. 2024

IJMS

View full text Add to dashboard Cite

show abstract

“…In another work, Nygate et al demonstrated the virtual staining of human sperm cells using QPI, allowing fertility evaluation in real-time 32 . QPI using oblique 33 .…”

Section: Label-free Virtual Stainingmentioning

confidence: 99%

“…One notable issue of using CycleGANs to perform virtual staining tasks is the intensity mismatch; for example, labelfree input images usually have dark background as opposed to the bright-field histologically stained images with white background, which can cause a challenge for image transformations due to the lack of pixel-level supervision. To overcome this problem, in addition to inverting the intensities of label-free input images 33,60 , other loss terms such as saliency constraint loss 26 , and multiscale structural similarity index measure (MS-SSIM) loss 42 were adopted. Although the performance of unsupervised learning is in general inferior to supervised learning 31,35,37,51,60 , it still provides a valuable solution in the cases where paired image datasets are not accessible/ available for training.…”

Section: Network Architecture and Training Strategiesmentioning

confidence: 99%

Deep learning-enabled virtual histological staining of biological samples

Bai

Yang

et al. 2023

Light Sci Appl

View full text Add to dashboard Cite

Histological staining is the gold standard for tissue examination in clinical pathology and life-science research, which visualizes the tissue and cellular structures using chromatic dyes or fluorescence labels to aid the microscopic assessment of tissue. However, the current histological staining workflow requires tedious sample preparation steps, specialized laboratory infrastructure, and trained histotechnologists, making it expensive, time-consuming, and not accessible in resource-limited settings. Deep learning techniques created new opportunities to revolutionize staining methods by digitally generating histological stains using trained neural networks, providing rapid, cost-effective, and accurate alternatives to standard chemical staining methods. These techniques, broadly referred to as virtual staining, were extensively explored by multiple research groups and demonstrated to be successful in generating various types of histological stains from label-free microscopic images of unstained samples; similar approaches were also used for transforming images of an already stained tissue sample into another type of stain, performing virtual stain-to-stain transformations. In this Review, we provide a comprehensive overview of the recent research advances in deep learning-enabled virtual histological staining techniques. The basic concepts and the typical workflow of virtual staining are introduced, followed by a discussion of representative works and their technical innovations. We also share our perspectives on the future of this emerging field, aiming to inspire readers from diverse scientific fields to further expand the scope of deep learning-enabled virtual histological staining techniques and their applications.

show abstract

“…This deep learning-based virtual staining technique has been extensively explored by multiple research groups and successfully applied to generate a range of histological stains, such as H&E 12,[19][20][21][22][23][24][25][26][27][28][29][30][31] , Masson's trichrome (MT) staining 12,20,22 and immunohistochemical (IHC) staining 32,33 . These previous works utilized images from various label-free microscopy modalities, including autofluorescence microscopy 12,22,[25][26][27]32 , quantitative phase imaging 20,34 , photoacoustic microscopy 29,31,35 and reflectance confocal microscopy 28 , among others 19,21,23,24,30,33,[36][37][38] . However, these earlier studies have primarily focused on standard biopsy samples, and there has been no virtual staining study on autopsy samples and other large specimens, which often demonstrate suboptimal staining quality with traditional histochemical approaches due to delayed fixation and autolysis.…”

mentioning

confidence: 99%

Virtual histological staining of unlabeled autopsy tissue

Li,

Pillar,

et al. 2024

Nat Commun

View full text Add to dashboard Cite

Traditional histochemical staining of post-mortem samples often confronts inferior staining quality due to autolysis caused by delayed fixation of cadaver tissue, and such chemical staining procedures covering large tissue areas demand substantial labor, cost and time. Here, we demonstrate virtual staining of autopsy tissue using a trained neural network to rapidly transform autofluorescence images of label-free autopsy tissue sections into brightfield equivalent images, matching hematoxylin and eosin (H&E) stained versions of the same samples. The trained model can effectively accentuate nuclear, cytoplasmic and extracellular features in new autopsy tissue samples that experienced severe autolysis, such as COVID-19 samples never seen before, where the traditional histochemical staining fails to provide consistent staining quality. This virtual autopsy staining technique provides a rapid and resource-efficient solution to generate artifact-free H&E stains despite severe autolysis and cell death, also reducing labor, cost and infrastructure requirements associated with the standard histochemical staining.

show abstract

Mode-mapping qOBM microscopy to virtual hematoxylin and eosin (H&E) histology via deep learning

Cited by 3 publications

References 0 publications

From Cell Populations to Molecular Complexes: Multiplexed Multimodal Microscopy to Explore p53-53BP1 Molecular Interaction

From Cell Populations to Molecular Complexes: Multiplexed Multimodal Microscopy to Explore p53-53BP1 Molecular Interaction

Deep learning-enabled virtual histological staining of biological samples

Virtual histological staining of unlabeled autopsy tissue

Contact Info

Product

Resources

About