Hematoxylin and Eosin (H&E) color variation among histological images from different laboratories can significantly degrade the performance of Computer-Aided Diagnosis systems. The staining procedure is the primary factor responsible for color variation, and consequently, the methods designed to reduce such variations are designed in concordance with this procedure. In particular, Blind Color Deconvolution (BCD) methods aim to identify the true underlying colors in the image and to separate the tissue structure from the color information. Unfortunately, BCD methods often assume that images are stained solely with pure staining colors (e.g., blue and pink for H&E). This assumption does not hold true when common artifacts such as blood are present, requiring an additional color component to represent them. This is a challenge for color standardization algorithms, which are unable to correctly identify the stains in the image, leading to unexpected results. In this work, we propose a Blood-Robust Bayesian K-Singular Value Decomposition model designed to simultaneously detect blood and extract color from histological images while preserving structural details. We evaluate our method using both synthetic and real images, which contain varying amounts of blood pixels.

Large amounts of digitized histopathological data display a promising future for developing pathological foundation models via self-supervised learning methods. Foundation models pretrained with these methods serve as a good basis for downstream tasks. However, the gap between natural and histopathological images hinders the direct application of existing methods. In this work, we present PathoDuet, a series of pretrained models on histopathological images, and a new self-supervised learning framework in histopathology. The framework is featured by a newly-introduced pretext token and later task raisers to explicitly utilize certain relations between images, like multiple magnifications and multiple stains. Based on this, two pretext tasks, cross-scale positioning and cross-stain transferring, are designed to pretrain the model on Hematoxylin and Eosin (H&E) images and transfer the model to immunohistochemistry (IHC) images, respectively. To validate the efficacy of our models, we evaluate the performance over a wide variety of downstream tasks, including patch-level colorectal cancer subtyping and whole slide image (WSI)-level classification in H&E field, together with expression level prediction of IHC marker, tumor identification and slide-level qualitative analysis in IHC field. The experimental results show the superiority of our models over most tasks and the efficacy of proposed pretext tasks. The codes and models are available at https://github.com/openmedlab/PathoDuet.

Hematoxylin and eosin (H&E) staining is a crucial technique for diagnosing glioma, allowing direct observation of tissue structures. However, the H&E staining workflow necessitates intricate processing, specialized laboratory infrastructures, and specialist pathologists, rendering it expensive, labor-intensive, and time-consuming. In view of these considerations, we combine the deep learning method and hyperspectral imaging technique, aiming at accurately and rapidly converting the hyperspectral images into virtual H&E staining images. The method overcomes the limitations of H&E staining by capturing tissue information at different wavelengths, providing comprehensive and detailed tissue composition information as the realistic H&E staining. In comparison with various generator structures, the Unet exhibits substantial overall advantages, as evidenced by a mean structure similarity index measure (SSIM) of 0.7731 and a peak signal-to-noise ratio (PSNR) of 23.3120, as well as the shortest training and inference time. A comprehensive software system for virtual H&E staining, which integrates CCD control, microscope control, and virtual H&E staining technology, is developed to facilitate fast intraoperative imaging, promote disease diagnosis, and accelerate the development of medical automation. The platform reconstructs large-scale virtual H&E staining images of gliomas at a high speed of 3.81 mm2/s. This innovative approach will pave the way for a novel, expedited route in histological staining.

The adsorption efficiency of cheap, ecofriendly, and easily available agro-waste, Trapa natans (Chestnut) and Citrullus lanatus (Watermelon) peels, has been investigated in their native forms (TNAT and CLAN) as well as citric acid impregnated forms (C-TNAT and C-CLAN), respectively, for the detoxification of toxic, deleterious, and carcinogenic Eosin yellow dye (EYD) from wastewater streams. Different operational parameters were optimized for the investigation of isothermal, kinetic and the thermodynamic models. R2 for sportive decontamination of Eosin by citric acid treated adsorbents were close to one, supporting the applicability of Langmuir, Temkin, and pseudo-second-order in this investigation. Maximum sorption capabilities were 222 and 667 mg/g for chemically treated bio-waste C-TNAT and C-CLAN, respectively, reflecting their efficient and promising performance, while Gibbs free energy revealed exothermic and spontaneous adsorption behavior. The kinetic statics for qe (cal) are quite close to qe (exp), indicating the viability and fitness of pseudo-second-order mechanisms. The present study suggests that both citric acid fabricated bio-waste C-TNAT and C-CLAN can be substantially employed to decontaminate persistent organic pollutants, like: Eosin yellow dye from wastewater using green approach to resolve socio-economic problems of developing countries.

Proximity labeling proteomics (PLP) strategies are powerful approaches to yield snapshots of protein neighborhoods. Here, we describe a multiscale PLP method with adjustable resolution that uses a commercially available photocatalyst, Eosin Y, which upon visible light illumination activates different photo-probes with a range of labeling radii. We applied this platform to profile neighborhoods of the oncogenic epidermal growth factor receptor and orthogonally validated more than 20 neighbors using immunoassays and AlphaFold-Multimer prediction. We further profiled the protein neighborhoods of cell-cell synapses induced by bispecific T cell engagers and chimeric antigen receptor T cells. This integrated multiscale PLP platform maps local and distal protein networks on and between cell surfaces, which will aid in the systematic construction of the cell surface interactome, revealing horizontal signaling partners and reveal new immunotherapeutic opportunities.

OBJECTIVE: To compare the staining quality between rapid hematoxylin and eosin (H&E) staining and routine H&E staining of frozen breast tissue sections.
METHODS: In this cross-sectional observational study, 120 frozen breast tissue sections were randomly assigned to rapid or routine H&E staining (n = 60 per group). Rapid H&E staining used a 7:1 mixture of modified Gill\'s hematoxylin and alcohol-soluble 1% eosin Y. The staining quality of each section was evaluated and scored. A score of >7 was considered excellent, a score of 6 to 7 good, and a score of ≤5 poor.
RESULTS: The staining time for rapid staining was approximately 3 minutes, whereas that of routine staining was approximately 12 minutes. There were no significant differences in the staining quality scores or proportions of sections in each grade between the two staining methods. The proportions of sections that were classified as excellent or good were 96.7% and 98.3% for rapid and routine staining, respectively.
CONCLUSIONS: In frozen breast tissue sections, rapid H&E staining may provide staining quality that is comparable to that of routine staining, while markedly reducing the staining time.

Mueller matrix microscopy can provide comprehensive polarization-related optical and structural information of biomedical samples label-freely. Thus, it is regarded as an emerging powerful tool for pathological diagnosis. However, the staining dyes have different optical properties and staining mechanisms, which can put influence on Mueller matrix microscopic measurement. In this Letter, we quantitatively analyze the polarization enhancement mechanism from hematoxylin and eosin (H&E) staining in multispectral Mueller matrix microscopy. We examine the influence of hematoxylin and eosin dyes on Mueller matrix-derived polarization characteristics of fibrous tissue structures. Combined with Monte Carlo simulations, we explain how the dyes enhance diattenuation and linear retardance as the illumination wavelength changed. In addition, it is demonstrated that by choosing an appropriate incident wavelength, more visual Mueller matrix polarimetric information can be observed of the H&E stained tissue sample. The findings can lay the foundation for the future Mueller matrix-assisted digital pathology.

Accurate assessment of epidermal growth factor receptor (EGFR) mutation status and subtype is critical for the treatment of non-small cell lung cancer patients. Conventional molecular testing methods for detecting EGFR mutations have limitations. In this study, an artificial intelligence-powered deep learning framework was developed for the weakly supervised prediction of EGFR mutations in non-small cell lung cancer from hematoxylin and eosin-stained histopathology whole-slide images. The study cohort was partitioned into training and validation subsets. Foreground regions containing tumor tissue were extracted from whole-slide images. A convolutional neural network employing a contrastive learning paradigm was implemented to extract patch-level morphologic features. These features were aggregated using a vision transformer-based model to predict EGFR mutation status and classify patient cases. The established prediction model was validated on unseen data sets. In internal validation with a cohort from the University of Science and Technology of China (n = 172), the model achieved patient-level areas under the receiver-operating characteristic curve (AUCs) of 0.927 and 0.907, sensitivities of 81.6% and 83.3%, and specificities of 93.0% and 92.3%, for surgical resection and biopsy specimens, respectively, in EGFR mutation subtype prediction. External validation with cohorts from the Second Affiliated Hospital of Anhui Medical University and the First Affiliated Hospital of Wannan Medical College (n = 193) yielded patient-level AUCs of 0.849 and 0.867, sensitivities of 79.2% and 80.7%, and specificities of 91.7% and 90.7% for surgical and biopsy specimens, respectively. Further validation with The Cancer Genome Atlas data set (n = 81) showed an AUC of 0.861, a sensitivity of 84.6%, and a specificity of 90.5%. Deep learning solutions demonstrate potential advantages for automated, noninvasive, fast, cost-effective, and accurate inference of EGFR alterations from histomorphology. Integration of such artificial intelligence frameworks into routine digital pathology workflows could augment existing molecular testing pipelines.

暂无摘要。

Alveolar, the smallest structural and functional units within the respiratory system, play a crucial role in maintaining lung function. Alveolar damage is a typical pathological hallmark of respiratory diseases. Nevertheless, there is currently no simple, rapid, economical, and unbiased method for quantifying alveolar size for entire lung tissue. Here, firstly, we conducted lung sample slicing based on the size, shape, and distribution of airway branches of different lobes. Next, we performed HE staining on different slices. Then, we provided an unbiased quantification of alveolar size using free software ImageJ. Through this protocol, we demonstrated that C57Bl/6 mice exhibit varying alveolar sizes among different lobes. Collectively, we provided a simple and unbiased method for a more comprehensive quantification of alveolar size in mice, which holds promise for a broader range of respiratory research using mouse models.