Deep learning-based transformation of H&E stained tissues into special stains

A deep learning model to predict Ki-67 positivity in oral squamous cell carcinoma

Anatomical pathology is undergoing its third revolution, transitioning from analogical to digital pathology and incorporating new artificial intelligence technologies into clinical practice. Aside from classification, detection, and segmentation models, predictive models are gaining traction since they can impact diagnostic processes and laboratory activity, lowering consumable usage and turnaround time. Our research aimed to create a deep-learning model to generate synthetic Ki-67 immunohistochemistry from Haematoxylin and Eosin (H&E) stained images. We used 175 oral squamous cell carcinoma (OSCC) from the University Federico II's Pathology Unit's archives to train our model to generate 4 Tissue Micro Arrays (TMAs). We sectioned one slide from each TMA, first stained with H&E and then re-stained with anti-Ki-67 immunohistochemistry (IHC). In digitised slides, cores were disarrayed, and the matching cores of the 2 stained were aligned to construct a dataset to train a Pix2Pix algorithm to convert H&E images to IHC. Pathologists could recognise the synthetic images in only half of the cases in a specially designed likelihood test. Hence, our model produced realistic synthetic images. We next used QuPath to quantify IHC positivity, achieving remarkable levels of agreement between genuine and synthetic IHC. Furthermore, a categorical analysis employing 3 Ki-67 positivity cut-offs (5%, 10%, and 15%) revealed high positive-predictive values. Our model is a promising tool for collecting Ki-67 positivity information directly on H&E slides, reducing laboratory demand and improving patient management. It is also a valuable option for smaller laboratories to easily and quickly screen bioptic samples and prioritise them in a digital pathology workflow.

The ACROBAT 2022 challenge: Automatic registration of breast cancer tissue

The alignment of tissue between histopathological whole-slide-images (WSI) is crucial for research and clinical applications. Advances in computing, deep learning, and availability of large WSI datasets have revolutionised WSI analysis. Therefore, the current state-of-the-art in WSI registration is unclear. To address this, we conducted the ACROBAT challenge, based on the largest WSI registration dataset to date, including 4,212 WSIs from 1,152 breast cancer patients. The challenge objective was to align WSIs of tissue that was stained with routine diagnostic immunohistochemistry to its H&E-stained counterpart. We compare the performance of eight WSI registration algorithms, including an investigation of the impact of different WSI properties and clinical covariates. We find that conceptually distinct WSI registration methods can lead to highly accurate registration performances and identify covariates that impact performances across methods. These results provide a comparison of the performance of current WSI registration methods and guide researchers in selecting and developing methods.

Kidney medicine meets computer vision: a bibliometric analysis

BACKGROUND AND OBJECTIVE

Rapid advances in computer vision (CV) have the potential to facilitate the examination, diagnosis, and treatment of diseases of the kidney. The bibliometric study aims to explore the research landscape and evolving research focus of the application of CV in kidney medicine research.

METHODS

The Web of Science Core Collection was utilized to identify publications related to the research or applications of CV technology in the field of kidney medicine from January 1, 1900, to December 31, 2022. We analyzed emerging research trends, highly influential publications and journals, prolific researchers, countries/regions, research institutions, co-authorship networks, and co-occurrence networks. Bibliographic information was analyzed and visualized using Python, Matplotlib, Seaborn, HistCite, and Vosviewer.

RESULTS

There was an increasing trend in the number of publications on CV-based kidney medicine research. These publications mainly focused on medical image processing, surgical procedures, medical image analysis/diagnosis, as well as the application and innovation of CV technology in medical imaging. The United States is currently the leading country in terms of the quantities of published articles and international collaborations, followed by China. Deep learning-based segmentation and machine learning-based texture analysis are the most commonly used techniques in this field. Regarding research hotspot trends, CV algorithms are shifting toward artificial intelligence, and research objects are expanding to encompass a wider range of kidney-related objects, with data dimensions used in research transitioning from 2D to 3D while simultaneously incorporating more diverse data modalities.

CONCLUSION

The present study provides a scientometric overview of the current progress in the research and application of CV technology in kidney medicine research. Through the use of bibliometric analysis and network visualization, we elucidate emerging trends, key sources, leading institutions, and popular topics. Our findings and analysis are expected to provide valuable insights for future research on the use of CV in kidney medicine research.

The digital revolution in veterinary pathology

For the past two centuries, the use of traditional light microscopy to examine tissues to make diagnoses has remained relatively unchanged. While the fundamental concept of tissue slide analysis has stayed the same, our interaction with the microscope is undergoing significant changes. Digital pathology (DP) has gained momentum in veterinary science and is on the verge of becoming a vital tool in diagnostics, research and education. Many diagnostic laboratories have incorporated DP as a critical part of their workflows. Innovations in DP and whole slide image technology have made telediagnosis (the process of transmitting digital clinical data using telecommunication networks for distant diagnosis) more accessible, leading to improved patient care through streamlining of workflows and greater accessibility of second opinions. The integration of machine learning and artificial intelligence and human-in-the-loop protocols for DP workflows will further the development of computer-aided diagnosis and prognostic tools. Despite its present weaknesses, DP will progressively aid veterinary clinicians and pathologists in delivering more accurate and reliable diagnoses. Consistent incorporation of DP frontline advancements into routine veterinary diagnostic pipelines will assist in improving current tools and help prepare pathologists for the progression of digitalization in the field.

Assessment of AI-based computational H&E staining versus chemical H&E staining for primary diagnosis in lymphomas: a brief interim report

Microscopic review of tissue sections is of foundational importance in pathology, yet the traditional chemistry-based histology laboratory methods are labour intensive, tissue destructive, poorly scalable to the evolving needs of precision medicine and cause delays in patient diagnosis and treatment. Recent AI-based techniques offer promise in upending histology workflow; one such method developed by PictorLabs can generate near-instantaneous diagnostic images via a machine learning algorithm. Here, we demonstrate the utility of virtual staining in a blinded, wash-out controlled study of 16 cases of lymph node excisional biopsies, including a spectrum of diagnoses from reactive to lymphoma and compare the diagnostic performance of virtual and chemical H&Es across a range of stain quality, image quality, morphometric assessment and diagnostic interpretation parameters as well as proposed follow-up immunostains. Our results show non-inferior performance of virtual H&E stains across all parameters, including an improved stain quality pass rate (92% vs 79% for virtual vs chemical stains, respectively) and an equivalent rate of binary diagnostic concordance (90% vs 92%). More detailed adjudicated reviews of differential diagnoses and proposed IHC panels showed no major discordances. Virtual H&Es appear fit for purpose and non-inferior to chemical H&Es in diagnostic assessment of clinical lymph node samples, in a limited pilot study.

Virtual multi-staining in a single-section view for renal pathology using generative adversarial networks

Sections stained in periodic acid-Schiff (PAS), periodic acid-methenamine silver (PAM), hematoxylin and eosin (H&E), and Masson's trichrome (MT) stain with minimal morphological discordance are helpful for pathological diagnosis in renal biopsy. Here, we propose an artificial intelligence-based re-stainer called PPHM-GAN (PAS, PAM, H&E, and MT-generative adversarial networks) with multi-stain to multi-stain transformation capability. We trained three GAN models on 512 × 512-pixel patches from 26 training cases. The model with the best transformation quality was selected for each pair of stain transformations by human evaluation. Frechet inception distances, peak signal-to-noise ratio, structural similarity index measure, contrast structural similarity, and newly introduced domain shift inception score were calculated as auxiliary quality metrics. We validated the diagnostic utility using 5120 × 5120 patches of ten validation cases for major glomerular and interstitial abnormalities. Transformed stains were sometimes superior to original stains for the recognition of crescent formation, mesangial hypercellularity, glomerular sclerosis, interstitial lesions, or arteriosclerosis. 23 of 24 glomeruli (95.83 %) from 9 additional validation cases transformed to PAM, PAS, or MT facilitated recognition of crescent formation. Stain transformations to PAM (p = 4.0E-11) and transformations from H&E (p = 4.8E-9) most improved crescent formation recognition. PPHM-GAN maximizes information from a given section by providing several stains in a virtual single-section view, and may change the staining and diagnostic strategy.

Hyaluronic Acid-Modified Micelles of Azithromycin and Quercetin Against Infections Caused by Methicillin-Resistant Staphylococcus Aureus

Introduction

Resistance of intracellular pathogens is a challenge in microbial therapy. Methicillin-resistant Staphylococcus aureus (MRSA), which is able to persist inside the cells of infected tissues, is protected from attack by the immune system and many antimicrobial agents. To overcome these limitations, nano-delivery systems can be used for targeted therapy of intracellular MRSA.

Methods

Hyaluronic acid-modified azithromycin/quercetin micelles (HA-AZI/Qe-M) were synthesized by thin film hydration. The micelles were characterized by transmission electron microscopy (TEM), dynamic light scattering (DLS) and Fourier transform infrared spectroscopy (FTIR), and the drug loading (DL) and encapsulation efficiency (EE) were detected by high performance liquid chromatography (HPLC). The uptake ability of RAW264.7 cells was investigated, and its distribution in mice was evaluated by in vivo imaging. The inhibitory effect of the micelles against MRSA in vitro and its ability to eliminate intracellular bacteria were evaluated. Bacterial muscle-infected mice were constructed to evaluate the therapeutic effect of the micelles on bacterial infections in vivo and the biocompatibility of the micelles was investigated.

Results

HA-AZI/Qe-M had suitable physical and chemical properties and characterization. In vitro antibacterial experiments showed that HA-AZI/Qe-M could effectively inhibit the growth of MRSA, inhibit and eliminate the biofilm formed by MRSA, and have an excellent therapeutic effect on intracellular bacterial infection. The results of RAW264.7 cells uptake and in vivo imaging showed that HA-AZI/Qe-M could increase the cellular uptake, target the infection site, and prolong the treatment time. The results of in vivo antibacterial infection experiments showed that HA-AZI/Qe-M was able to ameliorate the extent of thigh muscle infections in mice and reduce the expression of inflammatory factors.

Conclusion

HA-AZI/Qe-M is a novel and effective nano-drug delivery system that can target intracellular bacterial infection, and it is expected to be safely used for the treatment of MRSA infection.

Stain transformation using Mueller matrix guided generative adversarial networks

Recently, virtual staining techniques have attracted more and more attention, which can help bypass the chemical staining process of traditional histopathological examination, saving time and resources. Meanwhile, as an emerging tool to characterize specific tissue structures in a label-free manner, the Mueller matrix microscopy can supplement more structural information that may not be apparent in bright-field images. In this Letter, we propose the Mueller matrix guided generative adversarial networks (MMG-GAN). By integrating polarization information provided by the Mueller matrix microscopy, the MMG-GAN enables the effective transformation of input H&E-stained images into corresponding Masson trichrome (MT)-stained images. The experimental results demonstrate the accuracy of the generated images by MMG-GAN and reveal the potential for more stain transformation tasks by incorporating the Mueller matrix polarization information, laying the foundation for future polarimetry-assisted digital pathology.

Virtual birefringence imaging and histological staining of amyloid deposits in label-free tissue using autofluorescence microscopy and deep learning

Systemic amyloidosis involves the deposition of misfolded proteins in organs/tissues, leading to progressive organ dysfunction and failure. Congo red is the gold-standard chemical stain for visualizing amyloid deposits in tissue, showing birefringence under polarization microscopy. However, Congo red staining is tedious and costly to perform, and prone to false diagnoses due to variations in amyloid amount, staining quality and manual examination of tissue under a polarization microscope. We report virtual birefringence imaging and virtual Congo red staining of label-free human tissue to show that a single neural network can transform autofluorescence images of label-free tissue into brightfield and polarized microscopy images, matching their histochemically stained versions. Blind testing with quantitative metrics and pathologist evaluations on cardiac tissue showed that our virtually stained polarization and brightfield images highlight amyloid patterns in a consistent manner, mitigating challenges due to variations in chemical staining quality and manual imaging processes in the clinical workflow.

Analysis of macrophage polarization and regulation characteristics in ovarian tissues of polycystic ovary syndrome

Background

Polycystic ovary syndrome (PCOS) can lead to infertility and increase the risk of endometrial cancer. Analyzing the macrophage polarization characteristics in ovarian tissues of PCOS is crucial for clinical treatment.

Methods

We obtained 13 PCOS and nine control ovarian samples from the CEO database and analyzed differentially expressed genes (DEGs). Macrophage polarization-related genes (MPRGs) were sourced from the GeneCards and MSigDB databases. Intersection of DEGs with MPRGs identified DEGs associated with macrophage polarization (MPRDEGs). Gene ontology (GO), Kyoto Encyclopedia of Genes and Genomes (KEGG), and Protein-protein interaction (PPI) Network analysis were conducted on MPRDEGs. Moreover, the top 10 genes from three algorithms were identified as the hub genes of MPRGs. In addition, miRNAs, transcription factors (TFs), and drugs were retrieved from relevant databases for regulatory network analysis of mRNA-miRNA, mRNA-TF, and mRNA-Drug interactions. Immune cell composition analysis between the PCOS and control groups was performed using the CIBERSORT algorithm to calculate correlations across 22 immune cell types.

Results

A total of 13 PCOS samples and nine control ovarian samples were obtained in this study. We identified 714 DEGs between the two groups, with 394 up-regulated and 320 down-regulated. Additionally, we identified 774 MPRGs, from which we derived 30 MPRDEGs by intersecting with DEGs, among which 21 exhibited interaction relationships. GO and KEGG analyses revealed the enrichment of MPRDEGs in five biological processes, five cell components, five molecular functions, and three biological pathways. Immune infiltration analysis indicated a strong positive correlation between activated nature killer (NK) cells and memory B cells, while neutrophils and monocytes showed the strongest negative correlation. Further investigation of MPRDEGs identified nine hub genes associated with 41 TFs, 82 miRNAs, and 44 drugs or molecular compounds. Additionally, qRT-PCR results demonstrated overexpression of the CD163, TREM1, and TREM2 genes in ovarian tissues from the PCOS group.

Conclusion

This study elucidated the polarization status and regulatory characteristics of macrophages in ovarian tissues of the PCOS subjects, confirming significant overexpression of CD163, TREM1, and TREM2. These findings contribute to a deeper understanding of the pathogenesis of PCOS.

Accelerating histopathology workflows with generative AI-based virtually multiplexed tumour profiling

Understanding the spatial heterogeneity of tumours and its links to disease initiation and progression is a cornerstone of cancer biology. Presently, histopathology workflows heavily rely on hematoxylin and eosin and serial immunohistochemistry staining, a cumbersome, tissue-exhaustive process that results in non-aligned tissue images. We propose the VirtualMultiplexer, a generative artificial intelligence toolkit that effectively synthesizes multiplexed immunohistochemistry images for several antibody markers (namely AR, NKX3.1, CD44, CD146, p53 and ERG) from only an input hematoxylin and eosin image. The VirtualMultiplexer captures biologically relevant staining patterns across tissue scales without requiring consecutive tissue sections, image registration or extensive expert annotations. Thorough qualitative and quantitative assessment indicates that the VirtualMultiplexer achieves rapid, robust and precise generation of virtually multiplexed imaging datasets of high staining quality that are indistinguishable from the real ones. The VirtualMultiplexer is successfully transferred across tissue scales and patient cohorts with no need for model fine-tuning. Crucially, the virtually multiplexed images enabled training a graph transformer that simultaneously learns from the joint spatial distribution of several proteins to predict clinically relevant endpoints. We observe that this multiplexed learning scheme was able to greatly improve clinical prediction, as corroborated across several downstream tasks, independent patient cohorts and cancer types. Our results showcase the clinical relevance of artificial intelligence-assisted multiplexed tumour imaging, accelerating histopathology workflows and cancer biology.

Deep learning for rapid virtual H&E staining of label-free glioma tissue from hyperspectral images

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.

Virtual staining for histology by deep learning

In pathology and biomedical research, histology is the cornerstone method for tissue analysis. Currently, the histological workflow consumes plenty of chemicals, water, and time for staining procedures. Deep learning is now enabling digital replacement of parts of the histological staining procedure. In virtual staining, histological stains are created by training neural networks to produce stained images from an unstained tissue image, or through transferring information from one stain to another. These technical innovations provide more sustainable, rapid, and cost-effective alternatives to traditional histological pipelines, but their development is in an early phase and requires rigorous validation. In this review we cover the basic concepts of virtual staining for histology and provide future insights into the utilization of artificial intelligence (AI)-enabled virtual histology.

CytoGAN: Unpaired staining transfer by structure preservation for cytopathology image analysis

With the development of digital pathology, deep learning is increasingly being applied to endometrial cell morphology analysis for cancer screening. And cytology images with different staining may degrade the performance of these analysis algorithms. To address the impact of staining patterns, many strategies have been proposed and hematoxylin and eosin (H&E) images have been transferred to other staining styles. However, none of the existing methods are able to generate realistic cytological images with preserved cellular layout, and many important clinical structural information is lost. To address the above issues, we propose a different staining transformation model, CytoGAN, which can quickly and realistically generate images with different staining styles. It includes a novel structure preservation module that preserves the cell structure well, even if the resolution or cell size between the source and target domains do not match. Meanwhile, a stain adaptive module is designed to help the model generate realistic and high-quality endometrial cytology images. We compared our model with ten state-of-the-art stain transformation models and evaluated by two pathologists. Furthermore, in the downstream endometrial cancer classification task, our algorithm improves the robustness of the classification model on multimodal datasets, with more than 20 % improvement in accuracy. We found that generating specified specific stains from existing H&E images improves the diagnosis of endometrial cancer. Our code will be available on github.

Evaluation of tumor budding with virtual panCK stains generated by novel multi-model CNN framework

As the global incidence of cancer continues to rise rapidly, the need for swift and precise diagnoses has become increasingly pressing. Pathologists commonly rely on H&E-panCK stain pairs for various aspects of cancer diagnosis, including the detection of occult tumor cells and the evaluation of tumor budding. Nevertheless, conventional chemical staining methods suffer from notable drawbacks, such as time-intensive processes and irreversible staining outcomes. The virtual stain technique, leveraging generative adversarial network (GAN), has emerged as a promising alternative to chemical stains. This approach aims to transform biopsy scans (often H&E) into other stain types. Despite achieving notable progress in recent years, current state-of-the-art virtual staining models confront challenges that hinder their efficacy, particularly in achieving accurate staining outcomes under specific conditions. These limitations have impeded the practical integration of virtual staining into diagnostic practices. To address the goal of producing virtual panCK stains capable of replacing chemical panCK, we propose an innovative multi-model framework. Our approach involves employing a combination of Mask-RCNN (for cell segmentation) and GAN models to extract cytokeratin distribution from chemical H&E images. Additionally, we introduce a tailored dynamic GAN model to convert H&E images into virtual panCK stains, integrating the derived cytokeratin distribution. Our framework is motivated by the fact that the unique pattern of the panCK is derived from cytokeratin distribution. As a proof of concept, we employ our virtual panCK stains to evaluate tumor budding in 45 H&E whole-slide images taken from breast cancer-invaded lymph nodes . Through thorough validation by both pathologists and the QuPath software, our virtual panCK stains demonstrate a remarkable level of accuracy. In stark contrast, the accuracy of state-of-the-art single cycleGAN virtual panCK stains is negligible. To our best knowledge, this is the first instance of a multi-model virtual panCK framework and the utilization of virtual panCK for tumor budding assessment. Our framework excels in generating dependable virtual panCK stains with significantly improved efficiency, thereby considerably reducing turnaround times in diagnosis. Furthermore, its outcomes are easily comprehensible even to pathologists who may not be well-versed in computer technology. We firmly believe that our framework has the potential to advance the field of virtual stain, thereby making significant strides towards improved cancer diagnosis.

In silico labeling in cell biology: Potential and limitations

In silico labeling is the computational cross-modality image translation where the output modality is a subcellular marker that is not specifically encoded in the input image, for example, in silico localization of organelles from transmitted light images. In principle, in silico labeling has the potential to facilitate rapid live imaging of multiple organelles with reduced photobleaching and phototoxicity, a technology enabling a major leap toward understanding the cell as an integrated complex system. However, five years have passed since feasibility was attained, without any demonstration of using in silico labeling to uncover new biological insight. In here, we discuss the current state of in silico labeling, the limitations preventing it from becoming a practical tool, and how we can overcome these limitations to reach its full potential.

Co-exposure to boscalid and amoxicillin inhibited the degradation of boscalid and aggravated the threat to the earthworm

The extensive application of pesticides and antibiotics in agricultural production makes it possible for them to coexist in farmland, and the interaction of the two pollutants can lead to changes in environmental behavior and toxicity, creating uncertainty risks to soil and soil organisms. In this study, we explored the environmental behavior and the effects of earthworms under co-exposure to amoxicillin and boscalid and further explored the accumulation and toxic effects on earthworms. The results showed that amoxicillin increased the adsorption of boscalid in soil and inhibited its degradation. In addition, we noticed that the co-exposure of amoxicillin and boscalid caused intestinal barrier damage, which increased the bioaccumulation of earthworms for boscalid and led to more severe oxidative stress and metabolic disorders in earthworms. In summary, our findings indicate that amoxicillin can increase the ecological risk of boscalid in the environment and imply that the encounter between antibiotics and pesticides in the environment can amplify the toxic effects of pesticides, which provides new insights into the ecological risks of antibiotics.

Clinical-Grade Validation of an Autofluorescence Virtual Staining System With Human Experts and a Deep Learning System for Prostate Cancer

The tissue diagnosis of adenocarcinoma and intraductal carcinoma of the prostate includes Gleason grading of tumor morphology on the hematoxylin and eosin stain and immunohistochemistry markers on the prostatic intraepithelial neoplasia-4 stain (CK5/6, P63, and AMACR). In this work, we create an automated system for producing both virtual hematoxylin and eosin and prostatic intraepithelial neoplasia-4 immunohistochemistry stains from unstained prostate tissue using a high-throughput hyperspectral fluorescence microscope and artificial intelligence and machine learning. We demonstrate that the virtual stainer models can produce high-quality images suitable for diagnosis by genitourinary pathologists. Specifically, we validate our system through extensive human review and computational analysis, using a previously validated Gleason scoring model, and an expert panel, on a large data set of test slides. This study extends our previous work on virtual staining from autofluorescence, demonstrates the clinical utility of this technology for prostate cancer, and exemplifies a rigorous standard of qualitative and quantitative evaluation for digital pathology.

Automatic Annotation Diagnostic Framework for Nasopharyngeal Carcinoma via Pathology-Fidelity GAN and Prior-Driven Classification

Non-keratinizing carcinoma is the most common subtype of nasopharyngeal carcinoma (NPC). Its poorly differentiated tumor cells and complex microenvironment present challenges to pathological diagnosis. AI-based pathological models have demonstrated potential in diagnosing NPC, but the reliance on costly manual annotation hinders development. To address the challenges, this paper proposes a deep learning-based framework for diagnosing NPC without manual annotation. The framework includes a novel unpaired generative network and a prior-driven image classification system. With pathology-fidelity constraints, the generative network achieves accurate digital staining from H&E to EBER images. The classification system leverages staining specificity and pathological prior knowledge to annotate training data automatically and to classify images for NPC diagnosis. This work used 232 cases for study. The experimental results show that the classification system reached a 99.59% accuracy in classifying EBER images, which closely matched the diagnostic results of pathologists. Utilizing PF-GAN as the backbone of the framework, the system attained a specificity of 0.8826 in generating EBER images, markedly outperforming that of other GANs (0.6137, 0.5815). Furthermore, the F1-Score of the framework for patch level diagnosis was 0.9143, exceeding those of fully supervised models (0.9103, 0.8777). To further validate its clinical efficacy, the framework was compared with experienced pathologists at the WSI level, showing comparable NPC diagnosis performance. This low-cost and precise diagnostic framework optimizes the early pathological diagnosis method for NPC and provides an innovative strategic direction for AI-based cancer diagnosis.

Transdermal Delivery of Recombinant Human Growth Hormone by Liposomal Gel for Skin Photoaging Therapy

Human growth hormone (hGH) has emerged as a promising therapeutic agent to prevent and treat skin photoaging. However, the success of hGH therapy largely lies in the availability of an optimal delivery system that enables the efficient delivery of hGH to the dermal layer of the skin. Here, we report a delivery system of hyaluronic acid/liposome-gel-encapsulated hGH (HA/HL-Gel) that can transdermally deliver hGH into the skin for hGH-based photoaging therapy through the upregulation of collagen type I (collagen-I). Specifically, hGH-liposomes were prepared by ethanol injection and then modified with HA to achieve specific targeting. The best formulation of HA/hGH-liposomes (HA/HL) had a high encapsulation efficiency (about 20%), with a size of 180 ± 1.2 nm. The optimized HA/HL was further incorporated into the carbomer gel to form an HA/HL-Gel. The biological activity of HA/HL on human dermal fibroblasts (HDFs) was confirmed by the elevated expression level of collagen-I through the enhanced local formation of insulin-like growth factor-1 (IGF-1) in the photoaging model. Moreover, HA/HL-Gel reduced ultraviolet (UV)-induced erythema and wrinkle formation. Meanwhile, immunohistochemical staining further showed higher levels of collagen-I in the HA/HL-Gel group compared to other groups tested. Taken together, these results demonstrate that HA/HL-Gel treatment could significantly ameliorate skin photoaging and thus may be used as a clinical potential for antiaging therapy.

Accuracy of special histochemical staining methods in diagnosis of oral pathology: A systematic review and meta-analysis

Clinical decision-making and biomedical research heavily rely on imaging techniques to visualize tissue morphology. To examine tissues in detail, it is necessary to use special histochemical stains to enhance contrast. This meta-analysis aimed to assess the sensitivity and specificity of these stains in diagnosing oral pathologic specimens. We conducted a search in 8 databases, including EMBASE, PubMed, Web of Science, Scopus, ProQuest, Ovid, Cinahl, and Cochrane, up to June 2022. Of 87,393 studies, 41 articles were selected for inclusion in our study. The results revealed that the specificity and sensitivity of the special histochemical stains were 86% with confidence interval (CI) 95%: 80%-90% and 83% with CI 95%: 75%-89%, respectively. Among the stains evaluated, toluidine blue, Papanicolaou, silver stain, Giemsa, Gram, feulgen, and periodic acid-Schiff (PAS) were the most frequently used for the detection of malignancy, premalignant lesions, dysplasia, and candidiasis. The specificity and sensitivity of each stain were analyzed individually, considering the type of specimen. Toluidine blue was the most commonly utilized special histochemical stain, particularly effective, for detecting malignancy, with a specificity of 97% with CI 95%: 88%-99% and sensitivity of 76% with CI 95%: 56%-89%. In conclusion, special histochemical stains are effective in diagnosing oral lesions, exhibiting reasonable specificity and sensitivity, especially in cases of premalignant and malignant lesions. Based on the reviewed articles in our study, the silver stain was identified as highly sensitive, while Giemsa and Papanicolaou stain exhibited the highest specificity.

Transformation from hematoxylin-and-eosin staining to Ki-67 immunohistochemistry digital staining images using deep learning: experimental validation on the labeling index

Purpose

Endometrial cancer (EC) is one of the most common types of cancer affecting women. While the hematoxylin-and-eosin (H&E) staining remains the standard for histological analysis, the immunohistochemistry (IHC) method provides molecular-level visualizations. Our study proposes a digital staining method to generate the hematoxylin-3,3'-diaminobenzidine (H-DAB) IHC stain of Ki-67 for the whole slide image of the EC tumor from its H&E stain counterpart.

Approach

We employed a color unmixing technique to yield stain density maps from the optical density (OD) of the stains and utilized the U-Net for end-to-end inference. The effectiveness of the proposed method was evaluated using the Pearson correlation between the digital and physical stain's labeling index (LI), a key metric indicating tumor proliferation. Two different cross-validation schemes were designed in our study: intraslide validation and cross-case validation (CCV). In the widely used intraslide scheme, the training and validation sets might include different regions from the same slide. The rigorous CCV validation scheme strictly prohibited any validation slide from contributing to training.

Results

The proposed method yielded a high-resolution digital stain with preserved histological features, indicating a reliable correlation with the physical stain in terms of the Ki-67 LI. In the intraslide scheme, using intraslide patches resulted in a biased accuracy (e.g., R = 0.98 ) significantly higher than that of CCV. The CCV scheme retained a fair correlation (e.g., R = 0.66 ) between the LIs calculated from the digital stain and its physical IHC counterpart. Inferring the OD of the IHC stain from that of the H&E stain enhanced the correlation metric, outperforming that of the baseline model using the RGB space.

Conclusions

Our study revealed that molecule-level insights could be obtained from H&E images using deep learning. Furthermore, the improvement brought via OD inference indicated a possible method for creating more generalizable models for digital staining via per-stain analysis.

Stain SAN: simultaneous augmentation and normalization for histopathology images

Purpose

We address the need for effective stain domain adaptation methods in histopathology to enhance the performance of downstream computational tasks, particularly classification. Existing methods exhibit varying strengths and weaknesses, prompting the exploration of a different approach. The focus is on improving stain color consistency, expanding the stain domain scope, and minimizing the domain gap between image batches.

Approach

We introduce a new domain adaptation method, Stain simultaneous augmentation and normalization (SAN), designed to adjust the distribution of stain colors to align with a target distribution. Stain SAN combines the merits of established methods, such as stain normalization, stain augmentation, and stain mix-up, while mitigating their inherent limitations. Stain SAN adapts stain domains by resampling stain color matrices from a well-structured target distribution.

Results

Experimental evaluations of cross-dataset clinical estrogen receptor status classification demonstrate the efficacy of Stain SAN and its superior performance compared with existing stain adaptation methods. In one case, the area under the curve (AUC) increased by 11.4%. Overall, our results clearly show the improvements made over the history of the development of these methods culminating with substantial enhancement provided by Stain SAN. Furthermore, we show that Stain SAN achieves results comparable with the state-of-the-art generative adversarial network-based approach without requiring separate training for stain adaptation or access to the target domain during training. Stain SAN's performance is on par with HistAuGAN, proving its effectiveness and computational efficiency.

Conclusions

Stain SAN emerges as a promising solution, addressing the potential shortcomings of contemporary stain adaptation methods. Its effectiveness is underscored by notable improvements in the context of clinical estrogen receptor status classification, where it achieves the best AUC performance. The findings endorse Stain SAN as a robust approach for stain domain adaptation in histopathology images, with implications for advancing computational tasks in the field.

ML-driven segmentation of microvascular features during histological examination of tissue-engineered vascular grafts

Introduction

The development of next-generation tissue-engineered medical devices such as tissue-engineered vascular grafts (TEVGs) is a leading trend in translational medicine. Microscopic examination is an indispensable part of animal experimentation, and histopathological analysis of regenerated tissue is crucial for assessing the outcomes of implanted medical devices. However, the objective quantification of regenerated tissues can be challenging due to their unusual and complex architecture. To address these challenges, research and development of advanced ML-driven tools for performing adequate histological analysis appears to be an extremely promising direction.

Methods

We compiled a dataset of 104 representative whole slide images (WSIs) of TEVGs which were collected after a 6-month implantation into the sheep carotid artery. The histological examination aimed to analyze the patterns of vascular tissue regeneration in TEVGs in situ. Having performed an automated slicing of these WSIs by the Entropy Masker algorithm, we filtered and then manually annotated 1,401 patches to identify 9 histological features: arteriole lumen, arteriole media, arteriole adventitia, venule lumen, venule wall, capillary lumen, capillary wall, immune cells, and nerve trunks. To segment and quantify these features, we rigorously tuned and evaluated the performance of six deep learning models (U-Net, LinkNet, FPN, PSPNet, DeepLabV3, and MA-Net).

Results

After rigorous hyperparameter optimization, all six deep learning models achieved mean Dice Similarity Coefficients (DSC) exceeding 0.823. Notably, FPN and PSPNet exhibited the fastest convergence rates. MA-Net stood out with the highest mean DSC of 0.875, demonstrating superior performance in arteriole segmentation. DeepLabV3 performed well in segmenting venous and capillary structures, while FPN exhibited proficiency in identifying immune cells and nerve trunks. An ensemble of these three models attained an average DSC of 0.889, surpassing their individual performances.

Conclusion

This study showcases the potential of ML-driven segmentation in the analysis of histological images of tissue-engineered vascular grafts. Through the creation of a unique dataset and the optimization of deep neural network hyperparameters, we developed and validated an ensemble model, establishing an effective tool for detecting key histological features essential for understanding vascular tissue regeneration. These advances herald a significant improvement in ML-assisted workflows for tissue engineering research and development.

Prognostic significance of TNFRSF4 expression and development of a pathomics model to predict expression in hepatocellular carcinoma

Background

TNFRSF4 plays a significant role in cancer progression, especially in hepatocellular carcinoma (HCC). This study aims to investigate the prognostic value of TNFRSF4 expression in patients with HCC and to develop a predictive pathomics model for its expression.

Methods

A cohort of patients with HCC retrieved from the TCGA database was analyzed using RNA-seq analysis to determine TNFRSF4 expression and its impact on overall survival (OS). Additionally, hematoxylin-eosin staining analysis was performed to construct a pathomics model for predicting TNFRSF4 expression. Then, pathway enrichment analysis was conducted, immune checkpoint markers were investigated, and immune cell infiltration was examined to explore the underlying biological mechanism of the pathomics score.

Results

TNFRSF4 expression was significantly higher in tumor tissues than in normal tissues. TNFRSF4 expression also exhibited significant correlations with various clinical variables, including pathologic stage III/IV and R1/R2/RX residual tumor. Furthermore, elevated TNFRSF4 expression was associated with unfavorable OS. Interestingly, in the subgroup analysis, elevated TNFRSF4 expression was identified as a significant risk factor for OS in male patients. The newly developed pathomics model successfully predicted TNFRSF4 expression with good performance and revealed a significant association between high pathomics scores and worse OS. In male patients, high pathomics scores were also associated with a higher risk of mortality. Moreover, pathomics scores were also involved in specific hallmarks, immune-related characteristics, and apoptosis-related genes in HCC, such as epithelial-mesenchymal transition, Tregs, and BAX expression.

Conclusions

Our findings suggest that TNFRSF4 expression and the newly devised pathomics scores hold potential as prognostic markers for OS in patients with HCC. Additionally, gender influenced the association between these markers and patient outcomes.

Deep Learning Analysis for Predicting Tumor Spread through Air Space in Early-Stage Lung Adenocarcinoma Pathology Images

The presence of spread through air spaces (STASs) in early-stage lung adenocarcinoma is a significant prognostic factor associated with disease recurrence and poor outcomes. Although current STAS detection methods rely on pathological examinations, the advent of artificial intelligence (AI) offers opportunities for automated histopathological image analysis. This study developed a deep learning (DL) model for STAS prediction and investigated the correlation between the prediction results and patient outcomes. To develop the DL-based STAS prediction model, 1053 digital pathology whole-slide images (WSIs) from the competition dataset were enrolled in the training set, and 227 WSIs from the National Taiwan University Hospital were enrolled for external validation. A YOLOv5-based framework comprising preprocessing, candidate detection, false-positive reduction, and patient-based prediction was proposed for STAS prediction. The model achieved an area under the curve (AUC) of 0.83 in predicting STAS presence, with 72% accuracy, 81% sensitivity, and 63% specificity. Additionally, the DL model demonstrated a prognostic value in disease-free survival compared to that of pathological evaluation. These findings suggest that DL-based STAS prediction could serve as an adjunctive screening tool and facilitate clinical decision-making in patients with early-stage lung adenocarcinoma.

Integrating spatial transcriptomics and bulk RNA-seq: predicting gene expression with enhanced resolution through graph attention networks

Spatial transcriptomics data play a crucial role in cancer research, providing a nuanced understanding of the spatial organization of gene expression within tumor tissues. Unraveling the spatial dynamics of gene expression can unveil key insights into tumor heterogeneity and aid in identifying potential therapeutic targets. However, in many large-scale cancer studies, spatial transcriptomics data are limited, with bulk RNA-seq and corresponding Whole Slide Image (WSI) data being more common (e.g. TCGA project). To address this gap, there is a critical need to develop methodologies that can estimate gene expression at near-cell (spot) level resolution from existing WSI and bulk RNA-seq data. This approach is essential for reanalyzing expansive cohort studies and uncovering novel biomarkers that have been overlooked in the initial assessments. In this study, we present STGAT (Spatial Transcriptomics Graph Attention Network), a novel approach leveraging Graph Attention Networks (GAT) to discern spatial dependencies among spots. Trained on spatial transcriptomics data, STGAT is designed to estimate gene expression profiles at spot-level resolution and predict whether each spot represents tumor or non-tumor tissue, especially in patient samples where only WSI and bulk RNA-seq data are available. Comprehensive tests on two breast cancer spatial transcriptomics datasets demonstrated that STGAT outperformed existing methods in accurately predicting gene expression. Further analyses using the TCGA breast cancer dataset revealed that gene expression estimated from tumor-only spots (predicted by STGAT) provides more accurate molecular signatures for breast cancer sub-type and tumor stage prediction, and also leading to improved patient survival and disease-free analysis. Availability: Code is available at https://github.com/compbiolabucf/STGAT.

Evolution of staining methods in neuroanatomy: Impetus for emanation of neuron doctrine during the turn of 20th century

The nervous system is distinctive as compared to other tissue systems in human body owing to intricate structural organization. Histological studies played a key role in unveiling complex details of nervous tissue. However, the process of developing suitable staining method for nerve cells was arduous and spanned across almost half a century. The present study explored details of the journey involving quest for propitious staining method in neuroanatomy culminating in promulgation of neuron doctrine at the onset of 20th century. Initial efforts involving hematoxylin (including its diverse modifications) and subsequent adoption of analogous dye-based stains (like Nissl's method) had limited success in visualization of different parts of a nerve cell and structural details of nervous tissue. This was due to inability of dye-based stains to penetrate the connective tissue sheath of nervous tissue. Eventually, advent of metallic stains in form of silver impregnation method (Golgi stain), reduced silver impregnation method with gold stain (Cajal's stain) and silver carbonate staining method of Río-Hortega unraveled the structure of nervous tissue. The evolution of staining methods catalyzed the refinement of theories pertinent to constitution of nervous tissue. Golgi's staining led to emergence of reticular theory (neurons exist as a network) and Nissl's staining was the basis of the concept of Nervösen Grau (nerve cells and glial cells are embedded in mass of gray matter). Finally, Cajal's staining method successfully elucidated the complex anatomy of nerve terminals and resulted in emanation of neuron doctrine (neurons exists as individual units with adjacent connections).

Enhanced Multiscale Human Brain Imaging by Semi-supervised Digital Staining and Serial Sectioning Optical Coherence Tomography

A major challenge in neuroscience is to visualize the structure of the human brain at different scales. Traditional histology reveals micro- and meso-scale brain features, but suffers from staining variability, tissue damage and distortion that impedes accurate 3D reconstructions. Here, we present a new 3D imaging framework that combines serial sectioning optical coherence tomography (S-OCT) with a deep-learning digital staining (DS) model. We develop a novel semi-supervised learning technique to facilitate DS model training on weakly paired images. The DS model performs translation from S-OCT to Gallyas silver staining. We demonstrate DS on various human cerebral cortex samples with consistent staining quality. Additionally, we show that DS enhances contrast across cortical layer boundaries. Furthermore, we showcase geometry-preserving 3D DS on cubic-centimeter tissue blocks and visualization of meso-scale vessel networks in the white matter. We believe that our technique offers the potential for high-throughput, multiscale imaging of brain tissues and may facilitate studies of brain structures.

PNAd-expressing vessels characterize the dermis of CD3+ T-cell-mediated cutaneous diseases

T-cell recruitment to skin tissues is essential for inflammation in different cutaneous diseases; however, the mechanisms by which these T cells access the skin remain unclear. High endothelial venules expressing peripheral node address in (PNAd), an L-selectin ligand, are located in secondary lymphoid organs and are responsible for increasing T-cell influx into the lymphoid tissues. They are also found in non-lymphoid tissues during inflammation. However, their presence in different common inflammatory cutaneous diseases and their correlation with T-cell infiltration remain unclear. Herein, we explored the mechanisms underlying the access of T cells to the skin by investigating the presence of PNAd-expressing vessels in different cutaneous diseases, and its correlation with T cells' presence. Skin sections of 43 patients with different diseases were subjected to immunohistochemical and immunofluorescence staining to examine the presence of PNAd-expressing vessels in the dermis. The correlation of the percentage of these vessels in the dermis of these patients with the severity/grade of CD3+ T-cell infiltration was assessed. PNAd-expressing vessels were commonly found in the skin of patients with different inflammatory diseases. A high percentage of these vessels in the dermis was associated with increased severity of CD3+ T-cell infiltration (P < 0.05). Additionally, CD3+ T cells were found both around the PNAd-expressing vessels and within the vessel lumen. PNAd-expressing vessels in cutaneous inflammatory diseases, characterized by CD3+ T-cell infiltration, could be a crucial entry point for T cells into the skin. Thus, selective targeting of these vessels could be beneficial in cutaneous inflammatory disease treatment.

Conventional HE staining combined with two special staining methods to identify antemortem stab wound in case with highly decomposed mutilated corpses

This study aims to identify an antemortem neck stab wound on a highly decomposed, headless and mutilated body by conventional hematoxylin-eosin (HE) staining combined with Ponceau-Victoria blue B staining (P-VB staining) and Masson staining. Specifically, a tissue sample was excised from the skin and muscle tissue at the junction of the normal and brownish discolored areas around the suspected stabbing tract of the left neck, in the upper and lower wound-clavicle-shoulder region. Conventional HE staining only provides a morphological and structural outline of the tissue, with both the injury hemorrhage and local connective tissue appearing eosinophilic pink. However, P-VB staining shows obvious contrast between the injury hemorrhage and connective tissue, with the former appearing yellow-green and the latter appearing orange-red. Similarly, Masson staining of the injury hemorrhage and connective tissue contrast clearly with purple-red and dark blue, respectively. Therefore, our study highlights that conventional HE staining with the combination of P-VB staining and Masson staining allowed for a clearer and corroborated identification of antemortem injury and hemorrhage from the stab wound in highly decomposed mutilated corpses.

Extracting interpretable features for pathologists using weakly supervised learning to predict p16 expression in oropharyngeal cancer

One drawback of existing artificial intelligence (AI)-based histopathological prediction models is the lack of interpretability. The objective of this study is to extract p16-positive oropharyngeal squamous cell carcinoma (OPSCC) features in a form that can be interpreted by pathologists using AI model. We constructed a model for predicting p16 expression using a dataset of whole-slide images from 114 OPSCC biopsy cases. We used the clustering-constrained attention-based multiple-instance learning (CLAM) model, a weakly supervised learning approach. To improve performance, we incorporated tumor annotation into the model (Annot-CLAM) and achieved the mean area under the receiver operating characteristic curve of 0.905. Utilizing the image patches on which the model focused, we examined the features of model interest via histopathologic morphological analysis and cycle-consistent adversarial network (CycleGAN) image translation. The histopathologic morphological analysis evaluated the histopathological characteristics of image patches, revealing significant differences in the numbers of nuclei, the perimeters of the nuclei, and the intercellular bridges between p16-negative and p16-positive image patches. By using the CycleGAN-converted images, we confirmed that the sizes and densities of nuclei are significantly converted. This novel approach improves interpretability in histopathological morphology-based AI models and contributes to the advancement of clinically valuable histopathological morphological features.

Rapid deep learning-assisted predictive diagnostics for point-of-care testing

Prominent techniques such as real-time polymerase chain reaction (RT-PCR), enzyme-linked immunosorbent assay (ELISA), and rapid kits are currently being explored to both enhance sensitivity and reduce assay time for diagnostic tests. Existing commercial molecular methods typically take several hours, while immunoassays can range from several hours to tens of minutes. Rapid diagnostics are crucial in Point-of-Care Testing (POCT). We propose an approach that integrates a time-series deep learning architecture and AI-based verification, for the enhanced result analysis of lateral flow assays. This approach is applicable to both infectious diseases and non-infectious biomarkers. In blind tests using clinical samples, our method achieved diagnostic times as short as 2 minutes, exceeding the accuracy of human analysis at 15 minutes. Furthermore, our technique significantly reduces assay time to just 1-2 minutes in the POCT setting. This advancement has the potential to greatly enhance POCT diagnostics, enabling both healthcare professionals and non-experts to make rapid, accurate decisions.

Virtual histological staining of unlabeled autopsy tissue

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.

Bright, photostable and long-circulating NIR-II nanoparticles for whole-process monitoring and evaluation of renal transplantation

Kidney transplantation is the gold standard for the treatment of end-stage renal diseases (ESRDs). However, the scarcity of donor kidneys has caused more and more ESRD patients to be stuck on the waiting list for transplant surgery. Improving the survival rate for renal grafts is an alternative solution to the shortage of donor kidneys. Therefore, real-time monitoring of the surgical process is crucial to the success of kidney transplantation, but efficient methods and techniques are lacking. Herein, a fluorescence technology based on bright, photostable and long-circulating aggregation-induced emission (AIE) active NIR-II nano-contrast agent DIPT-ICF nanoparticles for the whole-process monitoring and evaluation of renal transplantation has been reported. In the aggregated state, DIPT-ICF exhibits superior photophysical properties compared with the commercial dyes IR-26 and IR-1061. Besides, the long-circulating characteristic of the AIE nano-contrast agent helps to achieve renal angiography in kidney retrieval surgery, donor kidney quality evaluation, diagnosing vascular and ureteral complications, and assessment of renal graft reperfusion beyond renovascular reconstruction, which considerably outperforms the clinically approved indocyanine green (ICG).

Apigenin analogs as α-glucosidase inhibitors with antidiabetic activity

This study investigated the inhibitory potential of a series of synthesized compounds (L1-L27) on α-glucosidase. Among them, compound L22 showed significant inhibitory effect. Through enzymatic kinetics studies, we demonstrated that L22 acts via a non-competitive inhibition mode with a Ki value of 2.61 μM, highlighting its high affinity for the enzyme. Molecular docking studies revealed the formation of hydrogen bonds between L22 and α-glucosidase and diverse interactions with neighboring amino acid residues. Furthermore, molecular dynamics simulations confirmed the stability of the L22-α-glucosidase complex. In a mouse model of type 2 diabetes, treatment with L22 significantly lowered fasting blood glucose levels, and reduced insulin resistance, suggesting its potential as a therapeutic agent for type 2 diabetes. Furthermore, L22 showed a protective effect against oxidative stress in the liver and alleviated liver and pancreatic abnormalities. These results provide valuable insights into the mechanism of action of L22 and its potential applications to treat type 2 diabetes, and improve liver health.

Shedding light on ultrasound in action: Optical and optoacoustic monitoring of ultrasound brain interventions

Monitoring brain responses to ultrasonic interventions is becoming an important pillar of a growing number of applications employing acoustic waves to actuate and cure the brain. Optical interrogation of living tissues provides a unique means for retrieving functional and molecular information related to brain activity and disease-specific biomarkers. The hybrid optoacoustic imaging methods have further enabled deep-tissue imaging with optical contrast at high spatial and temporal resolution. The marriage between light and sound thus brings together the highly complementary advantages of both modalities toward high precision interrogation, stimulation, and therapy of the brain with strong impact in the fields of ultrasound neuromodulation, gene and drug delivery, or noninvasive treatments of neurological and neurodegenerative disorders. In this review, we elaborate on current advances in optical and optoacoustic monitoring of ultrasound interventions. We describe the main principles and mechanisms underlying each method before diving into the corresponding biomedical applications. We identify areas of improvement as well as promising approaches with clinical translation potential.

Dual contrastive learning based image-to-image translation of unstained skin tissue into virtually stained H&E images

Staining is a crucial step in histopathology that prepares tissue sections for microscopic examination. Hematoxylin and eosin (H&E) staining, also known as basic or routine staining, is used in 80% of histopathology slides worldwide. To enhance the histopathology workflow, recent research has focused on integrating generative artificial intelligence and deep learning models. These models have the potential to improve staining accuracy, reduce staining time, and minimize the use of hazardous chemicals, making histopathology a safer and more efficient field. In this study, we introduce a novel three-stage, dual contrastive learning-based, image-to-image generative (DCLGAN) model for virtually applying an "H&E stain" to unstained skin tissue images. The proposed model utilizes a unique learning setting comprising two pairs of generators and discriminators. By employing contrastive learning, our model maximizes the mutual information between traditional H&E-stained and virtually stained H&E patches. Our dataset consists of pairs of unstained and H&E-stained images, scanned with a brightfield microscope at 20 × magnification, providing a comprehensive set of training and testing images for evaluating the efficacy of our proposed model. Two metrics, Fréchet Inception Distance (FID) and Kernel Inception Distance (KID), were used to quantitatively evaluate virtual stained slides. Our analysis revealed that the average FID score between virtually stained and H&E-stained images (80.47) was considerably lower than that between unstained and virtually stained slides (342.01), and unstained and H&E stained (320.4) indicating a similarity virtual and H&E stains. Similarly, the mean KID score between H&E stained and virtually stained images (0.022) was significantly lower than the mean KID score between unstained and H&E stained (0.28) or unstained and virtually stained (0.31) images. In addition, a group of experienced dermatopathologists evaluated traditional and virtually stained images and demonstrated an average agreement of 78.8% and 90.2% for paired and single virtual stained image evaluations, respectively. Our study demonstrates that the proposed three-stage dual contrastive learning-based image-to-image generative model is effective in generating virtual stained images, as indicated by quantified parameters and grader evaluations. In addition, our findings suggest that GAN models have the potential to replace traditional H&E staining, which can reduce both time and environmental impact. This study highlights the promise of virtual staining as a viable alternative to traditional staining techniques in histopathology.

Attention-Enhanced Unpaired xAI-GANs for Transformation of Histological Stain Images

Histological staining is the primary method for confirming cancer diagnoses, but certain types, such as p63 staining, can be expensive and potentially damaging to tissues. In our research, we innovate by generating p63-stained images from H&E-stained slides for metaplastic breast cancer. This is a crucial development, considering the high costs and tissue risks associated with direct p63 staining. Our approach employs an advanced CycleGAN architecture, xAI-CycleGAN, enhanced with context-based loss to maintain structural integrity. The inclusion of convolutional attention in our model distinguishes between structural and color details more effectively, thus significantly enhancing the visual quality of the results. This approach shows a marked improvement over the base xAI-CycleGAN and standard CycleGAN models, offering the benefits of a more compact network and faster training even with the inclusion of attention.

Intraoperative margin assessment for basal cell carcinoma with deep learning and histologic tumor mapping to surgical site

Successful treatment of solid cancers relies on complete surgical excision of the tumor either for definitive treatment or before adjuvant therapy. Intraoperative and postoperative radial sectioning, the most common form of margin assessment, can lead to incomplete excision and increase the risk of recurrence and repeat procedures. Mohs Micrographic Surgery is associated with complete removal of basal cell and squamous cell carcinoma through real-time margin assessment of 100% of the peripheral and deep margins. Real-time assessment in many tumor types is constrained by tissue size, complexity, and specimen processing / assessment time during general anesthesia. We developed an artificial intelligence platform to reduce the tissue preprocessing and histological assessment time through automated grossing recommendations, mapping and orientation of tumor to the surgical specimen. Using basal cell carcinoma as a model system, results demonstrate that this approach can address surgical laboratory efficiency bottlenecks for rapid and complete intraoperative margin assessment.

Time for a full digital approach in nephropathology: a systematic review of current artificial intelligence applications and future directions

INTRODUCTION

Artificial intelligence (AI) integration in nephropathology has been growing rapidly in recent years, facing several challenges including the wide range of histological techniques used, the low occurrence of certain diseases, and the need for data sharing. This narrative review retraces the history of AI in nephropathology and provides insights into potential future developments.

METHODS

Electronic searches in PubMed-MEDLINE and Embase were made to extract pertinent articles from the literature. Works about automated image analysis or the application of an AI algorithm on non-neoplastic kidney histological samples were included and analyzed to extract information such as publication year, AI task, and learning type. Prepublication servers and reviews were not included.

RESULTS

Seventy-six (76) original research articles were selected. Most of the studies were conducted in the United States in the last 7 years. To date, research has been mainly conducted on relatively easy tasks, like single-stain glomerular segmentation. However, there is a trend towards developing more complex tasks such as glomerular multi-stain classification.

CONCLUSION

Deep learning has been used to identify patterns in complex histopathology data and looks promising for the comprehensive assessment of renal biopsy, through the use of multiple stains and virtual staining techniques. Hybrid and collaborative learning approaches have also been explored to utilize large amounts of unlabeled data. A diverse team of experts, including nephropathologists, computer scientists, and clinicians, is crucial for the development of AI systems for nephropathology. Collaborative efforts among multidisciplinary experts result in clinically relevant and effective AI tools.

Development of an automated estimation of foot process width using deep learning in kidney biopsies from patients with Fabry, minimal change, and diabetic kidney diseases

Podocyte injury plays a key role in pathogenesis of many kidney diseases with increased podocyte foot process width (FPW), an important measure of podocyte injury. Unfortunately, there is no consensus on the best way to estimate FPW and unbiased stereology, the current gold standard, is time consuming and not widely available. To address this, we developed an automated FPW estimation technique using deep learning. A U-Net architecture variant model was trained to semantically segment the podocyte-glomerular basement membrane interface and filtration slits. Additionally, we employed a post-processing computer vision approach to accurately estimate FPW. A custom segmentation utility was also created to manually classify these structures on digital electron microscopy (EM) images and to prepare a training dataset. The model was applied to EM images of kidney biopsies from 56 patients with Fabry disease, 15 with type 2 diabetes, 10 with minimal change disease, and 17 normal individuals. The results were compared with unbiased stereology measurements performed by expert technicians unaware of the clinical information. FPW measured by deep learning and by the expert technicians were highly correlated and not statistically different in any of the studied groups. A Bland-Altman plot confirmed interchangeability of the methods. FPW measurement time per biopsy was substantially reduced by deep learning. Thus, we have developed a novel validated deep learning model for FPW measurement on EM images. The model is accessible through a cloud-based application making calculation of this important biomarker more widely accessible for research and clinical applications.

PhaseFIT: live-organoid phase-fluorescent image transformation via generative AI

Organoid models have provided a powerful platform for mechanistic investigations into fundamental biological processes involved in the development and function of organs. Despite the potential for image-based phenotypic quantification of organoids, their complex 3D structure, and the time-consuming and labor-intensive nature of immunofluorescent staining present significant challenges. In this work, we developed a virtual painting system, PhaseFIT (phase-fluorescent image transformation) utilizing customized and morphologically rich 2.5D intestinal organoids, which generate virtual fluorescent images for phenotypic quantification via accessible and low-cost organoid phase images. This system is driven by a novel segmentation-informed deep generative model that specializes in segmenting overlap and proximity between objects. The model enables an annotation-free digital transformation from phase-contrast to multi-channel fluorescent images. The virtual painting results of nuclei, secretory cell markers, and stem cells demonstrate that PhaseFIT outperforms the existing deep learning-based stain transformation models by generating fine-grained visual content. We further validated the efficiency and accuracy of PhaseFIT to quantify the impacts of three compounds on crypt formation, cell population, and cell stemness. PhaseFIT is the first deep learning-enabled virtual painting system focused on live organoids, enabling large-scale, informative, and efficient organoid phenotypic quantification. PhaseFIT would enable the use of organoids in high-throughput drug screening applications.

Deep UV-excited fluorescence microscopy installed with CycleGAN-assisted image translation enhances precise detection of lymph node metastasis towards rapid intraoperative diagnosis

Rapid and precise intraoperative diagnosing systems are required for improving surgical outcomes and patient prognosis. Because of the poor quality and time-intensive process of the prevalent frozen section procedure, various intraoperative diagnostic imaging systems have been explored. Microscopy with ultraviolet surface excitation (MUSE) is an inexpensive, maintenance-free, and rapid imaging technique that yields images like thin-sectioned samples without sectioning. However, pathologists find it nearly impossible to assign diagnostic labels to MUSE images of unfixed specimens; thus, AI for intraoperative diagnosis cannot be trained in a supervised learning manner. In this study, we propose a deep-learning pipeline model for lymph node metastasis detection, in which CycleGAN translate MUSE images of unfixed lymph nodes to formalin-fixed paraffin-embedded (FFPE) sample, and diagnostic prediction is performed using deep convolutional neural network trained on FFPE sample images. Our pipeline yielded an average accuracy of 84.6% when using each of the three deep convolutional neural networks, which is a 18.3% increase over the classification-only model without CycleGAN. The modality translation to FFPE sample images using CycleGAN can be applied to various intraoperative diagnostic imaging systems and eliminate the difficulty for pathologists in labeling new modality images in clinical sites. We anticipate our pipeline to be a starting point for accurate rapid intraoperative diagnostic systems for new imaging modalities, leading to healthcare quality improvement.

Roadmap on Label-Free Super-Resolution Imaging

Label-free super-resolution (LFSR) imaging relies on light-scattering processes in nanoscale objects without a need for fluorescent (FL) staining required in super-resolved FL microscopy. The objectives of this Roadmap are to present a comprehensive vision of the developments, the state-of-the-art in this field, and to discuss the resolution boundaries and hurdles which need to be overcome to break the classical diffraction limit of the LFSR imaging. The scope of this Roadmap spans from the advanced interference detection techniques, where the diffraction-limited lateral resolution is combined with unsurpassed axial and temporal resolution, to techniques with true lateral super-resolution capability which are based on understanding resolution as an information science problem, on using novel structured illumination, near-field scanning, and nonlinear optics approaches, and on designing superlenses based on nanoplasmonics, metamaterials, transformation optics, and microsphere-assisted approaches. To this end, this Roadmap brings under the same umbrella researchers from the physics and biomedical optics communities in which such studies have often been developing separately. The ultimate intent of this paper is to create a vision for the current and future developments of LFSR imaging based on its physical mechanisms and to create a great opening for the series of articles in this field.