Search bioRxiv⌕ Search
Home/Archive/bioRxiv

bioRxiv · 10.1101/2025.10.07.675857

Artificial Intelligence-enabled Histological Analysis in Preclinical Respiratory Disease Models: A Scoping Review

Kuhar, E.·Park, J.·Jahandideh, F.·Komeili, M.·Sadeknury, A.·Kang, N.·Karunamurthy, P.·Reza Zarei, M.·Ebrahimi, A.·Gill, S. E.·Liaw, P. C.·Fergusson, D. A.·Stewart, D. J.·Mer, A.·Lalu, M. M.
View original source ↗Export metadata ↓

Abstract

Histological analysis is a cornerstone of preclinical respiratory disease research, enabling assessment of pathology, therapeutic effects, and mechanisms. However, conventional approaches rely on manual scoring, which is subjective, time-consuming, and difficult to scale due to low throughput and inter-observer variability. Artificial intelligence (AI), particularly deep learning, offers potential to automate histology workflows, but its use and evaluation in preclinical respiratory models have not been synthesized. We conducted a scoping review following Joanna Briggs Institute guidelines, searching MEDLINE and Embase (inception-January 2025) for preclinical studies using AI to analyze histology in respiratory disease models. Screening, full-text review, and data extraction were performed in duplicate. Of 6271 studies screened, 29 met inclusion criteria. Most used murine models (76%) and investigated lung cancer (28%), pulmonary fibrosis (24%), or tuberculosis (17%). Hematoxylin and eosin was the most common stain (48%), with others targeting collagen or immune markers. AI tasks included image classification (n=20), segmentation (n=10), and object detection (n=4), predominantly using convolutional neural networks (69%). Preprocessing methods (e.g., stain normalization) were common, but annotation and training practices were inconsistently reported. Performance was generally high (accuracy [≥]90%; 7 studies) though validation metrics varied, and external validation was absent. Most studies used "black box" models, with minimal application of explainability techniques. Reproducibility measures, such as sharing datasets or code were rarely reported. AI tools are poised to transform histological analysis in preclinical respiratory research. By addressing gaps in validation, transparency, and standardization, the field can harness these technologies to deliver robust, efficient, and scalable workflows. Registration: Open Science Framework https://doi.org/10.17605/OSF.IO/NM94E

Explore related subjects

cell biologyPreprint

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Kuhar, E., Park, J., Jahandideh, F., Komeili, M., Sadeknury, A., Kang, N., Karunamurthy, P., Reza Zarei, M., Ebrahimi, A., Gill, S. E., Liaw, P. C., Fergusson, D. A., Stewart, D. J., Mer, A., Lalu, M. M.. 2025-10-07. Artificial Intelligence-enabled Histological Analysis in Preclinical Respiratory Disease Models: A Scoping Review. https://doi.org/10.1101/2025.10.07.675857

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related preprints

bioRxiv2026

Deep generative embeddings of gene expression and splicing reposition the interpretation of single-cell transcriptomic signatures

Single-cell transcriptomic analysis predominantly derives cell identity from gene expression analysis, while alternative splicing is processed separately despite its fundamental role for cell homeostasis. To overcome the limits of separate investigations, we developed a probabilistic deep learning framework, Crecerelle, enabling resolution of the contributions of gene expression and alternative splicing in each cell. Crecerelle learns cell embeddings from gene expressions and alternative splicing isoforms, to decipher their mutually dependent impact on the functional characterisation of cells in a data-driven manner, exemplified for the Tabula Muris dataset. This is enabled through a zero-and-N-inflated Dirichlet-Multinomial for a variational autoencoder that learns cell embeddings solely from splicing profiles, as well as a bi-modal variational autoencoder with a relevance-weighted mixture-of-experts variational posterior to consolidate the modality-specific contribution at single-cell level. Crecerelle reveals cell-type-specific isoform markers as well as subpopulations with unique isoforms and uncovers regulatory and disease-associated pathways not detected by gene expression analyses alone. This scalable and interpretable framework thus allows a more holistic study of transcriptomic regulation and will open a route to modality-relevance-weighted investigations across single-cell multiomics datasets and their influence on cellular homeostasis, tissue development and disease phenotypes.

cell biology↗
bioRxiv2026

MHC Molecules on B Cell Microvilli Are Spatially Associated with IL-15Rα

Interleukin-15 (IL-15) trans-presentation (TP) by B cells is an important mechanism of T-cell activation; however, the spatial organisation of interleukin-15 receptor (IL-15R) relative to major histocompatibility complex (MHC) molecules on B-cell microvilli remains poorly understood. As microvilli protrude from the B-cell surface and may serve as sites of initial B cell-T-cell contact, the distribution of IL-15R and MHC molecules within these structures may be important during the earliest stages of T-cell recognition and activation. Here, we investigated the spatial association and molecular proximity of IL-15R with MHC class I and class II molecules on B-cell microvilli before immunological synapse formation, using confocal microscopy, stimulated emission depletion (STED) microscopy, stochastic optical reconstruction microscopy (STORM), and fluorescence lifetime imaging microscopy-based Forster resonance energy transfer (FLIM-FRET). Both MHC class I and class II molecules showed significant spatial association with IL-15R; however, the extent of colocalisation decreased as spatial resolution increased. STED microscopy revealed significant colocalisation between IL-15R and MHC class I, whereas STORM did not detect this association. In contrast, IL-15R and MHC class II remained significantly colocalised at both resolutions. FLIM-FRET further demonstrated molecular proximity between IL-15R and both MHC class I and class II molecules, with higher FRET efficiency observed for MHC class II. Collectively, these findings indicate that IL-15R is spatially organised in proximity to both MHC class I and class II molecules on B-cell microvilli before immunological synapse formation. This arrangement at potential sites of initial B-cell-T-cell contact may facilitate the coordination of IL-15 trans-presentation and antigen presentation during the earliest stages of B-cell-T-cell interactions.

cell biology↗
bioRxiv2026

Pulsed-SILAC in single mouse embryos reveals early embryonic protein synthesis dynamics and phosphosite regulation

Early embryogenesis relies extensively on maternally deposited products until zygotic genome activation, yet the dynamics for the synthesis of new proteins in mammalian embryos remains poorly characterized. To address this, we applied pulsed stable isotope labelling by amino acids in cell culture (pSILAC) combined with narrow-window data-independent acquisition mass spectrometry to single mouse oocytes and embryos to resolve de novo protein synthesis during early embryogenesis. This revealed that the maternal proteome is not a static reservoir, with components of the subcortical maternal complex and amino acid transporters SLC7A1/2 being actively synthesized during the earliest developmental stages. Furthermore, phosphoproteomic analysis identified hundreds of previously unreported phosphosites and extensive regulation during the oocyte-to-embryo transition. Notably, phosphorylation of the PRC2-interacting KLP motif of EZHIP emerged as a potential regulatory mechanism, with modification of this region reducing EZHIP-PRC2 interaction and coinciding with H3K27me3 remodelling. Together, single embryo pSILAC revealed a maternal proteome that is continuously synthesized, recycled, and post-translationally regulated during early embryogenesis.

cell biology↗