MAPS: Pathologist-level cell type annotation from tissue images through machine learning

Shaban, Muhammad; Bai, Yunhao; Qiu, Hengwei; Mao, Shulin; Yeung, Jason; Yeo, Yao Yu; Shanmugam, Vignesh; Chen, Han; Zhu, Bokai; Nolan, Garry P.; Shipp, Margaret A.; Rodig, Scott J.; Jiang, Sizun; Mahmood, Faisal

doi:10.1101/2023.06.25.546474

Cited by 5 publications

(7 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is also hard to combine different imaging databases and imaging modalities due to the difference between multiplex marker panels and imaging technologies. Novel computation methods for unseen spatial single-cell dataset annotation 28,29 and missing marker imputation 30,31 could be used to further improve the generalizability of the SNOWFLAKE pipeline. Despite these limitations, SNOWFLAKE provides a complementary solution to the need to extract relevant single-cell motifs prediction and biomarker identification for the understanding of spatial arrangement in health and disease.…”

Section: Discussionmentioning

confidence: 99%

Spatial Morphoproteomic Features Predict Uniqueness of Immune Microarchitectures and Responses in Lymphoid Follicles

Hu,

Allam,

Kaushik

et al. 2024

Preprint

View full text Add to dashboard Cite

Multiplex imaging technologies allow the characterization of single cells in their cellular environments. Understanding the organization of single cells within their microenvironment and quantifying disease-status related biomarkers is essential for multiplex datasets. Here we proposed SNOWFLAKE, a graph neural network framework pipeline for the prediction of disease-status from combined multiplex cell expression and morphology in human B-cell follicles. We applied SNOWFLAKE to a multiplex dataset related to COVID-19 infection in humans and showed better predictive power of the SNOWFLAKE pipeline compared to other machine learning and deep learning methods. Moreover, we combined morphological features inside graph edge features to utilize attribution methods for extracting disease-relevant motifs from single-cell spatial graphs. The underlying subgraphs were further analyzed and associated with disease status across the dataset. We showed that SNOWFLAKE successfully extracted significant low dimensional embedding from subgraphs with a clear separation between disease status and helped characterize unique cellular interactions in the subgraphs. SNOWFLAKE is a generalizable pipeline for the analysis of multiplex imaging data modality by extracting disease-relevant subgraphs guided by graph-level prediction.

show abstract

Section: Discussionmentioning

confidence: 99%

Spatial Morphoproteomic Features Predict Uniqueness of Immune Microarchitectures and Responses in Lymphoid Follicles

Hu,

Allam,

Kaushik

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…However, the model must be retrained for each dataset it is applied to. MAPS 21 , another recently published deep learning algorithm for cell classification, likewise must be retrained on each new dataset. Custom models have the potential to generate classifications that precisely conform to the specifics of a given dataset, but the time and effort to accomplish such a task is significant.…”

Section: Discussionmentioning

confidence: 99%

“…However, manually scoring cells in highly multiplexed imaging data is not scalable. As a result, nearly all existing algorithms use integrated expression for cell type assignment 10,[13][14][15][16]20,21 . This simplification has major benefits in generalization, computational efficiency, and interoperability for algorithm developers, and has been the natural choice in the absence of viable alternatives.…”

Section: Introductionmentioning

confidence: 99%

Automated classification of cellular expression in multiplexed imaging data with Nimbus

Rumberger,

Greenwald,

Ranek

et al. 2024

Preprint

View full text Add to dashboard Cite

Multiplexed imaging offers a powerful approach to characterize the spatial topography of tissues in both health and disease. To analyze such data, the specific combination of markers that are present in each cell must be enumerated to enable accurate phenotyping, a process that often relies on unsupervised clustering. We constructed the Pan-Multiplex (Pan-M) dataset containing 197 million distinct annotations of marker expression across 15 different cell types. We used Pan-M to create Nimbus, a deep learning model to predict marker positivity from multiplexed image data. Nimbus is a pre-trained model that uses the underlying images to classify marker expression across distinct cell types, from different tissues, acquired using different microscope platforms, without requiring any retraining. We demonstrate that Nimbus predictions capture the underlying staining patterns of the full diversity of markers present in Pan-M. We then show how Nimbus predictions can be integrated with downstream clustering algorithms to robustly identify cell subtypes in image data. We have open-sourced Nimbus and Pan-M to enable community use athttps://github.com/angelolab/Nimbus-Inference.

show abstract

“…Thus, most tiles of the cHL MIBI dataset are composed of multiple stitched adjacent FOVs. Within each tile, the inter-FOV signal level difference and boundary effects were corrected with a series of publicly available scripts as previously described (21, 77).…”

Section: Methodsmentioning

confidence: 99%

Epstein-Barr Virus Orchestrates Spatial Reorganization and Immunomodulation within the Classic Hodgkin Lymphoma Tumor Microenvironment

Yeo,

Qiu,

Bai

et al. 2024

Preprint

Self Cite

View full text Add to dashboard Cite

Classic Hodgkin Lymphoma (cHL) is a tumor composed of rare malignant Hodgkin and Reed-Sternberg (HRS) cells nested within a T-cell rich inflammatory immune infiltrate. cHL is associated with Epstein-Barr Virus (EBV) in ~25% of cases. The specific contributions of EBV to the pathogenesis of cHL remain largely unknown, in part due to technical barriers in dissecting the tumor microenvironment (TME) in high detail. Herein, we applied multiplexed ion beam imaging (MIBI) spatial proteomics on 6 EBV- positive and 14 EBV-negative cHL samples. We identify key TME features that distinguish between EBV-positive and EBV-negative cHL, including the relative predominance of memory CD8 T cells and increased T-cell dysfunction as a function of spatial proximity to HRS cells. Building upon a larger multi-institutional cohort of 22 EBV-positive and 24 EBV-negative cHL samples, we orthogonally validated our findings through a spatial multi-omics approach, coupling whole transcriptome capture with antibody-defined cell types for tumor and T-cell populations within the cHL TME. We delineate contrasting transcriptomic immunological signatures between EBV- positive and EBV-negative cases that differently impact HRS cell proliferation, tumor- immune interactions, and mechanisms of T-cell dysregulation and dysfunction. Our multi-modal framework enabled a comprehensive dissection of EBV-linked reorganization and immune evasion within the cHL TME, and highlighted the need to elucidate the cellular and molecular factors of virus-associated tumors, with potential for targeted therapeutic strategies.

show abstract

MAPS: Pathologist-level cell type annotation from tissue images through machine learning

Cited by 5 publications

References 24 publications

Spatial Morphoproteomic Features Predict Uniqueness of Immune Microarchitectures and Responses in Lymphoid Follicles

Spatial Morphoproteomic Features Predict Uniqueness of Immune Microarchitectures and Responses in Lymphoid Follicles

Automated classification of cellular expression in multiplexed imaging data with Nimbus

Epstein-Barr Virus Orchestrates Spatial Reorganization and Immunomodulation within the Classic Hodgkin Lymphoma Tumor Microenvironment

Contact Info

Product

Resources

About