CellSighter: a neural network to classify cells in highly multiplexed images

Amitay, Yael; Bussi, Yuval; Feinstein, Ben; Bagon, Shai; Milo, Idan; Keren, Leeat

doi:10.1038/s41467-023-40066-7

Cited by 32 publications

(14 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We sought next to demonstrate real world practicality of MAPS, and its performance against other state-of-the-art approaches, ASTIR 14 and CellSighter 16 . We collected and annotated in-house data from (1) MIBI on cHL using a first cohort (cHL 1; 1669853 cells), (2) MIBI on cHL using a second cohort (cHL 2; 192795 cells), and (3) CODEX on cHL (145161 cells).…”

Section: Resultsmentioning

confidence: 99%

“…The CellSighter is a deep learning based supervised cell classification method 16 . Unlike ASTIR and the proposed method which works on cell expression matrices, CellSighter takes image, cell segmentation mask, and cell to class mapping as input.…”

Section: Methodsmentioning

confidence: 99%

“…Therefore, there is a need for scalable computational methods that can accurately classify cells from spatial proteomics data. Promising automated approaches developed recently include probabilistic inferential approaches 14 , 15 , and convolutional neural networks 16 , 17 . Geuenich et al introduced ASTIR, an automated method for assigning cell identities using single-cell multiplexed imaging data.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

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

Shaban,

Bai,

Qiu

et al. 2024

Nat Commun

View full text Add to dashboard Cite

Highly multiplexed protein imaging is emerging as a potent technique for analyzing protein distribution within cells and tissues in their native context. However, existing cell annotation methods utilizing high-plex spatial proteomics data are resource intensive and necessitate iterative expert input, thereby constraining their scalability and practicality for extensive datasets. We introduce MAPS (Machine learning for Analysis of Proteomics in Spatial biology), a machine learning approach facilitating rapid and precise cell type identification with human-level accuracy from spatial proteomics data. Validated on multiple in-house and publicly available MIBI and CODEX datasets, MAPS outperforms current annotation techniques in terms of speed and accuracy, achieving pathologist-level precision even for typically challenging cell types, including tumor cells of immune origin. By democratizing rapidly deployable and scalable machine learning annotation, MAPS holds significant potential to expedite advances in tissue biology and disease comprehension.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

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

Shaban,

Bai,

Qiu

et al. 2024

Nat Commun

View full text Add to dashboard Cite

show abstract

“…Supervised classification of cells in highly multiplexed images can be particularly difficult because image annotations are both difficult to acquire and specific to the staining panel used for the imaging experiment [34]. Therefore, models trained for cell classification in high-plex images are not typically generalizable to new datasets [35]. Additionally, identification of rare cell types is also problematic because they or often not represented in training data.…”

Section: Discussionmentioning

confidence: 99%

Pseudo-spectral angle mapping for automated pixel-level analysis of highly multiplexed tissue image data

Durkee,

Ai,

Casella

et al. 2024

Preprint

View full text Add to dashboard Cite

The rapid development of highly multiplexed microscopy systems has enabled the study of cells embedded within their native tissue, which is providing exciting insights into the spatial features of human disease [1]. However, computational methods for analyzing these high-content images are still emerging, and there is a need for more robust and generalizable tools for evaluating the cellular constituents and underlying stroma captured by high-plex imaging [2]. To address this need, we have adapted spectral angle mapping – an algorithm used widely in hyperspectral image analysis – to compress the channel dimension of high-plex immunofluorescence images. As many high-plex immunofluorescence imaging experiments probe unique sets of protein markers, existing cell and pixel classification models do not typically generalize well. Pseudospectral angle mapping (pSAM) uses reference pseudospectra – or pixel vectors – to assign each pixel in an image a similarity score to several cell class reference vectors, which are defined by each unique staining panel. Here, we demonstrate that the class maps provided by pSAM can directly provide insight into the prevalence of each class defined by reference pseudospectra. In a dataset of high-plex images of colon biopsies from patients with gut autoimmune conditions, sixteen pSAM class representation maps were combined with instance segmentation of cells to provide cell class predictions. Finally, pSAM detected a diverse set of structure and immune cells when applied to a novel dataset of kidney biopsies imaged with a 43-marker panel. In summary, pSAM provides a powerful and readily generalizable method for evaluating high-plex immunofluorescence image data.Significance StatementUnderstanding the cellular constituents captured by highly multiplexed tissue imaging is a major limitation affecting the usability of these novel imaging methods. Many imaging experiments have uniquely designed staining panels, reducing the generalizability of cell classification models to new datasets. We present pseudospectral angle mapping (pSAM), which can compress high-dimensional image data into class representations. We demonstrate that the class representations generated by pSAM can be used to interpret high-plex image data and guide cell classification. Importantly, we also demonstrate that pSAM can generalize to new image datasets—collected with a different staining panel in samples from different tissues—without manual image annotation, subjective intensity gating, or re-training an algorithm.

show abstract

“…While accurate cell segmentation is crucial for further brain mapping analysis at the cellular level, further quantification and identification are also essential in following connecto-informatics analysis. CellProfiler [ 104 ], an early software widely used for cell phenotype identification, and newer tools such as CellCognition and CellSighter, use deep learn and unsupervised learning to automate the analysis of cell based on their phenotypes [ 105 , 106 ]. Another algorithm demonstrated the accurate classification of cells by their phenotypes in a mixed cell population image with high accuracy [ 107 ].…”

Section: Mapping Brain Connectivity Through Feature Extractionmentioning

confidence: 99%

Connecto-informatics at the mesoscale: current advances in image processing and analysis for mapping the brain connectivity

Choi,

Feng,

Jeong

et al. 2024

Brain Inf.

View full text Add to dashboard Cite

Mapping neural connections within the brain has been a fundamental goal in neuroscience to understand better its functions and changes that follow aging and diseases. Developments in imaging technology, such as microscopy and labeling tools, have allowed researchers to visualize this connectivity through high-resolution brain-wide imaging. With this, image processing and analysis have become more crucial. However, despite the wealth of neural images generated, access to an integrated image processing and analysis pipeline to process these data is challenging due to scattered information on available tools and methods. To map the neural connections, registration to atlases and feature extraction through segmentation and signal detection are necessary. In this review, our goal is to provide an updated overview of recent advances in these image-processing methods, with a particular focus on fluorescent images of the mouse brain. Our goal is to outline a pathway toward an integrated image-processing pipeline tailored for connecto-informatics. An integrated workflow of these image processing will facilitate researchers’ approach to mapping brain connectivity to better understand complex brain networks and their underlying brain functions. By highlighting the image-processing tools available for fluroscent imaging of the mouse brain, this review will contribute to a deeper grasp of connecto-informatics, paving the way for better comprehension of brain connectivity and its implications.

show abstract

CellSighter: a neural network to classify cells in highly multiplexed images

Cited by 32 publications

References 54 publications

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

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

Pseudo-spectral angle mapping for automated pixel-level analysis of highly multiplexed tissue image data

Connecto-informatics at the mesoscale: current advances in image processing and analysis for mapping the brain connectivity

Contact Info

Product

Resources

About