Application of digital pathology‐based advanced analytics of tumour microenvironment organisation to predict prognosis and therapeutic response DOI Creative Commons
Xiao Fu, Erik Sahai, Anna Wilkins

et al.

The Journal of Pathology, Journal Year: 2023, Volume and Issue: 260(5), P. 578 - 591

Published: Aug. 1, 2023

Abstract In recent years, the application of advanced analytics, especially artificial intelligence (AI), to digital H&E images, and other histological image types, has begun radically change how images are used in clinic. Alongside recognition that tumour microenvironment (TME) a profound impact on phenotype, technical development highly multiplexed immunofluorescence platforms enhanced biological complexity can be captured TME with high precision. AI an increasingly powerful role quantitation features association such clinically important outcomes, as occurs distinct stages conventional machine learning. Deep‐learning algorithms able elucidate patterns inherent input data minimum levels human and, hence, have potential achieve relevant predictions discovery features. Furthermore, diverse repertoire deep‐learning interrogate extends beyond convolutional neural networks include attention‐based models, graph networks, multimodal models. To date, models largely been evaluated retrospectively, outside well‐established rigour prospective clinical trials, part because traditional trial methodology may not always suitable for assessment technology. However, enable pathology‐based analytics meaningfully care, specific measures ‘added benefit’ current standard care validation setting important. This will need accompanied by adequate explainability interpretability. Despite challenges, combination expanding datasets, increased computational power, possibility integration pre‐clinical experimental insights into model means there is exciting future progress these applications. © 2023 The Authors. Journal Pathology published John Wiley & Sons Ltd behalf Pathological Society Great Britain Ireland.

Language: Английский

Identification and characterization of cell niches in tissue from spatial omics data at single-cell resolution DOI Creative Commons
Jingyang Qian, Xin Shao,

Hudong Bao

et al.

Nature Communications, Journal Year: 2025, Volume and Issue: 16(1)

Published: Feb. 16, 2025

Deciphering the features, structure, and functions of cell niche in tissues remains a major challenge. Here, we present scNiche, computational framework to identify characterize niches from spatial omics data at single-cell resolution. We benchmark scNiche with both simulated biological datasets, demonstrate that can effectively robustly while outperforming other existing methods. In proteomics human triple-negative breast cancer, reveals influence microenvironment on cellular phenotypes, further dissects patient-specific distinct compositions or phenotypic characteristics. By analyzing mouse liver transcriptomics across normal early-onset failure donors, uncovers disease-specific injury niches, delineates remodeling failure. Overall, enables decoding data. authors develop characterise

Language: Английский

Citations

0
Characterization of tumour heterogeneity through segmentation-free representation learning on multiplexed imaging data DOI
Jimin Tan, Hortense Le, Jiehui Deng

et al.

Nature Biomedical Engineering, Journal Year: 2025, Volume and Issue: unknown

Published: Feb. 20, 2025

Language: Английский

Citations

0
STModule: identifying tissue modules to uncover spatial components and characteristics of transcriptomic landscapes DOI Creative Commons
Ran Wang, Qian Yan, Xiaojing Guo

et al.

Genome Medicine, Journal Year: 2025, Volume and Issue: 17(1)

Published: March 3, 2025

Abstract Here we present STModule, a Bayesian method developed to identify tissue modules from spatially resolved transcriptomics that reveal spatial components and essential characteristics of tissues. STModule uncovers diverse expression signals in transcriptomic landscapes such as cancer, intraepithelial neoplasia, immune infiltration, outcome-related molecular features various cell types, which facilitate downstream analysis provide insights into tumor microenvironments, disease mechanisms, treatment development, histological organization captures broader spectrum biological compared other methods detects novel components. The characterized by gene sets demonstrate greater robustness transferability across different biopsies. STModule: https://github.com/rwang-z/STModule.git .

Language: Английский

Citations

0
Analyzing Spatial Point Patterns in Digital Pathology: Immune Cells in High-Grade Serous Ovarian Carcinomas DOI
Jonatan A. González, Julia Wrobel, Simon Vandekar

et al.

The American Statistician, Journal Year: 2025, Volume and Issue: unknown, P. 1 - 26

Published: March 28, 2025

Language: Английский

Citations

0
Application of digital pathology‐based advanced analytics of tumour microenvironment organisation to predict prognosis and therapeutic response DOI Creative Commons
Xiao Fu, Erik Sahai, Anna Wilkins

et al.

The Journal of Pathology, Journal Year: 2023, Volume and Issue: 260(5), P. 578 - 591

Published: Aug. 1, 2023

Abstract In recent years, the application of advanced analytics, especially artificial intelligence (AI), to digital H&E images, and other histological image types, has begun radically change how images are used in clinic. Alongside recognition that tumour microenvironment (TME) a profound impact on phenotype, technical development highly multiplexed immunofluorescence platforms enhanced biological complexity can be captured TME with high precision. AI an increasingly powerful role quantitation features association such clinically important outcomes, as occurs distinct stages conventional machine learning. Deep‐learning algorithms able elucidate patterns inherent input data minimum levels human and, hence, have potential achieve relevant predictions discovery features. Furthermore, diverse repertoire deep‐learning interrogate extends beyond convolutional neural networks include attention‐based models, graph networks, multimodal models. To date, models largely been evaluated retrospectively, outside well‐established rigour prospective clinical trials, part because traditional trial methodology may not always suitable for assessment technology. However, enable pathology‐based analytics meaningfully care, specific measures ‘added benefit’ current standard care validation setting important. This will need accompanied by adequate explainability interpretability. Despite challenges, combination expanding datasets, increased computational power, possibility integration pre‐clinical experimental insights into model means there is exciting future progress these applications. © 2023 The Authors. Journal Pathology published John Wiley & Sons Ltd behalf Pathological Society Great Britain Ireland.

Language: Английский

Citations

10