Recommendations on compiling test datasets for evaluating artificial intelligence solutions in pathology DOI Creative Commons
André Homeyer, Christian Geißler, Lars Ole Schwen

et al.

Modern Pathology, Journal Year: 2022, Volume and Issue: 35(12), P. 1759 - 1769

Published: Sept. 10, 2022

Artificial intelligence (AI) solutions that automatically extract information from digital histology images have shown great promise for improving pathological diagnosis. Prior to routine use, it is important evaluate their predictive performance and obtain regulatory approval. This assessment requires appropriate test datasets. However, compiling such datasets challenging specific recommendations are missing. A committee of various stakeholders, including commercial AI developers, pathologists, researchers, discussed key aspects conducted extensive literature reviews on in pathology. Here, we summarize the results derive general We address several questions: Which how many needed? How deal with low-prevalence subsets? can potential bias be detected? should reported? What requirements different countries? The intended help developers demonstrate utility products pathologists agencies verify reported measures. Further research needed formulate criteria sufficiently representative so operate less user intervention better support diagnostic workflows future.

Language: Английский

Artificial intelligence for multimodal data integration in oncology DOI Creative Commons
Jana Lipková, Richard J. Chen, Bowen Chen

et al.

Cancer Cell, Journal Year: 2022, Volume and Issue: 40(10), P. 1095 - 1110

Published: Oct. 1, 2022

In oncology, the patient state is characterized by a whole spectrum of modalities, ranging from radiology, histology, and genomics to electronic health records. Current artificial intelligence (AI) models operate mainly in realm single modality, neglecting broader clinical context, which inevitably diminishes their potential. Integration different data modalities provides opportunities increase robustness accuracy diagnostic prognostic models, bringing AI closer practice. are also capable discovering novel patterns within across suitable for explaining differences outcomes or treatment resistance. The insights gleaned such can guide exploration studies contribute discovery biomarkers therapeutic targets. To support these advances, here we present synopsis methods strategies multimodal fusion association discovery. We outline approaches interpretability directions AI-driven through interconnections. examine challenges adoption discuss emerging solutions.

Language: Английский

Citations

342
Towards a general-purpose foundation model for computational pathology DOI
Richard J. Chen, Tong Ding, Ming Y. Lu

et al.

Nature Medicine, Journal Year: 2024, Volume and Issue: 30(3), P. 850 - 862

Published: March 1, 2024

Language: Английский

Citations

220
The 2022 World Health Organization Classification of Tumors of the Urinary System and Male Genital Organs—Part B: Prostate and Urinary Tract Tumors DOI
George J. Netto, Mahul B. Amin, Daniel M. Berney

et al.

European Urology, Journal Year: 2022, Volume and Issue: 82(5), P. 469 - 482

Published: Aug. 11, 2022

Language: Английский

Citations

187
Deep learning-enabled virtual histological staining of biological samples DOI Creative Commons
Bijie Bai, Xilin Yang, Yuzhu Li

et al.

Light Science & Applications, Journal Year: 2023, Volume and Issue: 12(1)

Published: March 3, 2023

Histological staining is the gold standard for tissue examination in clinical pathology and life-science research, which visualizes cellular structures using chromatic dyes or fluorescence labels to aid microscopic assessment of tissue. However, current histological workflow requires tedious sample preparation steps, specialized laboratory infrastructure, trained histotechnologists, making it expensive, time-consuming, not accessible resource-limited settings. Deep learning techniques created new opportunities revolutionize methods by digitally generating stains neural networks, providing rapid, cost-effective, accurate alternatives chemical methods. These techniques, broadly referred as virtual staining, were extensively explored multiple research groups demonstrated be successful various types from label-free images unstained samples; similar approaches also used transforming an already stained into another type stain, performing stain-to-stain transformations. In this Review, we provide a comprehensive overview recent advances deep learning-enabled techniques. The basic concepts typical are introduced, followed discussion representative works their technical innovations. We share our perspectives on future emerging field, aiming inspire readers diverse scientific fields further expand scope applications.

Language: Английский

Citations

157
A visual-language foundation model for computational pathology DOI
Ming Y. Lu, Bowen Chen, Drew F. K. Williamson

et al.

Nature Medicine, Journal Year: 2024, Volume and Issue: 30(3), P. 863 - 874

Published: March 1, 2024

Language: Английский

Citations

142
Demystifying Supervised Learning in Healthcare 4.0: A New Reality of Transforming Diagnostic Medicine DOI Creative Commons
Sudipta Roy, Tanushree Meena, Se‐Jung Lim

et al.

Diagnostics, Journal Year: 2022, Volume and Issue: 12(10), P. 2549 - 2549

Published: Oct. 20, 2022

The global healthcare sector continues to grow rapidly and is reflected as one of the fastest-growing sectors in fourth industrial revolution (4.0). majority industry still uses labor-intensive, time-consuming, error-prone traditional, manual, manpower-based methods. This review addresses current paradigm, potential for new scientific discoveries, technological state preparation, supervised machine learning (SML) prospects various sectors, ethical issues. effectiveness innovation disease diagnosis, personalized medicine, clinical trials, non-invasive image analysis, drug discovery, patient care services, remote monitoring, hospital data, nanotechnology learning-based automation along with requirement explainable artificial intelligence (AI) are evaluated. In order understand architecture treatment, a thorough study medical imaging analysis from technical point view presented. also represents thinking developments that will push boundaries increase opportunity through AI SML near future. Nowadays, SML-based applications require lot data quality awareness data-heavy, knowledge management paramount. biomedical needs skills, consciousness data-intensive study, knowledge-centric health system. As result, merits, demerits, precautions need take ethics other effects into consideration. overall insight this paper help researchers academia address future research be discussed on sectors.

Language: Английский

Citations

108
Artificial intelligence for digital and computational pathology DOI
Andrew H. Song, Guillaume Jaume, Drew F. K. Williamson

et al.

Nature Reviews Bioengineering, Journal Year: 2023, Volume and Issue: 1(12), P. 930 - 949

Published: Oct. 2, 2023

Language: Английский

Citations

92
A Multimodal Generative AI Copilot for Human Pathology DOI Creative Commons
Ming Y. Lu, Bowen Chen, Drew F. K. Williamson

et al.

Nature, Journal Year: 2024, Volume and Issue: unknown

Published: June 12, 2024

Computational pathology

Language: Английский

Citations

87
The promise of digital healthcare technologies DOI Creative Commons
Andy Wai Kan Yeung, Ali Torkamani, Atul J. Butte

et al.

Frontiers in Public Health, Journal Year: 2023, Volume and Issue: 11

Published: Sept. 26, 2023

Digital health technologies have been in use for many years a wide spectrum of healthcare scenarios. This narrative review outlines the current and future strategies significance digital modern applications. It covers state scientific field (delineating major strengths, limitations, applications) envisions impact relevant emerging key technologies. Furthermore, we attempt to provide recommendations innovative approaches that would accelerate benefit research, translation utilization

Language: Английский

Citations

81
Benchmarking Self-Supervised Learning on Diverse Pathology Datasets DOI
Mingu Kang,

Heon Song,

Seonwook Park

et al.

2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Journal Year: 2023, Volume and Issue: unknown, P. 3344 - 3354

Published: June 1, 2023

Computational pathology can lead to saving human lives, but models are annotation hungry and images notoriously expensive annotate. Self-supervised learning (SSL) has shown be an effective method for utilizing unlabeled data, its application could greatly benefit downstream tasks. Yet, there no principled studies that compare SSL methods discuss how adapt them pathology. To address this need, we execute the largest-scale study of pre-training on image date. Our is conducted using 4 representative diverse We establish large-scale domain-aligned in consistently out-performs ImageNet standard settings such as linear fine-tuning evaluations, well low-label regimes. Moreover, propose a set domain-specific techniques experimentally show leads performance boost. Lastly, first time, apply challenging task nuclei instance segmentation large consistent improvements. release pre-trained model weights 1 https://lunit-io.github.io/research/publications/pathology_ssl.

Language: Английский

Citations

79