Multimodal recurrence risk prediction model for HR+/HER2- early breast cancer following adjuvant chemo-endocrine therapy: integrating pathology image and clinicalpathological features DOI Creative Commons
Xiaoyan Wu, Yiman Li, Ji‐Long Chen

et al.

Breast Cancer Research, Journal Year: 2025, Volume and Issue: 27(1)

Published: March 28, 2025

Language: Английский

A vision–language foundation model for precision oncology DOI
Jinxi Xiang, Xiyue Wang, Xiaoming Zhang

et al.

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

Published: Jan. 8, 2025

Language: Английский

Citations

9

When multiple instance learning meets foundation models: Advancing histological whole slide image analysis DOI

Hongming Xu,

Mingkang Wang,

Duan‐Bo Shi

et al.

Medical Image Analysis, Journal Year: 2025, Volume and Issue: 101, P. 103456 - 103456

Published: Jan. 14, 2025

Language: Английский

Citations

3

Validation of histopathology foundation models through whole slide image retrieval DOI Creative Commons
Saghir Alfasly,

Ghazal Alabtah,

Sobhan Hemati

et al.

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: Feb. 1, 2025

We evaluated several foundation models in histopathology for image retrieval using a zero-shot approach. These generated embeddings that were directly employed without additional fine-tuning. Our experiments conducted on diagnostic slides from The Cancer Genome Atlas (TCGA), which covers 23 organs and 117 cancer subtypes. used Yottixel as the framework whole-slide (WSI) via patch-based embeddings. Retrieval performance was macro-averaged F1 scores top-1, top-3, top-5 retrievals. indicated varying levels of performance: Yottixel-DenseNet (27% ± 13%), Yottixel-UNI (42% 14%), Yottixel-Virchow (40% Yottixel-GigaPath (41% GigaPath WSI 14%). results demonstrate potential limitations retrieval, underscoring need further advancements embedding techniques.

Language: Английский

Citations

2

Artificial intelligence for medicine 2025: Navigating the endless frontier DOI
Jiyan Dai, Huiyu Xu, Tao Chen

et al.

The Innovation Medicine, Journal Year: 2025, Volume and Issue: unknown, P. 100120 - 100120

Published: Jan. 1, 2025

<p>Artificial intelligence (AI) is driving transformative changes in the field of medicine, with its successful application relying on accurate data and rigorous quality standards. By integrating clinical information, pathology, medical imaging, physiological signals, omics data, AI significantly enhances precision research into disease mechanisms patient prognoses. technologies also demonstrate exceptional potential drug development, surgical automation, brain-computer interface (BCI) research. Through simulation biological systems prediction intervention outcomes, enables researchers to rapidly translate innovations practical applications. While challenges such as computational demands, software ethical considerations persist, future remains highly promising. plays a pivotal role addressing societal issues like low birth rates aging populations. can contribute mitigating rate through enhanced ovarian reserve evaluation, menopause forecasting, optimization Assisted Reproductive Technologies (ART), sperm analysis selection, endometrial receptivity fertility remote consultations. In posed by an population, facilitate development dementia models, cognitive health monitoring strategies, early screening systems, AI-driven telemedicine platforms, intelligent smart companion robots, environments for aging-in-place. profoundly shapes medicine.</p>

Language: Английский

Citations

2

Exploring scalable medical image encoders beyond text supervision DOI
Fernando Pérez‐García, Harshita Sharma, Sam Bond-Taylor

et al.

Nature Machine Intelligence, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 13, 2025

Language: Английский

Citations

2

Unraveling complexity and leveraging opportunities in uncommon breast cancer subtypes DOI Creative Commons
Fresia Pareja, Rohit Bhargava, Virginia F. Borges

et al.

npj Breast Cancer, Journal Year: 2025, Volume and Issue: 11(1)

Published: Jan. 24, 2025

Special histologic subtypes of breast cancer (BC) exhibit unique phenotypes and molecular profiles with diagnostic therapeutic implications, often differing in behavior clinical trajectory from common BC forms. Novel methodologies, such as artificial intelligence may improve classification. Genetic predisposition plays roles a subset cases. Uncommon presentations like male, inflammatory pregnancy-related pose challenges. Emerging strategies targeting genetic alterations or immune microenvironment are being explored.

Language: Английский

Citations

1

Unlocking the potential of digital pathology: Novel baselines for compression DOI Creative Commons
Maximilian Fischer, Peter Neher, Peter J. Schüffler

et al.

Journal of Pathology Informatics, Journal Year: 2025, Volume and Issue: unknown, P. 100421 - 100421

Published: Jan. 1, 2025

Language: Английский

Citations

1

A comprehensive evaluation of histopathology foundation models for ovarian cancer subtype classification DOI Creative Commons
Jack Breen, Katrina J. Allen, Kieran Zucker

et al.

npj Precision Oncology, Journal Year: 2025, Volume and Issue: 9(1)

Published: Jan. 30, 2025

Language: Английский

Citations

1

Artificial intelligence in digital pathology — time for a reality check DOI
Arpit Aggarwal, Satvika Bharadwaj, Germán Corredor

et al.

Nature Reviews Clinical Oncology, Journal Year: 2025, Volume and Issue: unknown

Published: Feb. 11, 2025

Language: Английский

Citations

1

General lightweight framework for vision foundation model supporting multi-task and multi-center medical image analysis DOI Creative Commons

Senliang Lu,

Yehang Chen, Yuan Chen

et al.

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

Published: March 1, 2025

Abstract The foundation model, trained on extensive and diverse datasets, has shown strong performance across numerous downstream tasks. Nevertheless, its application in the medical domain is significantly hindered by issues such as data volume, heterogeneity, privacy concerns. Therefore, we propose Vision Foundation Model General Lightweight (VFMGL) framework, which facilitates decentralized construction of expert clinical models for various VFMGL framework transfers general knowledge from large-parameter vision to construct lightweight, robust tailored specific Through experiments analyses a range tasks scenarios, demonstrate that achieves superior both image classification segmentation tasks, effectively managing challenges posed heterogeneity. These results underscore potential advancing efficacy reliability AI-driven diagnostics.

Language: Английский

Citations

1