Deep Gaussian Process with Uncertainty Estimation for Microsatellite Instability and Immunotherapy Response Prediction Based on Histology DOI Open Access
Sunho Park,

Mark Pettigrew,

Yoon Jin

et al.

bioRxiv (Cold Spring Harbor Laboratory), Journal Year: 2024, Volume and Issue: unknown

Published: Nov. 3, 2024

Abstract Determining tumor microsatellite status has significant clinical value because tumors that are instability-high (MSI-H) or mismatch repair deficient (dMMR) respond well to immune check-point inhibitors (ICIs) and oftentimes not chemotherapeutics. We propose MSI-SEER, a deep Gaussian process-based Bayesian model analyzes H&E whole-slide images in weakly-supervised-learning predict gastric colorectal cancers. performed extensive validation using multiple large datasets comprised of patients from diverse racial backgrounds. MSI-SEER achieved state-of-the-art performance with MSI prediction, which was by integrating uncertainty prediction. high accuracy for predicting ICI responsiveness combining stroma-to-tumor ratio. Finally, MSI-SEER’s tile-level predictions revealed novel insights into the role spatial distribution MSI-H regions microenvironment response.

Language: Английский

Artificial Intelligence in Gastrointestinal Cancer Research: Image Learning Advances and Applications DOI Creative Commons
Shengyuan Zhou, Yi Xie,

Xujiao Feng

et al.

Cancer Letters, Journal Year: 2025, Volume and Issue: 614, P. 217555 - 217555

Published: Feb. 12, 2025

Language: Английский

Citations

2
From whole-slide image to biomarker prediction: end-to-end weakly supervised deep learning in computational pathology DOI
Omar S.M. El Nahhas,

Marko van Treeck,

Georg Wölflein

et al.

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

Published: Sept. 16, 2024

Language: Английский

Citations

9
Collaborative learning DOI

Lucia Innocenti,

Michela Antonelli, Sébastien Ourselin

et al.

Elsevier eBooks, Journal Year: 2025, Volume and Issue: unknown, P. 427 - 440

Published: Jan. 1, 2025

Language: Английский

Citations

1
The artificial intelligence revolution in gastric cancer management: clinical applications DOI Creative Commons
Runze Li,

Jingfan Li,

Yuman Wang

et al.

Cancer Cell International, Journal Year: 2025, Volume and Issue: 25(1)

Published: March 21, 2025

Nowadays, gastric cancer has become a significant issue in the global burden, and its impact cannot be ignored. The rapid development of artificial intelligence technology is attempting to address this situation, aiming change clinical management landscape fundamentally. In transformative change, machine learning deep learning, as two core technologies, play pivotal role, bringing unprecedented innovations breakthroughs diagnosis, treatment, prognosis evaluation cancer. This article comprehensively reviews latest research status application algorithms cancer, covering multiple dimensions such image recognition, pathological analysis, personalized risk assessment. These applications not only significantly improve sensitivity monitoring, accuracy precision survival but also provide robust data support scientific basis for decision-making. integration intelligence, from optimizing diagnosis process enhancing diagnostic efficiency promoting practice medicine, demonstrates promising prospects reshaping treatment model Although most current AI-based models have been widely used practice, with continuous deepening expansion we reason believe that new era AI-driven care approaching.

Language: Английский

Citations

0
The current landscape of artificial intelligence in computational histopathology for cancer diagnosis DOI Creative Commons
Aaditya Tiwari, Aruni Ghose,

Maryam Hasanova

et al.

Discover Oncology, Journal Year: 2025, Volume and Issue: 16(1)

Published: April 1, 2025

Artificial intelligence (AI) marks a frontier in histopathologic analysis shift towards the clinic, becoming mainstream choice to interpret histological images. Surveying studies assessing AI applications histopathology from 2013 2024, we review key methods (including supervised, unsupervised, weakly supervised and transfer learning) deep learning-based pattern recognition computational for diagnostic prognostic purposes. Deep learning also showed utility identifying wide range of genetic mutations standard pathology biomarkers routine histology. This survey 41 primary encompasses regions applicability multi-cancer while marking prospects introduce into clinical setting with examples including Swarm Learning Data Fusion.

Language: Английский

Citations

0
Beyond Biomarkers: Machine Learning-Driven Multiomics for Personalized Medicine in Gastric Cancer DOI Open Access
J. Daniel,

Canfeng Fan,

Tomoya Sano

et al.

Journal of Personalized Medicine, Journal Year: 2025, Volume and Issue: 15(5), P. 166 - 166

Published: April 24, 2025

Gastric cancer (GC) remains one of the leading causes cancer-related mortality worldwide, with most cases diagnosed at advanced stages. Traditional biomarkers provide only partial insights into GC’s heterogeneity. Recent advances in machine learning (ML)-driven multiomics technologies, including genomics, epigenomics, transcriptomics, proteomics, metabolomics, pathomics, and radiomics, have facilitated a deeper understanding GC by integrating molecular imaging data. In this review, we summarize current landscape ML-based integration for GC, highlighting its role precision diagnosis, prognosis prediction, biomarker discovery achieving personalized medicine.

Language: Английский

Citations

0
SwarmMAP: Swarm Learning for Decentralized Cell Type Annotation in Single Cell Sequencing Data DOI Creative Commons
Oliver Lester Saldanha,

Vivien Goepp,

Kathy Pfeiffer

et al.

bioRxiv (Cold Spring Harbor Laboratory), Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 16, 2025

Rapid technological advancements have made it possible to generate single-cell data at a large scale. Several laboratories around the world can now transcriptomic from different tissues. Unsupervised clustering, followed by annotation of cell type identified clusters, is crucial step in analyses. However, there no consensus on marker genes use for annotation, and celltype currently mostly done manual inspection genes, which irreproducible, poorly scalable. Additionally, patient-privacy also critical issue with human datasets. There need standardize automate across datasets privacy-preserving manner. Here, we developed SwarmMAP that uses Swarm Learning train machine learning models cell-type classification based sequencing decentralized way. does not require any exchange raw between centers. has F1-score 0.93, 0.98, 0.88 heart, lung, breast datasets, respectively. Learning-based yield an average performance 0.907 par achieved trained centralized ( p -val= 0.937 , Mann-Whitney U Test). We find increasing number increases prediction accuracy enables handling higher diversity. Together, these findings demonstrate viable approach annotation. available https://github.com/hayatlab/SwarmMAP .

Language: Английский

Citations

0
An ensemble approach of deep CNN models with Beta normalization aggregation for gastrointestinal disease detection DOI

Zafran Waheed,

Jinsong Gui,

Kamran Amjad

et al.

Biomedical Signal Processing and Control, Journal Year: 2025, Volume and Issue: 105, P. 107567 - 107567

Published: Feb. 4, 2025

Language: Английский

Citations

0
Swarm learning with weak supervision enables automatic breast cancer detection in magnetic resonance imaging DOI Creative Commons
Oliver Lester Saldanha, Jiefu Zhu, Gustav Müller‐Franzes

et al.

Communications Medicine, Journal Year: 2025, Volume and Issue: 5(1)

Published: Feb. 6, 2025

Language: Английский

Citations

0
Targeting amino acid metabolism to inhibit gastric cancer progression and promote anti-tumor immunity: a review DOI Creative Commons

Yuchun Jiang,

Tao Qing,

Xuehan Qiao

et al.

Frontiers in Immunology, Journal Year: 2025, Volume and Issue: 16

Published: Feb. 13, 2025

The incidence of gastric cancer remains high and poses a serious threat to human health. Recent comprehensive investigations into amino acid metabolism immune system components within the tumor microenvironment have elucidated functional interactions between cells, metabolism. This study reviews characteristics in cancer, with particular focus on methionine, cysteine, glutamic acid, serine, taurine, other acids. It discusses relationship these metabolic processes, development, body’s anti-tumor immunity, analyzes importance targeting for chemotherapy immunotherapy.

Language: Английский

Citations

0