Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

METTL5-mediated rRNA modification controls prostate cancer progression through the IRF7/DNA2 axis and mitophagy regulation.

Oncogene·2026
Same author

Biological roles of extracellular proteins in Streptococcus mutans.

Microbiological research·2026
Same author

Adjuvant Pembrolizumab plus Belzutifan for Renal-Cell Carcinoma.

The New England journal of medicine·2026
Same author

TRIM17 downregulation modulates CRPC progression and enzalutamide resistance by derepressing BCL2 expression via the p53-dependent and p53-independent pathways.

Cell death and differentiation·2026
Same author

Stratification system with tumor-associated macrophages for predicting prognostic and therapeutic implications in clear cell renal cell carcinoma.

Journal of the National Cancer Center·2026
Same author

Consolidative therapy for PSMA-avid lesions after 3 cycles of apalutamide plus androgen deprivation in metastatic hormone-sensitive prostate cancer: A prospective phase 2 single-arm trial.

European journal of nuclear medicine and molecular imaging·2026

Related Experiment Video

Updated: Jul 31, 2025

An Orthotopic Bladder Cancer Model for Gene Delivery Studies
07:48

An Orthotopic Bladder Cancer Model for Gene Delivery Studies

Published on: December 1, 2013

12.6K

Histopathological bladder cancer gene mutation prediction with hierarchical deep multiple-instance learning.

Rui Yan1, Yijun Shen2, Xueyuan Zhang3

  • 1Institute of Computing Technology, Chinese Academy of Sciences, Beijing, 100190, China; University of Chinese Academy of Sciences, Beijing, 100049, China.

Medical Image Analysis
|May 1, 2023
PubMed
Summary

Predicting gene mutations from pathological images is now feasible. A new framework uses image analysis to identify mutations, improving upon current methods and aiding clinical diagnosis.

Keywords:
Bladder cancerContrastive learningGene mutation predictionHistopathological image analysisMultiple instance learning

More Related Videos

Induction of Invasive Transitional Cell Bladder Carcinoma in Immune Intact Human MUC1 Transgenic Mice: A Model for Immunotherapy Development
11:02

Induction of Invasive Transitional Cell Bladder Carcinoma in Immune Intact Human MUC1 Transgenic Mice: A Model for Immunotherapy Development

Published on: October 30, 2013

21.3K
Magnetic Resonance Imaging Assessment of Carcinogen-induced Murine Bladder Tumors
05:19

Magnetic Resonance Imaging Assessment of Carcinogen-induced Murine Bladder Tumors

Published on: March 29, 2019

10.4K

Related Experiment Videos

Last Updated: Jul 31, 2025

An Orthotopic Bladder Cancer Model for Gene Delivery Studies
07:48

An Orthotopic Bladder Cancer Model for Gene Delivery Studies

Published on: December 1, 2013

12.6K
Induction of Invasive Transitional Cell Bladder Carcinoma in Immune Intact Human MUC1 Transgenic Mice: A Model for Immunotherapy Development
11:02

Induction of Invasive Transitional Cell Bladder Carcinoma in Immune Intact Human MUC1 Transgenic Mice: A Model for Immunotherapy Development

Published on: October 30, 2013

21.3K
Magnetic Resonance Imaging Assessment of Carcinogen-induced Murine Bladder Tumors
05:19

Magnetic Resonance Imaging Assessment of Carcinogen-induced Murine Bladder Tumors

Published on: March 29, 2019

10.4K

Area of Science:

  • Computational pathology
  • Bioinformatics
  • Medical imaging analysis

Background:

  • Gene mutation detection traditionally relies on costly and time-consuming molecular methods.
  • Pathological images offer a ubiquitous and potentially faster alternative for mutation prediction.
  • Current image-based methods struggle with the scale of gigapixel Whole Slide Images (WSIs) and identifying specific mutated regions.

Purpose of the Study:

  • To develop an effective framework for predicting gene mutations directly from Whole Slide Images (WSIs).
  • To overcome the limitations of existing methods in identifying mutated regions within large-scale pathological images.
  • To enhance the clinical utility of gene mutation detection by leveraging readily available pathological data.

Main Methods:

  • A three-part framework was designed: supervised learning for cancerous area segmentation, contrastive learning for comprehensive cancerous patch clustering, and a hierarchical deep multi-instance learning (HDMIL) method for mutation classification.
  • HDMIL incorporates a two-stage attention mechanism to identify patches highly correlated with gene mutations, providing interpretability.
  • The framework processes gigapixel WSIs to predict gene mutations.

Main Results:

  • The proposed framework significantly outperforms existing state-of-the-art methods for WSI-based gene mutation prediction.
  • The method demonstrated successful prediction of five clinically relevant gene mutations in the TCGA bladder cancer dataset.
  • The attention mechanism in HDMIL offers interpretability, allowing pathologists to correlate gene mutations with histopathological morphology.

Conclusions:

  • The developed framework offers a powerful and efficient approach for predicting gene mutations from pathological images.
  • This method has the potential to significantly advance the clinical application of gene mutation detection.
  • The interpretability feature aids in understanding the relationship between histopathology and genetic mutations.