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 Experiment Video

Updated: Jun 13, 2026

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data
14:27

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data

Published on: June 26, 2013

Spatial biomarker discovery via interpretable semantic learning in histopathology.

Junhao Liang1, Xiaofeng Jiang2, Nic Gabriel Reitsam3

  • 1Else Kroener Fresenius Center for Digital Health, Faculty of Medicine, TUD Dresden University of Technology, Dresden, Germany; State Key Laboratory of Precision Measurement Technology and Instruments, Department of Precision Instrument, Tsinghua University, Beijing 100084, China.

Cancer Cell
|June 11, 2026
PubMed

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

Early-onset colorectal cancer across Europe: Burden, mechanisms, and health-system implications.

European journal of cancer (Oxford, England : 1990)·2026
Same author

A deep learning framework for efficient pathology image analysis.

Nature communications·2026
Same author

Evaluating statistical models for overdispersed multi-omics data: a multiplex immunofluorescence case study.

American journal of epidemiology·2026
Same author

Site- and age-dependent associations between Fusobacterium nucleatum and colorectal cancer mortality.

Cancer·2026
Same author

KRAS and BRAF mutations modify adjuvant chemotherapy outcomes in early stage colorectal cancer.

NPJ precision oncology·2026
Same author

Context-Dependent Survival Associations Between Interleukin-13 Expression and Immunotherapy in Advanced Solid Tumors.

ImmunoTargets and therapy·2026
Summary

PathPrism, an interpretable AI framework, discovers spatial biomarkers in whole-slide images for precision oncology. It enables transparent modeling of prognosis and therapy response, advancing colorectal cancer research.

Area of Science:

  • Computational pathology
  • Artificial intelligence in oncology
  • Biomarker discovery

Background:

  • Spatial biomarkers are crucial for precision oncology but difficult to discover in complex whole-slide images.
  • Existing AI models often lack interpretability, hindering clinical translation.

Purpose of the Study:

  • To develop PathPrism, an interpretable AI framework for systematic spatial biomarker discovery and virtual experimentation.
  • To enable transparent modeling of prognosis, molecular alterations, and therapy response using tissue architecture.

Main Methods:

  • PathPrism encodes whole-slide images into pathologically informed spatial features for transparent modeling.
  • Applied to 7,000 colorectal cancer patients across 11 cohorts.
  • Integrated large language models for hypothesis generation and VirtualWSI for semantic perturbation.
Keywords:
AI-driven discoveryadjuvant chemotherapycolorectal cancercomputational pathologycontrollable virtual experimentsinterpretable representationsspatial biomarkerstransparent modelingtumor microenvironment

More Related Videos

Mining Spatial Transcriptomics Datasets using DeepSpaceDB
10:16

Mining Spatial Transcriptomics Datasets using DeepSpaceDB

Published on: September 5, 2025

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping
10:25

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Published on: September 25, 2019

Related Experiment Videos

Last Updated: Jun 13, 2026

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data
14:27

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data

Published on: June 26, 2013

Mining Spatial Transcriptomics Datasets using DeepSpaceDB
10:16

Mining Spatial Transcriptomics Datasets using DeepSpaceDB

Published on: September 5, 2025

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping
10:25

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Published on: September 25, 2019

Main Results:

  • Discovered hundreds of spatial biomarkers predicting survival, MSI, BRAF, and TP53 mutations in colorectal cancer.
  • Stratified chemotherapy benefit in stage II/III colorectal cancer patients.
  • Demonstrated PathPrism's scalability and interpretability for biomarker discovery.

Conclusions:

  • PathPrism offers a scalable and interpretable AI framework for spatial biomarker discovery in oncology.
  • The framework facilitates transparent modeling and hypothesis generation, advancing precision medicine.
  • VirtualWSI enables novel spatial biomarker atlas exploration and semantic perturbation.