Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Home
From Prediction To Interpretation In Computational Pathology.

Home
From Prediction To Interpretation In Computational Pathology.

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

Combined acetaldehyde metabolism burden modifies IBD susceptibility to alcohol consumption.

Gut·2026

Same author

Mortality, cardiovascular disease, and cancer in coeliac disease and dermatitis herpetiformis: a matched cohort study.

Lancet regional health. Americas·2026

Same author

Microscopic colitis and primary sclerosing cholangitis are bidirectionally associated: A nationwide matched cohort and case-control study.

Journal of internal medicine·2026

Same author

Integrated metabolomics and genetic analyses reveal loss of protective docosahexaenoic acid as a key driver linking ultra-processed food to Crohn's disease risk.

medRxiv : the preprint server for health sciences·2026

Same author

Long-term risk of acute pancreatitis in patients with celiac disease: A nationwide population-based cohort study.

Journal of internal medicine·2026

Same author

Melan-Dx: a knowledge-enhanced vision-language framework improves differential diagnosis of melanocytic neoplasm pathology.

NPJ digital medicine·2026

Same journal

Intratumoral B cells under stress.

Cancer cell·2026

Same journal

Chronic stress unleashes an intratumor phage-fibroblast-B cell circuit to promote tumor growth.

Cancer cell·2026

Same journal

Molecular phenotypes and spatial archetypes: A new framework for cancer-associated fibroblasts.

Cancer cell·2026

Same journal

OpenIO: An open framework for AI-native immunotherapy.

Cancer cell·2026

Same journal

Targeting drug-tolerant persister cells: Let's bring on the TROPs!

Cancer cell·2026

Same journal

Macrophage-mediated brain-bone marrow crosstalk promotes chronic stress-induced glioma growth.

Cancer cell·2026

See all related articles

Related Experiment Video

Constructing and Visualizing Models using Mime-based Machine-learning Framework

Constructing and Visualizing Models using Mime-based Machine-learning Framework

Published on: July 22, 2025

From prediction to interpretation in computational pathology.

Jialu Yao¹, Zhi Huang²

¹Department of Electrical and Systems Engineering, University of Pennsylvania, Philadelphia, PA 19104, USA.

|June 25, 2026

View abstract on PubMed

Summary

This summary is machine-generated.

PathPrism offers interpretable spatial tissue analysis from histopathology slides. This computational pathology framework aids biomarker discovery and clinical prediction, moving beyond black-box models.

More Related Videos

In Vivo Functional Study of Disease-associated Rare Human Variants Using Drosophila

In Vivo Functional Study of Disease-associated Rare Human Variants Using Drosophila

Published on: August 20, 2019

Related Experiment Videos

Constructing and Visualizing Models using Mime-based Machine-learning Framework

Constructing and Visualizing Models using Mime-based Machine-learning Framework

Published on: July 22, 2025

In Vivo Functional Study of Disease-associated Rare Human Variants Using Drosophila

In Vivo Functional Study of Disease-associated Rare Human Variants Using Drosophila

Published on: August 20, 2019

Area of Science:

Computational pathology
Histopathology
Biomedical imaging analysis

Background:

Computational pathology has largely relied on 'black-box' predictive models.
Interpretable models are needed for deeper biological insights and clinical translation.

Purpose of the Study:

To introduce PathPrism, a novel computational framework for analyzing histopathology slides.
To demonstrate PathPrism's utility in biomarker discovery, clinical prediction, and hypothesis generation.
To showcase a shift towards interpretable methods in computational pathology.

Main Methods:

Development of PathPrism, a framework generating interpretable spatial representations of tissue organization.
Application of PathPrism to routine histopathology slides.

Main Results:

PathPrism enables the extraction of biologically meaningful information from tissue structures.
The framework supports identification of potential biomarkers and improves clinical prediction accuracy.
Spatial representations facilitate hypothesis generation for further research.

Conclusions:

PathPrism represents a significant advancement in computational pathology, emphasizing interpretability.
Interpretable spatial analysis of histopathology slides can enhance biomarker discovery and clinical decision-making.
The framework supports a transition towards more transparent and biologically relevant computational pathology tools.