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

Kaplan-Meier Approach01:24

Kaplan-Meier Approach

The Kaplan-Meier estimator is a non-parametric method used to estimate the survival function from time-to-event data. In medical research, it is frequently employed to measure the proportion of patients surviving for a certain period after treatment. This estimator is fundamental in analyzing time-to-event data, making it indispensable in clinical trials, epidemiological studies, and reliability engineering. By estimating survival probabilities, researchers can evaluate treatment effectiveness,...
Cancer Survival Analysis01:21

Cancer Survival Analysis

Cancer survival analysis focuses on quantifying and interpreting the time from a key starting point, such as diagnosis or the initiation of treatment, to a specific endpoint, such as remission or death. This analysis provides critical insights into treatment effectiveness and factors that influence patient outcomes, helping to shape clinical decisions and guide prognostic evaluations. A cornerstone of oncology research, survival analysis tackles the challenges of skewed, non-normally...
Survival Tree01:19

Survival Tree

Survival trees are a non-parametric method used in survival analysis to model the relationship between a set of covariates and the time until an event of interest occurs, often referred to as the "time-to-event" or "survival time." This method is particularly useful when dealing with censored data, where the event has not occurred for some individuals by the end of the study period, or when the exact time of the event is unknown.
 Building a Survival Tree
Constructing a survival tree begins...
Comparing the Survival Analysis of Two or More Groups01:20

Comparing the Survival Analysis of Two or More Groups

Survival analysis is a cornerstone of medical research, used to evaluate the time until an event of interest occurs, such as death, disease recurrence, or recovery. Unlike standard statistical methods, survival analysis is particularly adept at handling censored data—instances where the event has not occurred for some participants by the end of the study or remains unobserved. To address these unique challenges, specialized techniques like the Kaplan-Meier estimator, log-rank test, and Cox...
Assumptions of Survival Analysis01:15

Assumptions of Survival Analysis

Survival models analyze the time until one or more events occur, such as death in biological organisms or failure in mechanical systems. These models are widely used across fields like medicine, biology, engineering, and public health to study time-to-event phenomena. To ensure accurate results, survival analysis relies on key assumptions and careful study design.

You might also read

Related Articles

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

Sort by
Same author

Multi-modal data integration reveals functionally credible predictive biomarkers in ovarian cancer.

Genome medicine·2026
Same author

Handling missing modalities in multimodal survival prediction for non-small cell lung cancer.

NPJ digital medicine·2026
Same author

PATHOS: Pathology attention framework for treatment response stratification in ovarian high-grade serous carcinomas following neoadjuvant chemotherapy on H&E images.

Journal of pathology informatics·2026
Same author

Searching for New Possible Peripheral Biomarkers of Cognitive Decline in Down Syndrome: The Role of IL-18 Pathway and its Interaction with TGF-β1 and TNF-α.

Neuromolecular medicine·2026
Same author

Modulation of Aerobic Glycolysis Genes During the Progression of Retinitis Pigmentosa.

Investigative ophthalmology & visual science·2026
Same author

Multiomic integration reveals tumoral heterogeneity of lipid dependence within lethal group 3 medulloblastoma.

Cancer cell·2026

Related Experiment Video

Updated: Jun 6, 2026

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

Practical guidelines for multiple instance learning in computational pathology: how embedding choice impacts overall

Francesca Miccolis1, Elisa Ficarra1, Marta Lovino2

  • 1Department of Engineering Enzo Ferrari, University of Modena and Reggio Emilia, Modena, Italy.

Frontiers in Bioinformatics
|June 5, 2026
PubMed
Summary

Choosing the right patch embedding is crucial for accurate cancer survival prediction using whole slide images (WSIs) with multiple instance learning (MIL). Domain-specific models significantly improve prognostic accuracy and interpretability across diverse cancer types.

Keywords:
computational pathologyfoundation modelsmultiple instance learningsurvival analysiswhole slide images

More Related Videos

Constructing and Visualizing Models using Mime-based Machine-learning Framework
06:19

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

Published on: July 22, 2025

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

Related Experiment Videos

Last Updated: Jun 6, 2026

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

Constructing and Visualizing Models using Mime-based Machine-learning Framework
06:19

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

Published on: July 22, 2025

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

Area of Science:

  • Computational pathology
  • Digital pathology
  • Machine learning in oncology

Background:

  • Whole Slide Images (WSIs) are vital in computational pathology but require advanced methods like Multiple Instance Learning (MIL) for prognostic modeling due to their large size.
  • Existing representation learning models for histopathology lack comprehensive evaluation regarding their impact on survival prediction when integrated with various MIL architectures across different cancer types.

Purpose of the Study:

  • To benchmark different tile embedding strategies and MIL architectures for Overall Survival (OS) prediction from WSIs.
  • To provide practical guidelines for developing robust and generalizable WSI-based survival prediction pipelines.

Main Methods:

  • Compared four tile embedding strategies (ResNet50, ProvGigaPath, UNI, CONCH) and three MIL models (ABMIL, TransMIL, DSMIL) on TCGA and CPTAC cohorts.
  • Evaluated patch-aggregation against end-to-end slide encoders (TITAN, ProvGigaPath) using a Cox Proportional Hazard (CPH) model.
  • Assessed prognostic performance via concordance index (c-index) and interpretability via risk stratification.

Main Results:

  • The choice of patch-level embedding significantly impacts OS prediction accuracy, robustness, and interpretability.
  • Domain-specific and foundation models outperformed conventional convolutional baselines.
  • Results were consistent across multiple cancer types, including BLCA, BRCA, COAD, HNSC, STAD, and ccRCC.

Conclusions:

  • Embedding selection is a critical factor in WSI-based survival prediction performance.
  • Evidence-based guidelines are provided for selecting optimal embeddings and MIL approaches for computational pathology pipelines.
  • Domain-specific and foundation models offer superior performance for prognostic modeling using WSIs.