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

Cancer Survival Analysis01:21

Cancer Survival Analysis

486
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...
486
Mouse Models of Cancer Study02:43

Mouse Models of Cancer Study

5.9K
Mice have long served as models for studying human biology and pathology because of their phylogenetic and physiological similarity with humans. They are also easy to maintain and breed in the laboratory, and hence, many inbred strains are now available for research. Studies on mice have contributed immeasurably to our understanding of cancer biology.
The development of transgenic, knockout, and knock-in mice has led to an exponential increase in their use as model organisms in research,...
5.9K

You might also read

Related Articles

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

Sort by
Same author

Deep Learning-Based Quality Control Using Subcellular RNA Spatial Distribution Patterns for Cell Segmentation in Spatial Transcriptomics Data.

Small methods·2025
Same author

Super-Resolution Compatible DNA Labeling Technique Reveals Chromatin Mobility and Organization Changes During Differentiation.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2025
Same author

High-throughput screening of E3 ubiquitin ligases identifies TRIM48 as a novel negative regulator of RIG-I signaling.

Cellular signalling·2025
Same author

Morphology-dependent entry kinetics and spread of influenza A virus.

The EMBO journal·2025
Same author

MethylBERT enables read-level DNA methylation pattern identification and tumour deconvolution using a Transformer-based model.

Nature communications·2025
Same author

DOT: a flexible multi-objective optimization framework for transferring features across single-cell and spatial omics.

Nature communications·2024

Related Experiment Video

Updated: Oct 31, 2025

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

8.5K

Long-term cancer survival prediction using multimodal deep learning.

Luís A Vale-Silva1, Karl Rohr2

  • 1Biomedical Computer Vision Group, BioQuant Center and Institute of Pharmacy and Molecular Biotechnology (IPMB), Heidelberg University, Heidelberg, 69120, Germany. luisvalesilva@gmail.com.

Scientific Reports
|June 30, 2021
PubMed
Summary

MultiSurv, a multimodal deep learning method, accurately predicts long-term cancer survival using diverse patient data. This novel approach handles missing information and offers insights into cancer characteristics.

More Related Videos

Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model
07:13

Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model

Published on: April 18, 2025

301
Competing-Risk Nomogram for Predicting Cancer-Specific Survival in Multiple Primary Colorectal Cancer Patients after Surgery
06:46

Competing-Risk Nomogram for Predicting Cancer-Specific Survival in Multiple Primary Colorectal Cancer Patients after Surgery

Published on: September 27, 2024

460

Related Experiment Videos

Last Updated: Oct 31, 2025

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

8.5K
Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model
07:13

Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model

Published on: April 18, 2025

301
Competing-Risk Nomogram for Predicting Cancer-Specific Survival in Multiple Primary Colorectal Cancer Patients after Surgery
06:46

Competing-Risk Nomogram for Predicting Cancer-Specific Survival in Multiple Primary Colorectal Cancer Patients after Surgery

Published on: September 27, 2024

460

Area of Science:

  • Computational biology
  • Artificial intelligence in oncology
  • Precision medicine

Background:

  • High-dimensional patient data in precision medicine requires advanced computational methods.
  • Accurate long-term survival prediction is crucial for cancer patient management.

Purpose of the Study:

  • To introduce MultiSurv, a multimodal deep learning framework for pan-cancer survival prediction.
  • To develop a method capable of integrating diverse data types for enhanced predictive accuracy.
  • To address the limitations of existing survival prediction models, particularly in handling non-linear and non-proportional hazards.

Main Methods:

  • MultiSurv employs dedicated submodels for clinical, imaging, and omics data feature extraction.
  • A data fusion layer integrates these multimodal representations.
  • A prediction submodel generates conditional survival probabilities over extended follow-up periods.
  • The method is designed to handle missing data across various modalities.

Main Results:

  • MultiSurv achieved accurate pan-cancer patient survival curve predictions across 33 cancer types.
  • Quantitative comparisons demonstrated superior performance over existing methods using time-dependent metrics.
  • Visualizations of the learned multimodal representations provided insights into cancer heterogeneity and characteristics.

Conclusions:

  • MultiSurv represents a significant advancement in multimodal deep learning for long-term cancer survival prediction.
  • The method's ability to integrate diverse data and handle missing values enhances its clinical applicability.
  • MultiSurv offers a powerful tool for precision oncology, improving patient stratification and treatment planning.