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 21, 2026

Positron Emission Tomography-based Dose Painting Radiation Therapy in a Glioblastoma Rat Model using the Small Animal Radiation Research Platform
07:57

Positron Emission Tomography-based Dose Painting Radiation Therapy in a Glioblastoma Rat Model using the Small Animal Radiation Research Platform

Published on: March 24, 2022

Using dose-surface maps to predict radiation-induced rectal bleeding: a neural network approach.

Florian Buettner1, Sarah L Gulliford, Steve Webb

  • 1Joint Department of Physics, Institute of Cancer Research and Royal Marsden NHS Foundation Trust, Sutton, Surrey SM2 5PT, UK. florian.buttner@icr.ac.uk

Physics in Medicine and Biology
|August 8, 2009
PubMed
Summary

Predicting radiation-induced rectal bleeding requires considering the shape of radiation dose distribution, not just volume. New models using dose-surface maps improve prediction accuracy for late toxicities after radiotherapy.

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

USP22 is a novel vulnerability regulating MEIS1 protein abundance and gene transcription in KMT2Ar acute leukemia.

Blood·2026
Same author

Recent progress in applications of computing to radiotherapy (ICCR 2016).

Physics in medicine and biology·2026
Same author

Continuous multi-omics pathway enrichment analysis resolves hidden functional heterogeneity.

Briefings in bioinformatics·2026
Same author

Interpretable multi-omics integration across mixed-order tensors with MANTRA.

Molecular systems biology·2026
Same author

Pathogenesis of diffuse large B cell lymphoma proteogenotypes.

Cancer cell·2026
Same author

Toward trustworthy healthcare AI: designing academic research for translation readiness.

Molecular systems biology·2026

Area of Science:

  • Radiation Oncology
  • Medical Physics
  • Machine Learning

Background:

  • Late toxicities after radiotherapy are typically modeled using dose-volume parameters.
  • Current models often overlook the spatial distribution of radiation dose.
  • Predicting radiation-induced rectal bleeding is crucial for patient management.

Purpose of the Study:

  • To develop a classifier for predicting radiation-induced rectal bleeding.
  • To incorporate all available dose information to the rectal wall.
  • To evaluate the impact of dose distribution's spatial and morphological aspects on predictive accuracy.

Main Methods:

  • Virtual rectum-unfolding to project dose onto a 2D dose-surface map (DSM).
  • Locally connected neural networks utilizing DSMs as input.

More Related Videos

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 21, 2026

Positron Emission Tomography-based Dose Painting Radiation Therapy in a Glioblastoma Rat Model using the Small Animal Radiation Research Platform
07:57

Positron Emission Tomography-based Dose Painting Radiation Therapy in a Glioblastoma Rat Model using the Small Animal Radiation Research Platform

Published on: March 24, 2022

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

  • Ten-fold cross-validation on data from 329 patients (RT01 trial).
  • Ensemble learning with expert ensembles of neural networks.

    • Main Results:

    • DSM-based expert ensembles achieved an area under the ROC curve of 0.64.
    • Dose-surface histogram (DSH)-based ensembles achieved an area under the ROC curve of 0.59.
    • DSM-based models demonstrated superior predictive performance compared to DSH-based models.

    Conclusions:

    • The spatial and morphological characteristics of radiation dose distribution are significant predictors of rectal bleeding.
    • Integrating dose shape information into predictive models enhances accuracy for radiation-induced rectal bleeding.
    • Future models for predicting radiotherapy toxicities should consider both volumetric and morphological dose aspects.