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

Improving Translational Accuracy02:07

Improving Translational Accuracy

11.9K
Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...
11.9K

You might also read

Related Articles

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

Sort by
Same author

Stereotactic Body Radiation Therapy for Locally Advanced Pancreatic Adenocarcinoma: A Systematic Review and Meta-Analysis of Prospective Trials.

Practical radiation oncology·2026
Same author

Implementing a fully computed tomography-free online adaptive palliative radiotherapy: a one-visit workflow.

Physics and imaging in radiation oncology·2026
Same author

Cone beam computed tomography-guided online adaptive radiation therapy: Clinical implementation in breast and axillary target volumes.

Clinical and translational radiation oncology·2025
Same author

ESTRO-ISRS clinical practice recommendations for re-irradiation of spinal metastases with Stereotactic Body Radiotherapy: Delphi consensus supported by a systematic review and meta-analysis.

Radiotherapy and oncology : journal of the European Society for Therapeutic Radiology and Oncology·2025
Same author

Interpreting convolutional neural network explainability for head-and-neck cancer radiotherapy organ-at-risk segmentation.

Computers in biology and medicine·2025
Same author

Hybrid proton planning combining spread-out Bragg peak beams with transmission beams to shorten field delivery times while maintaining plan quality.

Physics and imaging in radiation oncology·2025

Related Experiment Video

Updated: Sep 15, 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

8.3K

Explainable AI for raising confidence in deep learning-based tumor tracking models.

Dragos Grama1,2, Max Dahele1, Ben Slotman1

  • 1Department of Radiation Oncology, Amsterdam UMC location Vrije Universiteit Amsterdam, Amsterdam, The Netherlands.

Medical Physics
|July 15, 2025
PubMed
Summary
This summary is machine-generated.

Explainable AI methods like Guided Backpropagation (GBP) and DeepLIFT can reliably explain deep learning models for lung tumor tracking during SBRT. This improves trust in AI predictions for accurate radiotherapy delivery.

Keywords:
explainable AIradiotherapytumor tracking

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

6.9K
Quantifying the Brain Metastatic Tumor Micro-Environment using an Organ-On-A Chip 3D Model, Machine Learning, and Confocal Tomography
09:53

Quantifying the Brain Metastatic Tumor Micro-Environment using an Organ-On-A Chip 3D Model, Machine Learning, and Confocal Tomography

Published on: August 16, 2020

7.3K

Related Experiment Videos

Last Updated: Sep 15, 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

8.3K
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

6.9K
Quantifying the Brain Metastatic Tumor Micro-Environment using an Organ-On-A Chip 3D Model, Machine Learning, and Confocal Tomography
09:53

Quantifying the Brain Metastatic Tumor Micro-Environment using an Organ-On-A Chip 3D Model, Machine Learning, and Confocal Tomography

Published on: August 16, 2020

7.3K

Area of Science:

  • Medical Physics
  • Artificial Intelligence in Medicine
  • Radiotherapy Technology

Background:

  • Volumetric Modulated Arc Therapy (VMAT) now offers research-level tumor position monitoring using fluoroscopic images.
  • Accurate lung tumor tracking during Stereotactic Body Radiotherapy (SBRT) with VMAT is crucial for ensuring irradiation within the planning target volume.

Purpose of the Study:

  • Traditional template matching for tumor tracking has low success rates.
  • A deep learning approach offers potential but requires methods to "open the black box" and determine prediction trustworthiness.

Main Methods:

  • Investigated four Explainable AI (XAI) methods: Guided Backpropagation (GBP), Layer-wise Relevance Propagation (LRP), DeepLIFT, and Pattern Attribution.
  • Evaluated XAI method reliability for a 2D markerless lung tumor tracking model using phantoms and clinical patient data.
  • Conducted quantitative and qualitative assessments to determine XAI suitability for tumor tracking.

Main Results:

  • Guided Backpropagation (GBP) and DeepLIFT showed reliable and consistent performance across all tested patients and phantoms.
  • Layer-wise Relevance Propagation (LRP) performed well on phantoms but yielded lower qualitative results with clinical data.

Conclusions:

  • GBP and DeepLIFT are suitable for explaining deep learning-based tracking models in SBRT VMAT.
  • Further research is necessary to establish robust clinical reliability measures for AI during treatment delivery.