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

You might also read

Related Articles

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

Sort by
Same author

Clinical, Imaging, Pathological, and Molecular Details of an Unusual Uveal Melanocytic Tumor of Childhood.

Ocular oncology and pathology·2026
Same author

A new AI assisted approach aligns data standards and accelerates interoperability in biomedical research.

NPJ digital medicine·2026
Same author

CT-to-FLAIR Style Transfer Improves Perilesional Edema Conspicuity in Brain Metastases.

AJNR. American journal of neuroradiology·2026
Same author

Low-Dose Intravenous Ketamine for Primary Pain Control During Naxitamab Anti-GD2 Immunotherapy Treatment.

Pediatric blood & cancer·2026
Same author

Functional neuroimaging biomarkers of impaired neurocognition after proton beam radiotherapy for brain tumors in pediatric patients: A prospective trial.

Neuro-oncology·2026
Same author

Clinical and pathologic correlations of machine learning quantification of Aβ deposits across 3 brain regions of decedents with Alzheimer disease.

Journal of neuropathology and experimental neurology·2026

Related Experiment Video

Updated: Jun 23, 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

6.8K

Evolutionary Strategies AI Addresses Multiple Technical Challenges in Deep Learning Deployment: Proof-of-Principle

Subhanik Purkayastha1, Hrithwik Shalu2, David Gutman1

  • 1Department of Radiology, Memorial Sloan Kettering Cancer Center, New York, NY, 10065, USA.

Journal of Imaging Informatics in Medicine
|June 17, 2024
PubMed
Summary

Deep neuroevolution (DNE) overcomes AI overfitting in radiology by generalizing well to diverse data. This AI approach achieved 97% accuracy in predicting brain metastasis, outperforming traditional methods on small datasets.

Keywords:
Artificial intelligenceConvolutional neural networkDeep neuroevolutionEvolutionary strategiesGenetic algorithms supervised deep learningMagnetic resonance imagingNeuroblastoma

More Related Videos

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

7.2K
Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches
09:47

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

1.0K

Related Experiment Videos

Last Updated: Jun 23, 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

6.8K
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

7.2K
Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches
09:47

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

1.0K

Area of Science:

  • Artificial Intelligence in Medical Imaging
  • Machine Learning for Radiology
  • Deep Learning in Healthcare

Background:

  • Radiology AI faces challenges with overfitting and generalizability, limiting clinical adoption.
  • Small datasets, common in rare diseases, exacerbate these issues.
  • Deep neuroevolution (DNE) shows promise for training AI on limited data but requires validation for generalizability.

Purpose of the Study:

  • To demonstrate the generalizability of deep neuroevolution (DNE) in artificial intelligence (AI) for radiology.
  • To validate DNE's performance on diverse external datasets, addressing a key limitation.
  • To showcase DNE's effectiveness in a specific use case: predicting brain metastasis from neuroblastoma using limited data.

Main Methods:

  • Optimized a convolutional neural network (CNN) using deep neuroevolution (DNE).
  • Trained the DNE-optimized CNN on a small dataset of 60 MRI images.
  • Validated the model on a diverse external dataset from over 50 institutions, comparing it against stochastic gradient descent (SGD) methods.

Main Results:

  • DNE achieved 97% accuracy on the heterogeneous external validation set.
  • Traditional SGD methods (training from scratch and transfer learning) failed to reach 60% accuracy.
  • DNE demonstrated significant generalizability from a small training set to diverse, unseen data.

Conclusions:

  • Deep neuroevolution (DNE) effectively generalizes to diverse external datasets in radiology AI, overcoming limitations of small training sets.
  • DNE's superior performance suggests its potential to significantly improve the clinical utility of AI in medical imaging.
  • This approach holds promise for advancing AI applications, particularly in scenarios with limited data availability, such as rare disease diagnosis.