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: Mar 12, 2026

Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction
06:19

Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction

Published on: August 16, 2024

922

Patch-based Convolutional Neural Network for Whole Slide Tissue Image Classification.

Le Hou1, Dimitris Samaras1, Tahsin M Kurc2

  • 1Dept. of Computer Science, Stony Brook University.

Proceedings. IEEE Computer Society Conference on Computer Vision and Pattern Recognition
|November 1, 2016
PubMed
Summary

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

Topology-Aware Segmentation Using Discrete Morse Theory.

... International Conference on Learning Representations·2026
Same author

TOPODIFFUSIONNET: A TOPOLOGY-AWARE DIFFUSION MODEL.

... International Conference on Learning Representations·2026
Same authorSame journal

Unifying Top-down and Bottom-up Scanpath Prediction Using Transformers.

Proceedings. IEEE Computer Society Conference on Computer Vision and Pattern Recognition·2026
Same author

Look Hear: Gaze Prediction for Speech-directed Human Attention.

Computer vision - ECCV ... : ... European Conference on Computer Vision : proceedings. European Conference on Computer Vision·2026
Same author

Altered dynamic functional connectivity of orbitofrontal cortex underlies olfactory and cognitive impairment in late-life depression.

Psychoradiology·2026
Same author

Towards interpretable prediction of recurrence risk in breast cancer using pathology foundation models.

NPJ digital medicine·2026
Same journal

CARL: A Framework for Equivariant Image Registration.

Proceedings. IEEE Computer Society Conference on Computer Vision and Pattern Recognition·2026
Same journal

Latent Drifting in Diffusion Models for Counterfactual Medical Image Synthesis.

Proceedings. IEEE Computer Society Conference on Computer Vision and Pattern Recognition·2026
Same journal

The Language of Motion: Unifying Verbal and Non-verbal Language of 3D Human Motion.

Proceedings. IEEE Computer Society Conference on Computer Vision and Pattern Recognition·2026
Same journal

Perceptual Inductive Bias Is What You Need Before Contrastive Learning.

Proceedings. IEEE Computer Society Conference on Computer Vision and Pattern Recognition·2026
Same journal

MultiMorph: On-demand Atlas Construction.

Proceedings. IEEE Computer Society Conference on Computer Vision and Pattern Recognition·2026
See all related articles
This summary is machine-generated.

Convolutional Neural Networks (CNNs) can now classify cancer subtypes using image patches. A novel decision fusion model intelligently combines patch predictions, achieving pathologist-level accuracy.

Area of Science:

  • Computational pathology
  • Digital pathology
  • Machine learning in oncology

Background:

  • Convolutional Neural Networks (CNNs) excel at image classification but face computational challenges with gigapixel Whole Slide Tissue Images (WSIs) for cancer subtype recognition.
  • Cancer subtype differentiation relies on cellular-level features observable at the image patch scale, suggesting patch-level analysis is viable.
  • Combining patch-level predictions and identifying discriminative patches are key challenges in WSI analysis.

Purpose of the Study:

  • To develop a patch-based classification method for cancer subtypes that overcomes the computational limitations of training on gigapixel WSIs.
  • To propose a novel decision fusion model for aggregating patch-level predictions from CNNs.
  • To introduce an Expectation-Maximization (EM) based method for robustly locating discriminative patches using spatial relationships.

Related Experiment Videos

Last Updated: Mar 12, 2026

Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction
06:19

Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction

Published on: August 16, 2024

922

Main Methods:

  • Training patch-level CNN classifiers on image patches extracted from WSIs.
  • Developing a decision fusion model to aggregate predictions from multiple patch-level CNNs.
  • Implementing a novel EM-based algorithm to identify and leverage discriminative patches for improved classification.

Main Results:

  • The proposed patch-based method achieved classification accuracy comparable to inter-observer agreement among pathologists for glioma and non-small-cell lung carcinoma subtypes.
  • Experimental results on smaller image datasets demonstrated that patch-based CNNs can outperform image-based CNNs.
  • The decision fusion model effectively aggregated patch-level predictions, and the EM method robustly located discriminative patches.

Conclusions:

  • Patch-level analysis with CNNs offers a computationally feasible and effective approach for cancer subtype classification from WSIs.
  • The novel decision fusion and EM-based patch localization methods provide a robust framework for leveraging detailed cellular information in digital pathology.
  • This approach holds significant potential for improving automated cancer diagnosis and subtyping in clinical settings.