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

Fixation and Sectioning01:03

Fixation and Sectioning

4.2K
Two basic types of preparation are used to visualize specimens with a light microscope: wet mounts and fixed specimens.
The simplest type of preparation is the wet mount, in which the specimen is placed in a drop of liquid on the slide. A liquid specimen can be directly deposited on the slide using a dropper. Solid specimens, such as skin scraping, can be placed on the slide before adding a drop of liquid to prepare the wet mount. Sometimes the liquid is simply water, but stains are often added...
4.2K
Karyotyping01:17

Karyotyping

59.1K
Overview
59.1K

You might also read

Related Articles

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

Sort by
Same author

Automated Analysis of Liquid Biopsy Using Deep Learning: Detecting Circulating Tumor Cells and Cancer-Associated Fibroblasts.

Methods in molecular biology (Clifton, N.J.)·2026
Same author

Detection of non-invasive sexing of early chick embryos in intact eggs using laser speckle contrast imaging and deep neural networks.

PloS one·2026
Same author

Phosphorus stress and spatial confinement lower the quorum-sensing activation threshold for phenazine production in Pseudomonas synxantha.

Current biology : CB·2026
Same author

Development and Validation of a Multimodal Clinical, Pathologic, and Genomic Model for Breast Cancer Recurrence.

medRxiv : the preprint server for health sciences·2026
Same author

QuTILs: Open-Source Image-Based Infiltrating Immune Cell Detection for Research Application.

Research square·2026
Same author

Recover Biological Structure from Sparse-View Diffraction Images with Neural Volumetric Prior.

Proceedings. IEEE International Conference on Computer Vision·2026

Related Experiment Video

Updated: Jun 12, 2025

Quantitation of Protein Expression and Co-localization Using Multiplexed Immuno-histochemical Staining and Multispectral Imaging
08:40

Quantitation of Protein Expression and Co-localization Using Multiplexed Immuno-histochemical Staining and Multispectral Imaging

Published on: April 8, 2016

12.8K

Impact of Stain Variation and Color Normalization for Prognostic Predictions in Pathology.

Siyu Steven Lin1, Haowen Zhou1, Richard J Cote2

  • 1California Institute of Technology, Department of Electrical Engineering, Pasadena CA 91125 USA.

Arxiv
|September 24, 2024
PubMed
Summary

Deep neural networks (DNNs) in pathology struggle with stain variations. A DNN trained on one batch of histology slides failed to generalize to another batch, even after stain normalization, highlighting a need for new image processing methods.

More Related Videos

Optimized Staining and Proliferation Modeling Methods for Cell Division Monitoring using Cell Tracking Dyes
22:49

Optimized Staining and Proliferation Modeling Methods for Cell Division Monitoring using Cell Tracking Dyes

Published on: December 13, 2012

35.6K
Quantitative Multispectral Analysis Following Fluorescent Tissue Transplant for Visualization of Cell Origins, Types, and Interactions
11:27

Quantitative Multispectral Analysis Following Fluorescent Tissue Transplant for Visualization of Cell Origins, Types, and Interactions

Published on: September 22, 2013

9.3K

Related Experiment Videos

Last Updated: Jun 12, 2025

Quantitation of Protein Expression and Co-localization Using Multiplexed Immuno-histochemical Staining and Multispectral Imaging
08:40

Quantitation of Protein Expression and Co-localization Using Multiplexed Immuno-histochemical Staining and Multispectral Imaging

Published on: April 8, 2016

12.8K
Optimized Staining and Proliferation Modeling Methods for Cell Division Monitoring using Cell Tracking Dyes
22:49

Optimized Staining and Proliferation Modeling Methods for Cell Division Monitoring using Cell Tracking Dyes

Published on: December 13, 2012

35.6K
Quantitative Multispectral Analysis Following Fluorescent Tissue Transplant for Visualization of Cell Origins, Types, and Interactions
11:27

Quantitative Multispectral Analysis Following Fluorescent Tissue Transplant for Visualization of Cell Origins, Types, and Interactions

Published on: September 22, 2013

9.3K

Area of Science:

  • Digital Pathology
  • Computational Pathology
  • Machine Learning in Medicine

Background:

  • Deep neural networks (DNNs) show promise in pathology, potentially exceeding human accuracy by learning subtle features from large datasets.
  • Variations in tinctorial qualities of histological slides pose a challenge for preparing digital pathology datasets for DNN tasks.
  • Stain normalization is a common technique to address image variations in digital pathology.

Purpose of the Study:

  • To evaluate the generalizability of a trained DNN model to new batches of histological slides processed at different times.
  • To assess the effectiveness of stain normalization techniques, including CycleGAN, in improving DNN model performance across different batches.
  • To identify the need for novel image processing and collection strategies for consistent microscopy data in predictive DNN algorithms.

Main Methods:

  • Utilized a previously reported DNN model for identifying early-stage non-small cell lung cancer (NSCLC) metastasis.
  • Trained and tested the DNN on two distinct batches of H&E stained primary tumor tissue sections from the same tissue blocks, processed at different times.
  • Applied traditional color-tuning and Cycle Generative Adversarial Network (CycleGAN) based stain normalization to assess their impact on cross-batch generalization.

Main Results:

  • The DNN model failed to generalize to a new batch of slides, exhibiting significantly lower predictive accuracy (AUC 0.52-0.53) compared to same-batch performance (AUC 0.74-0.81).
  • Stain normalization methods, including CycleGAN, did not improve the DNN's cross-batch generalizability.
  • Tinctorial variations between slide batches were a critical factor limiting the DNN model's predictive performance.

Conclusions:

  • Well-trained DNN models in digital pathology may not generalize to data processed at different times, even with stain normalization.
  • Current stain normalization techniques are insufficient to overcome the generalization gap caused by temporal variations in slide processing.
  • Development of new methods for consistent microscopy image acquisition and processing is crucial for reliable and broadly applicable predictive DNN algorithms in pathology.