Search research articles

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

Integrating Clinical Cancer and PTM Proteomics Data Identifies a Mechanism of ACK1 Kinase Activation.

Molecular cancer research : MCR·2023

Same author

AIF promotes a JNK1-mediated cadherin switch independently of respiratory chain stabilization.

The Journal of biological chemistry·2018

See all related articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: Apr 14, 2026

Microfluidic Co-Culture Models for Dissecting the Immune Response in in vitro Tumor Microenvironments

Microfluidic Co-Culture Models for Dissecting the Immune Response in in vitro Tumor Microenvironments

Published on: April 30, 2021

Leveraging Vision Transformers for High-Precision Classification of Cancer Cell Cultures: A Comparative Study on

Noreen Fayyaz Khan¹, Lu Liu¹, Lucas Bierscheid^2,3

¹Department of Computer ScienceNorth Dakota State University Fargo ND 58105 USA.

IEEE Open Journal of Engineering in Medicine and Biology

|April 13, 2026

Summary

Deep learning models, including attention-augmented CNNs and Vision Transformers (ViTs), accurately classify cancer cell cultures. ViTs offer superior performance for automated cancer cell analysis and disease progression studies.

Keywords:

CNN variants and ViT Cancer cell classification MDA-MB-231 cell line PC3 cell line microscopy image processing

More Related Videos

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

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

Semi-automatic PD-L1 Characterization and Enumeration of Circulating Tumor Cells from Non-small Cell Lung Cancer Patients by Immunofluorescence

Semi-automatic PD-L1 Characterization and Enumeration of Circulating Tumor Cells from Non-small Cell Lung Cancer Patients by Immunofluorescence

Published on: August 14, 2019

Related Experiment Videos

Last Updated: Apr 14, 2026

Microfluidic Co-Culture Models for Dissecting the Immune Response in in vitro Tumor Microenvironments

Microfluidic Co-Culture Models for Dissecting the Immune Response in in vitro Tumor Microenvironments

Published on: April 30, 2021

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

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

Semi-automatic PD-L1 Characterization and Enumeration of Circulating Tumor Cells from Non-small Cell Lung Cancer Patients by Immunofluorescence

Semi-automatic PD-L1 Characterization and Enumeration of Circulating Tumor Cells from Non-small Cell Lung Cancer Patients by Immunofluorescence

Published on: August 14, 2019

Area of Science:

Computational biology
Biomedical imaging
Machine learning in oncology

Background:

Accurate cancer cell classification is vital for understanding tumor behavior and drug responses.
Manual evaluation methods are subjective and error-prone, highlighting the need for automated solutions.
Deep learning offers a promising avenue for objective and reliable automated cancer cell analysis.

Purpose of the Study:

To design and evaluate a deep learning pipeline for automated cancer cell classification.
To benchmark the performance of Convolutional Neural Networks (CNNs) against Vision Transformers (ViTs).
To assess the impact of attention mechanisms on model accuracy and generalization.

Main Methods:

A pipeline integrating Otsu thresholding, morphological filtering, and watershed segmentation was developed.
Class-balanced augmentation was employed to handle imbalanced datasets.
A baseline CNN, attention-augmented CNN variants (CNN-SE, CNN-CBAM), and a ViT were benchmarked using 5-fold cross-validation.

Main Results:

Attention modules significantly improved CNN performance.
The Vision Transformer (ViT) demonstrated the highest overall accuracy and generalization capabilities.
ViTs showed an advantage in modeling long-range dependencies within cancer cell images.

Conclusions:

Attention mechanisms help bridge the performance gap between CNNs and transformers.
Transformers provide superior end-to-end performance for cancer cell image analysis.
Attention-augmented CNNs and ViTs serve as valuable tools for automated cancer cell culture analysis.