Related Experiment Video
Updated: Jun 30, 2025
14:09
Localization and Relative Quantification of Carbon Nanotubes in Cells with Multispectral Imaging Flow Cytometry
Published on: December 12, 2013
6.2K
Label-free quantification of gold nanoparticles at the single-cell level using a multi-column convolutional neural
Abu S M Mohsin1, Shadab H Choudhury1
1Nanotechnology, IoT and Applied Machine Learning Research Group, Brac University, Dhaka, Bangladesh. asm.mohsin@bracu.ac.bd.
The Analyst
|March 15, 2024
Summary
We developed a new AI method using a custom deep learning model to accurately quantify gold nanoparticle uptake in live cells. This overcomes limitations of manual counting and traditional imaging techniques for nanomedicine research.
Area of Science:
- Biomedical Engineering
- Nanotechnology
- Artificial Intelligence
Background:
- Gold nanoparticles (AuNPs) are vital in cellular imaging, diagnostics, and drug delivery.
- Accurate quantification of AuNP uptake in live cells is essential for optimizing nanomedicine efficacy and safety.
- Existing methods for AuNP quantification are often time-consuming, subjective, or limited by imaging constraints.
Purpose of the Study:
- To develop a novel, accurate, and scalable method for quantifying gold nanoparticle uptake in live cells.
- To overcome the limitations of manual counting and existing imaging techniques.
- To enable a deeper understanding of AuNP-cell interactions for advancing nanomedicine.
Main Methods:
- A dataset of dark-field images of 50 nm AuNPs in live cells was annotated.
- A customized multi-column convolutional neural network (MC-CNN) was developed for particle counting.
- The MC-CNN performance was compared against traditional particle counting architectures and spectroscopy-based methods.
Main Results:
- The customized MC-CNN demonstrated superior performance in counting AuNPs within cells compared to conventional methods.
- The developed AI approach provides a scalable and accurate solution for quantifying AuNP uptake.
- This method addresses challenges posed by image artifacts like varying intensities, blurring, and occlusion.
Conclusions:
- The developed MC-CNN offers a significant advancement for quantifying gold nanoparticle uptake in live cells.
- This facilitates better understanding of nanoparticle behavior and interactions, crucial for nanomedicine and drug delivery applications.
- The open-source code enables broader adoption and further research in label-free nanoparticle quantification.
