Quantifying Nanoparticles and Monomer-Dimer Distribution in Optical Images using Deep Learning

Paper Links

Coming Soon

Abstract

Nanoparticles embedded in polymer matrices play a critical role in enhancing the properties and functionalities of composite materials. Detecting and quantifying nanoparticles from optical images is crucial for understanding their distribution, aggregation, and interactions, leading to advancements in nanotechnology, materials science, and biomedical research. In this paper, we propose a deep learning approach for automatic nanoparticle detection and oligomerization quantification in a polymer matrix for optical images. We introduce a novel deep neural network architecture, YOLOv8 and train it on a carefully annotated dataset of 80 nm gold nanospheres (AuNS). The performance of the model is evaluated using Accuracy, mAP (mean Average Precision), and IoU (Intersection over Union) metrics, demonstrating its effectiveness in nanoparticle detection and oligomerization within the polymer matrix. It will also be useful for analyzing nanoparticle uptake and aggregation kinetics in live cells, identifying membrane protein interactions, and drug delivery

Code

Available on Github

Dataset

Coming soon

Credits

Shadab Hafiz Choudhury ¹ and Dr. Abu Mohsin ^{1 2}

^{1: Department of Electrical and Electronic Engineering, Brac University
2: Corresponding Author}
_{Both authors contributed equally to this work.}