Extraction of Iron Oxide Nanoparticles from 3 Dimensional MRI Images UsingK-Mean Algorithm

Abstract

Nanomedicine targeted drug delivery is one of the emerging techniques for diagnosis and treatment of complex diseases. Medical image processing of High-Resolution Magnetic Resonance Imaging (HR-MRI), when combined with iron oxide nanoparticles (IO-NPs), provides a precious tool to monitor diagnosis and treatment processes. The challenge is to detect the nanoparticles inside the HR-MRI images. This is due to the low resolution of the images and the small size of the nanoparticles. In this paper, we study the drug delivery efficiency using a mouse with an inflamed calf, with IO-NPs attached to the therapeutic drug and injected into the mouse's eye. Our aim is to know how much of the drug injected will reach the inflamed region of the calf. A high-resolution MRI system was used to take images of the inflamed calf region. Knowing that iron oxide has a strong magnetic intensity on MRI images, image processing techniques were used to identify the location and quantity of IO-NPs attached to the drug. By knowing the location and quantity of IO-NPs we can estimate the quantity of drug delivered to the region of interest. In our project, K-mean algorithm, an automatic clustering algorithm was used to detect the iron oxide NPs in the MRI images. This then extracts them from the 3D model of the femoral region of interest. Extraction of NPs permits an estimation of the number of NPs clustered in the region and furthermore estimates the quantity of the drug delivered to the region of interest. The results obtained of nanoparticle detection and extraction seem to be a promising way to estimate the amount of delivered drug to a targeted area.