Get started
Work

Medical Image Modeling and Processing

Year: 2024
Type: dissertation
Abstract: During the last few decades of the twentieth century, medical imaging has been playing a prominent role in many fields of biomedical research and clinical practice. Image modalities such as x-rays, computed tomography (CT), and magnetic resonance images (MRI) have all been valuable additions to the radiologist's arsenal of imaging tools. Medical images assure quality diagnosis and patient safety by gathering valuable information without invading the human body. Apart from clinical diagnosis, medical images are used as tools for education where they are used for training individuals before operating on a patient. Many medical educators tum to simulation based training systems to provide meaningful learning experiences. Modeling and simulation of medical images is an essential part of such training systems. In this thesis work, we developed two algorithms for medical applications. The first part of he thesis deals with wound debridement simulation, and it automatically generates he wound textures used in the simulation. Previously, the images were generated by artists manually using image editing tools such as Photoshop. The proposed algorithm is a procedural method that has two passes. In the first pass, we use the Perlin noise function to generate noise at every pixel location of the wound image. In the second pass, the noise is confined to the wound area by elliptical shape composition. By automatically generating texture images, each execution of the wound debridement simulation produces new wound conditions thereby greatly enhancing the training scenarios and improving the training outcome. The second part of the thesis deals with MRI image denoising, and it optimizes the parameter values associated with the denoising algorithm. Many image denoising algorithms have been proposed for MRI images. Noise removal is accomplished at the expense of blurred subtle features in the image. Therefore, there is always a trade-off between noise removal and structure information preservation. In the proposed algorithm, we define several cost functions to assess the outcome of denoising methods and utilize the Strength Pareto Evolutionary Algorithm (SPEA2) to simultaneously optimize those cost functions by modifying parameters associated with the denoising algorithm. The proposed optimization procedure is illustrated by optimizing the parameters of image denoising based on block matching and 3D collaborative filtering. Using the proposed optimization procedure, instead of a single solution, we obtain a set of solutions so that the designer can choose the best trade-offs.
DOI: 10.25777/9v0j-2w63
Author: Pedada, Ramu
Language: English
Open Access status: green
OpenAlex ID: W6908507459
Cites:
Cited by:
Related to: