Abstract
The purpose of this research is to provide an unsupervised precise measurement technique in tracking the change of brain parenchyma volume over time. Tracking this change can be a very useful imaging metric for neurological patients who may develop brain dementia overtime. This technique should help in assessing the patient diagnosis, progress, and response to medication.
A novel unsupervised segmentation technique was developed to measure the brain parenchyma volume with a high degree of precision. The technique consisted of two stages. The first stage used a novel manner of multi-spectral analysis and the second stage used a series of morphological filters coupled with several logical image operators to remove possible segmentation outliers.
This technique required dual spin echo T2 weighted MR data of the brain. Twenty MR data sets were segmented and the accuracy was evaluated visually and found to be free of outliers. The precision of the technique was tested on a series of MR data sets for two normal subjects. Each series consisted of seven MR data sets per subject scanned over a month period. The percent brain parenchyma was calculated for the two subjects with a percent coefficient of variation of less than 0.4%. The technique ran on a standard personal computer in less than 30 seconds per data set without user interaction. This research provided an unsupervised, precise, and fast technique to track the progression of change in brain parenchyma volume.
Keywords: Imaging Metric, MR Brain Segmentation, Multispectral Analysis.
Graphical Abstract
Call for Papers in Thematic Issues
Intelligent Information Retrieval for Multispectral and Hyperspectral Imaging
Multispectral and hyperspectral imaging is an interdisciplinary research area, widely focuses on spectral, spatial, and temporal data. It offers a plethora of opportunities to efficiently analyze the vast area of the earth's surface. However, there are numerous factors such as dimensionality and size of the hyperspectral data, lesser training samples, ...read more
Machine and Deep Learning in Medical Image Diagnosis
Medical Image Processing regards a set of methodologies that have been developed over recent years with the purpose of improving medical image quality, improving medical data visualization, understanding, and assisting medical diagnosis, and so on. The application of machine and deep learning methods in sensing and imaging can potentially have ...read more
Quantum Machine Learning for Medical Data and Imaging
Quantum computing has promised a significant speedup in certain computationally intensive tasks that are intractable on classical computers. Researchers in quantum machine learning, such as those working in computer vision, image processing, biomedical analysis, and related topics, may play an important role in comprehending and working on complicated medical data, ...read more
35
1
1