Neural Network-Based Learning Kernel for Automatic Segmentation of Multiple Sclerosis Lesions on Magnetic Resonance Images
Journal Title: Journal of Biomedical Physics and Engineering - Year 2017, Vol 7, Issue 2
Abstract
Background: Multiple Sclerosis (MS) is a degenerative disease of central nervous system. MS patients have some dead tissues in their brains called MS lesions. MRI is an imaging technique sensitive to soft tissues such as brain that shows MS lesions as hyper-intense or hypo-intense signals. Since manual segmentation of these lesions is a laborious and time consuming task, automatic segmentation is a need. Materials and Methods: In order to segment MS lesions, a method based on learning kernels has been proposed. The proposed method has three main steps namely; pre-processing, sub-region extraction and segmentation. The segmentation is performed by a kernel. This kernel is trained using a modified version of a special type of Artificial Neural Networks (ANN) called Massive Training ANN (MTANN). The kernel incorporates surrounding pixel information as features for classification of middle pixel of kernel. The materials of this study include a part of MICCAI 2008 MS lesion segmentation grand challenge data-set. Results: Both qualitative and quantitative results show promising results. Similarity index of 70 percent in some cases is considered convincing. These results are obtained from information of only one MRI channel rather than multi-channel MRIs. Conclusion: This study shows the potential of surrounding pixel information to be incorporated in segmentation by learning kernels. The performance of proposed method will be improved using a special pre-processing pipeline and also a post-processing step for reducing false positives/negatives. An important advantage of proposed model is that it uses just FLAIR MRI that reduces computational time and brings comfort to patients.
Authors and Affiliations
H Khastavaneh
Keywords
Related Articles
- EP ID EP330380
- DOI -
- Views 105
- Downloads 0
Evaluation of Radiation Exposure Pattern and Radiation Absorbed Dose Resulting from Occupational Exposure of Anesthesiologists to Ionizing Radiation
Introduction: Little information is available concerning the radiation exposure of anesthesiologists, and no such data have previously been collected in Iran. This prospective study was performed to determine the amount...
Effect of Microwave Wi-Fi Radiation at Frequency of 2.4 GHz on Epileptic Behavior of Rats
Background: Electromagnetic fields (EMF) with different intensities are widely used at home, offices and public places.Today, there is a growing global concern about the effects of human exposure to EMFs. Epilepsy is one...
Investigating the Effect of Air Cavities of Sinuses on the Radiotherapy Dose Distribution Using Monte Carlo Method
Background: Considering that some vital organs exist in the head and neck region, the treatment of tumors in this area is a crucial task. The existence of air cavities, namely sinuses, disrupt the radiotherapy dose distr...
Effects of Laser Physical Parameters on Lesion Size in Retinal Photocoagulation Surgery: Clinical OCT and Experimental Study
Introduction: The aim of the present study was to determine burn intensity in retinal laser photocoagulation based on laser parameters; wavelength, power, beam size and pulse duration, using Optical Coherence Tomography...
Thyroid Ultrasonography in Differentiation between Graves’ Disease and Hashimoto's Thyroiditis
Purpose: Graves' disease and Hashimoto's thyroiditis are the most common causes of hyper and hypothyroidism, respectively. Differentiation of these 2 diseases, if the patient is euthyroid, may sometimes be extremely diff...