Unsupervised Multimodal Magnetic Resonance Images Segmentation and Multiple Sclerosis Lesions Extraction based on Edge and Texture Features
Journal Title: Applied Medical Informatics - Year 2017, Vol 39, Issue 1
Abstract
Segmentation of Multiple Sclerosis (MS) lesions is a crucial part of MS diagnosis and therapy. Segmentation of lesions is usually performed manually, exposing this process to human errors. Thus, exploiting automatic and semi-automatic methods is of interest. In this paper, a new method is proposed to segment MS lesions from multichannel MRI data (T1-W and T2-W). For this purpose, statistical features of spatial domain and wavelet coefficients of frequency domain are extracted for each pixel of skull-stripped images to form a feature vector. An unsupervised clustering algorithm is applied to group pixels and extracts lesions. Experimental results demonstrate that the proposed method is better than other state of art and contemporary methods of segmentation in terms of Dice metric, specificity, false-positive-rate, and Jaccard metric.
Authors and Affiliations
Tannaz AKBARPOUR, Mousa SHAMSI, Sabalan DANESHVAR, Masoud POOREISA
Keywords
Related Articles
- EP ID EP655011
- DOI -
- Views 80
- Downloads 0
A Knowledge-Based Prototype to Support the Intelligent Diagnosis of High-Risk Pregnancy
High-risk pregnancy identification (HRP) involves data interpretation and analysis by experts of pregnancy characteristics, and similar prior experiences; this task can be complex depending on the characteristics of the...
Patient data security in the era of medical connected devices
Internet of Things (IoT) is a domain that includes embedded devices connected to a network and used in multiple applications such as: transport, telecommunications, medicine, industrial field and many others. Medical Con...
Implication of Tumor Necrosis Factor - Alpha in Preeclampsia
[i][b]Introduction[/b][/i]: Preeclampsia is an exacerbation of a generalized inflammatory response, physiologically present in the third trimester of pregnancy. [i][b]Aim[/b][/i]: The aim of the study consists in the e...
Virtual reality for stroke rehabilitation: characteristics of protocols, pilot and feasibility studies
Introduction: Virtual reality (VR) for stroke rehabilitation is a therapeutic intervention expected to follow the randomized control trials (RCTs) requirements. This study aimed to identify the characteristics of protoco...
Hybrid Machine Learning Approaches in Viability Assessment of Dental Pulp Stem Cells Treated with Platelet-Rich Concentrates on Different Periods
The unique characteristics of dental pulp stem cells (DPSCs), like multi-lineage differentiation, have attracted considerable interest among clinicians and researchers for the treatment of various diseases. Platelet-deri...