Tripoliti Evanthia E, Fotiadis Dimitrios I, Argyropoulou Maria
Unit of Medical Technology and Intelligent Information Systems, Department of Computer Science, University of Ioannina and Biomedical Research Institute - FORTH, GR 451 10 Ioannina, Greece.
Artif Intell Med. 2007 Jun;40(2):65-85. doi: 10.1016/j.artmed.2007.02.003. Epub 2007 Mar 30.
The aim of this paper is the development of an automated method for the segmentation and quantification of inflammatory tissue of the hand in patients suffering form rheumatoid arthritis using contrast enhanced T1-weighted magnetic resonance images.
The proposed automatic method consists of four stages: (a) preprocessing of images, (b) identification of the number of clusters, by minimizing the appropriate validity index, (c) segmentation using the fuzzy C-means algorithm employing four features which are related to intensity and the location of pixels and (d) postprocessing, where defuzzification is performed and small objects and vessels are eliminated and quantification takes place.
The proposed method is evaluated using a dataset of image sequences obtained from 25 patients suffering from rheumatoid arthritis. For 17 of them we have obtained follow-up images after 1 year treatment. The obtained sensitivity and positive predictive rate is 97.71% and 83.35%, respectively. In addition, quantification of inflammation before and after treatment, as well as, comparison with manual segmentation is carried out.
The proposed method performs very well and results in high detection and quantification accuracy. However, the reduction of false positives and the identification of old inflammation must be addressed.
本文旨在开发一种自动化方法，用于利用对比增强T1加权磁共振图像，对类风湿性关节炎患者手部的炎症组织进行分割和定量分析。
所提出的自动方法包括四个阶段：（a）图像预处理；（b）通过最小化适当的有效性指标来确定聚类数量；（c）使用模糊C均值算法进行分割，该算法采用与像素强度和位置相关的四个特征；（d）后处理，进行去模糊处理，消除小物体和血管，并进行定量分析。
使用从25名类风湿性关节炎患者获得的图像序列数据集对所提出的方法进行评估。其中17名患者在治疗1年后获得了随访图像。所获得的灵敏度和阳性预测率分别为97.71%和83.35%。此外，还对治疗前后的炎症进行了定量分析，并与手动分割进行了比较。
所提出的方法表现良好，检测和定量准确性高。然而，必须解决减少假阳性和识别陈旧性炎症的问题。
