• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Arabian Journal for Science and Engineering >Segmentation of Ischemic Stroke Lesion in Brain MRI Based on Social Group Optimization and Fuzzy-Tsallis Entropy
【24h】

Segmentation of Ischemic Stroke Lesion in Brain MRI Based on Social Group Optimization and Fuzzy-Tsallis Entropy

机译：基于社会群体优化和Fuzzy-Tsallis熵的脑MRI缺血性脑卒中分割

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Stroke is one of the widespread causes of morbidity worldwide and is also the foremost reason for attained disability in human community. Ischemic stroke can be confirmed by investigating the interior brain regions. Magnetic resonance image (MRI) is one of the noninvasive imaging techniques widely adopted in medical discipline to record brain malformations. In this paper, a hybrid semi-automated image processing methodology is proposed to inspect the ischemic stroke lesion using the MRI recorded with flair and diffusion-weighted modality. The proposed approach consists of two sections, namely the preprocessing based on the social group optimization monitored Fuzzy-Tsallis entropy and post-processing technique, which consists of a segmentation algorithm to extract the ISL from preprocessed image in order to estimate the stroke severity and also to plan for further treatment process. The proposed hybrid approach is experimentally investigated using the ischemic stroke lesion segmentation challenge database. This work also presents a detailed investigation among well-known segmentation approaches, like watershed algorithm, region growing technique, principal component analysis, Chan–Vese active contour, and level set approaches, existing in the literature. The results of the experimental work executed using ISLES 2015 challenge dataset confirm that proposed methodology offers superior average values for image similarity indices like Jaccard (78.60%), Dice (88.54%), false positive rate (3.69%), and false negative rate (11.78%). This work also helps to achieve improved value of sensitivity (99.65%), specificity (78.05%), accuracy (91.17%), precision (98.11%), BCR (90.19%), and BER (6.09%).
机译：中风是世界范围内发病率普遍的原因之一，也是人类社区中导致残疾的最主要原因。缺血性中风可以通过研究大脑内部区域来确认。磁共振成像（MRI）是医学领域广泛采用的无创成像技术之一，用于记录脑畸形。在本文中，提出了一种混合半自动图像处理方法，以使用具有天赋和扩散加权模式的MRI记录来检查缺血性中风病变。所提出的方法包括两部分，即基于社会群体优化监控的Fuzzy-Tsallis熵的预处理和后处理技术，后处理技术由分割算法组成，该算法从预处理图像中提取ISL以估计笔划的严重性，并且计划进一步的治疗过程。使用缺血性中风病灶分割挑战数据库对实验提出的混合方法进行了实验研究。这项工作还对著名的分割方法进行了详细的研究，例如分水岭算法，区域增长技术，主成分分析，Chan-Vese有效轮廓和水平集方法，这些方法在文献中已经存在。使用ISLES 2015挑战数据集执行的实验工作结果证实，所提出的方法为图像相似性指标（如Jaccard（78.60％），Dice（88.54％），假阳性率（3.69％）和假阴性率（ 11.78％）。这项工作还有助于提高灵敏度（99.65％），特异性（78.05％），准确性（91.17％），精度（98.11％），BCR（90.19％）和BER（6.09％）的值。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号