Performance measure characterization for evaluating neuroimage segmentation algorithms
Performance measure characterization for evaluating neuroimage segmentation algorithms
复制标题
DOI：
10.1016/j.neuroimage.2009.03.068
复制
发表时间：
2009-08-01
期刊：
影响因子：
5.7
通讯作者：
Chu, Woei-Chyn
中科院分区：
文献类型：
--
作者：
Chang, Herng-Hua;Zhuang, Audrey H.;Chu, Woei-Chyn
由于神经解剖结构的复杂性、图像的质量和准确分割的要求，表征脑图像中分割算法的性能一直是一个持续的挑战。使用与灵敏度和特异性相关的Jaccard和Dice相似性系数来评估分割算法的性能已经引起了很大的兴趣。本文论述了评价框架中采用的基本绩效衡量系数的基本特征。在探讨Jaccard系数、Dice系数和特异性系数性质的基础上，提出了评价图像分割技术的新的测度系数一致性和敏感性。它表明，一致性是更敏感和更严格的Jaccard和骰子，它有更好的区分能力，在检测小的变化分割图像。与特异性相比，敏感性提供了一致和可靠的评价分数，而无需结合图像背景属性。所提出的系数的优点是通过使用各种分割技术在各种各样的脑图像中提取神经解剖结构来说明。(C)2009 Elsevier Inc. All rights reserved.
Characterizing the performance of segmentation algorithms in brain images has been a persistent challenge due to the complexity of neuroanatomical structures, the quality of imagery and the requirement of accurate segmentation. There has been much interest in using the Jaccard and Dice similarity coefficients associated with Sensitivity and Specificity for evaluating the performance of segmentation algorithms. This paper addresses the essential characteristics of the fundamental performance measure coefficients adopted in evaluation frameworks. While exploring the properties of the Jaccard, Dice and Specificity coefficients, we Propose new measure coefficients Conformity and Sensibility for evaluating image segmentation techniques. It is indicated that Conformity is more sensitive and rigorous than Jaccard and Dice in that it has better discrimination capabilities in detecting small variations in segmented images. Comparing to Specificity, Sensibility provides consistent and reliable evaluation scores without the incorporation of image background properties. The merits of the proposed coefficients are illustrated by extracting neuroanatomical structures in a wide variety of brain images using various segmentation techniques. (C) 2009 Elsevier Inc. All rights reserved.