arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1906.11031cs.CVeess.IV
收藏

连续Dice系数:一种概率分割的评价方法

Continuous Dice Coefficient: a Method for Evaluating Probabilistic Segmentations

University of Minnesota, Twin Cities(明尼苏达大学双城分校);Duke University(杜克大学)

Reuben R Shamir, Yuval Duchin, Jinyoung Kim, Guillermo Sapiro, Noam Harel

摘要:

目的:重叠度量常被用来量化两个二值区域之间的相似性。然而,现代分割算法输出的概率或置信度图具有在0到1区间内的连续值。此外,这些二进制重叠的措施是偏向于结构的大小。应对这些挑战是这项工作的目标。研究方法:我们扩展了经典的骰子系数(DC)重叠的定义,以方便直接比较地面真实的二进制图像与概率图。我们称这种方法为连续Dice系数(cDC),并证明了:1)cDC小于或等于1且cDC = 1,当且仅当结构重叠是完全的; 2)cDC随重叠量单调递减。我们比较了经典的DC和cDC的模拟部分容积效应,其中包括分割的共同目标深部脑刺激。最后,我们研究了自动分割丘脑底核的cDC。结果如下:对丘脑(大结构)的部分容积效应模拟得出DC和cDC平均值(SD)分别为0.98(0.006)和0.99(0.001)。对于底丘脑核(小结构),DC和cDC分别为0.86(0.025)和0.97(0.006)。自动分割的DC和cDC分别为0.66和0.80。结论:cDC对于概率分割是良好定义的,与DC相比,对结构尺寸的偏差较小,对部分容积效应的稳健性更高。意义:所提出的方法有利于更好地评估分割算法。作为一种更好的测量工具,它为开发更好的分割方法打开了大门。

英文摘要:

Objective: Overlapping measures are often utilized to quantify the similarity between two binary regions. However, modern segmentation algorithms output a probability or confidence map with continuous values in the zero-to-one interval. Moreover, these binary overlapping measures are biased to structure size. Addressing these challenges is the objective of this work. Methods: We extend the definition of the classical Dice coefficient (DC) overlap to facilitate the direct comparison of a ground truth binary image with a probabilistic map. We call the extended method continuous Dice coefficient (cDC) and show that 1) cDC is less or equal to 1 and cDC = 1 if-and-only-if the structures overlap is complete, and, 2) cDC is monotonically decreasing with the amount of overlap. We compare the classical DC and the cDC in a simulation of partial volume effects that incorporates segmentations of common targets for deep-brainstimulation. Lastly, we investigate the cDC for an automatic segmentation of the subthalamic-nucleus. Results: Partial volume effect simulation on thalamus (large structure) resulted with DC and cDC averages (SD) of 0.98 (0.006) and 0.99 (0.001), respectively. For subthalamic-nucleus (small structure) DC and cDC were 0.86 (0.025) and 0.97 (0.006), respectively. The DC and cDC for automatic STN segmentation were 0.66 and 0.80, respectively. Conclusion: The cDC is well defined for probabilistic segmentation, less biased to structure size and more robust to partial volume effects in comparison to DC. Significance: The proposed method facilitates a better evaluation of segmentation algorithms. As a better measurement tool, it opens the door for the development of better segmentation methods.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑