The Validation Index: A New Metric for Validation of Segmentation Algorithms Using Two or More Expert Outlines With Application to Radiotherapy Planning
The Validation Index: A New Metric for Validation of Segmentation Algorithms Using Two or More Expert Outlines With Application to Radiotherapy Planning
复制标题
DOI：
10.1109/tmi.2013.2258031
复制
发表时间：
2013-08-01
影响因子：
10.6
通讯作者：
Harris, Emma J.
中科院分区：
文献类型：
--
作者：
Juneja, Prabhjot;Evans, Philp M.;Harris, Emma J.
需要进行验证以确保自动分割算法适用于放射治疗靶区定义。在缺乏真正分割的情况下，算法分割根据专家对感兴趣区域的概述进行验证。使用多名专家来克服专家间的差异。文献中已经研究了几种方法，但结合多个专家大纲的信息以给出单个验证指标的最合适方法尚不清楚。没有人考虑可以根据放射治疗计划中的具体病例要求定制的指标。验证指数（VI）是一种使用专家同意程度的新验证指标。引入控制参数来验证不同放射治疗场景所需的分割：对于接近危险器官的目标和难以辨别的目标，预计专家之间会有很大差异。 VI 使用两个模拟理想化案例和来自两项临床研究的数据进行评估。 VI 与常用的 Dice 相似系数（DSCpair-wise）进行比较，发现比 DSCpair-wise 对专家之间一致性的变化更敏感。 VI 被证明可以适应特定的放射治疗计划场景。
Validation is required to ensure automated segmentation algorithms are suitable for radiotherapy target definition. In the absence of true segmentation, algorithmic segmentation is validated against expert outlining of the region of interest. Multiple experts are used to overcome inter-expert variability. Several approaches have been studied in the literature, but the most appropriate approach to combine the information from multiple expert outlines, to give a single metric for validation, is unclear. None consider a metric that can be tailored to case-specific requirements in radiotherapy planning. Validation index (VI), a new validation metric which uses experts' level of agreement was developed. A control parameter was introduced for the validation of segmentations required for different radiotherapy scenarios: for targets close to organs-at-risk and for difficult to discern targets, where large variation between experts is expected. VI was evaluated using two simulated idealized cases and data from two clinical studies. VI was compared with the commonly used Dice similarity coefficient (DSCpair-wise) and found to be more sensitive than the DSCpair-wise to the changes in agreement between experts. VI was shown to be adaptable to specific radiotherapy planning scenarios.