Automated volume analysis of head and neck lesions on CT scans using 3D level set segmentation
Automated volume analysis of head and neck lesions on CT scans using 3D level set segmentation
复制标题
DOI：
10.1118/1.2794174
复制
发表时间：
2007-11-01
期刊：
影响因子：
3.8
通讯作者：
Chan, Heang-Ping
中科院分区：
文献类型：
--
作者：
Street, Ethan;Hadjiiski, Lubomir;Chan, Heang-Ping
作者开发了一种半自动系统，用于分割头颈部CT扫描中的各种病变。该系统以近似边界框作为输入，并使用多级水平集来执行最终分割。一个由23名患者的33次扫描上标记的69个病变组成的数据集用于评价系统的性能。将自动分割的轮廓与由三位经验丰富的放射科医生手动绘制的2D和3D金标准轮廓进行比较。三个性能指标用于比较。此外，放射科医生为所有自动分割提供了I至10级的质量评级。对于这项初步研究，作者观察到自动轮廓和金标准轮廓之间的差异大于观察者间差异。然而，该系统对放射科医生进行了重复检查，实现了85.4%的平均面积相交率，而两名放射科医生之间的平均面积相交率为91.2%。平均绝对面积误差分别为21.1%和10.8%，放射科医生之间的平均2D距离分别为1.38 mm和0.84 mm。此外，质量评级数据表明，尽管在设计系统时对病变特征的假设非常宽松，但自动轮廓非常接近许多病变。(c)2007年美国医学物理学家协会。
The authors have developed a semiautomatic system for segmentation of a diverse set of lesions in head and neck CT scans. The system takes as input an approximate bounding box, and uses a multistage level set to perform the final segmentation. A data set consisting of 69 lesions marked on 33 scans from 23 patients was used to evaluate the performance of the system. The contours from automatic segmentation were compared to both 2D and 3D gold standard contours manually drawn by three experienced radiologists. Three performance metric measures were used for the comparison. In addition, a radiologist provided quality ratings on a I to 10 scale for all of the automatic segmentations. For this pilot study, the authors observed that the differences between the automatic and gold standard contours were larger than the interobserver differences. However, the system performed comparably to the radiologists, achieving an average area intersection ratio of 85.4% compared to an average of 91.2% between two radiologists. The average absolute area error was 21.1% compared to 10.8%, and the average 2D distance was 1.38 mm compared to 0.84 mm between the radiologists. In addition, the quality rating data showed that, despite the very lax assumptions made on the lesion characteristics in designing the system, the automatic contours approximated many of the lesions very well. (c) 2007 American Association of Physicists in Medicine.