A comparative study of automatic image segmentation algorithms for target tracking in MR-IGRT.
A comparative study of automatic image segmentation algorithms for target tracking in MR-IGRT.
复制标题
DOI：
10.1120/jacmp.v17i2.5820
复制
发表时间：
2016-03-08
影响因子：
2.1
通讯作者：
Hu Y
中科院分区：
文献类型：
--
作者：
Feng Y;Kawrakow I;Olsen J;Parikh PJ;Noel C;Wooten O;Du D;Mutic S;Hu Y
放射治疗期间的机载磁共振（MR）图像引导提供了更准确的治疗输送的可能性。为了利用真实的实时图像信息，一个关键的先决条件是能够成功分割和跟踪感兴趣区域（ROI）。本工作的目的是使用MR图像引导放射治疗（MR-IGRT）系统采集的运动图像（每秒4帧）评价不同分割算法的性能。由经验丰富的放射肿瘤学家手动绘制肾脏、膀胱、十二指肠和肝脏肿瘤的轮廓，作为性能评价的基础事实。除手动分割外，还使用阈值、模糊k均值（FKM）、k谐波均值（KHM）和反应扩散水平集进化（RD‐LSE）算法以及ViewRay治疗计划和输送系统（VR‐TPDS）提供的组织跟踪算法自动分割图像。利用Dice系数和目标配准误差（TRE）作为人工ROI的质心与自动分割ROI的质心之间的距离，通过与人工分割的比较，定量评价了这五种算法的性能。所有方法都能够成功分割膀胱和肾脏，但只有FKM、KHM和VR-TPDS能够分割肝脏肿瘤和十二指肠。阈值、FKM、KHM和RD‐LSE算法的性能随着局部图像对比度的降低而降低，而VP‐TPDS方法的性能由于参考配准算法而几乎不受局部图像对比度的影响。对于分割高对比度图像（即，肾脏），阈值方法提供了最好的速度（）与令人满意的精度（）。当图像对比度较低时，VR‐TPDS方法具有最佳的自动轮廓。结果表明分割前的图像质量确定程序以及使用机载MR‐IGRT系统进行最佳分割的不同方法的组合。PACS编号：87.57.nm、87.57.N‐、87.61.Tg
On‐board magnetic resonance (MR) image guidance during radiation therapy offers the potential for more accurate treatment delivery. To utilize the real‐time image information, a crucial prerequisite is the ability to successfully segment and track regions of interest (ROI). The purpose of this work is to evaluate the performance of different segmentation algorithms using motion images (4 frames per second) acquired using a MR image‐guided radiotherapy (MR‐IGRT) system. Manual contours of the kidney, bladder, duodenum, and a liver tumor by an experienced radiation oncologist were used as the ground truth for performance evaluation. Besides the manual segmentation, images were automatically segmented using thresholding, fuzzy k‐means (FKM), k‐harmonic means (KHM), and reaction‐diffusion level set evolution (RD‐LSE) algorithms, as well as the tissue tracking algorithm provided by the ViewRay treatment planning and delivery system (VR‐TPDS). The performance of the five algorithms was evaluated quantitatively by comparing with the manual segmentation using the Dice coefficient and target registration error (TRE) measured as the distance between the centroid of the manual ROI and the centroid of the automatically segmented ROI. All methods were able to successfully segment the bladder and the kidney, but only FKM, KHM, and VR‐TPDS were able to segment the liver tumor and the duodenum. The performance of the thresholding, FKM, KHM, and RD‐LSE algorithms degraded as the local image contrast decreased, whereas the performance of the VP‐TPDS method was nearly independent of local image contrast due to the reference registration algorithm. For segmenting high‐contrast images (i.e., kidney), the thresholding method provided the best speed () with a satisfying accuracy (). When the image contrast was low, the VR‐TPDS method had the best automatic contour. Results suggest an image quality determination procedure before segmentation and a combination of different methods for optimal segmentation with the on‐board MR‐IGRT system. PACS number(s): 87.57.nm, 87.57.N‐, 87.61.Tg
登录
查看更多内容
影响因子：
5.7
作者：
Nestor SM;Gibson E;Gao FQ;Kiss A;Black SE;Alzheimer's Disease Neuroimaging Initiative
通讯作者：
Alzheimer's Disease Neuroimaging Initiative
影响因子：
3.5
作者：
Dong, Bin;Graves, Yan Jiang;Jiang, Steve B.
通讯作者：
Jiang, Steve B.
影响因子：
3.8
作者：
Fallone, B. G.;Murray, B.;Tymofichuk, D.
通讯作者：
Tymofichuk, D.
影响因子：
3.5
作者：
Keall, Paul J.;Barton, Michael;Crozier, Stuart
通讯作者：
Crozier, Stuart
影响因子：
4.8
作者：
DICE, LR
通讯作者：
DICE, LR