基于多图谱配准的三维胰腺CT图像分割

李进; 王远军

光学技术, 2022, 48 (3): 350, 网络出版: 2023-01-20

基于多图谱配准的三维胰腺CT图像分割

Segmentation of 3D pancreatic CT image based on multi-atlas registration

论文大纲

李进王远军

作者单位

上海理工大学健康科学与工程学院, 上海 200093

多图谱配准胰腺分割标签融合局部动态阈值 Multi-atlas registration pancreas segmentation label fusion local dynamic threshold

摘要

胰腺的自动分割一直是医学图像分割中一项具有挑战性的问题。胰腺是一个具有高度解剖变异性的器官, 目前的多图谱分割方法很难对胰腺的边缘产生精确的分割。针对这一问题, 采用了基于多图谱配准的分割算法对胰腺进行分割, 优化了一种局部动态阈值的后处理方法。在标签融合阶段, 采用概率阈值融合算法、Majority voting(MV)算法、STAPLE算法和SIMPLE算法四种标签融合算法进行对比。在后处理阶段, 采用局部动态阈值处理方法, 首先通过初步分割结果对目标图像提取目标区域, 然后自动确定阈值实现该区域的二值化, 最终与初步分割结果取交集作为最终分割结果。采用留一交叉验证策略对80例NIH胰腺CT图像和22例来自上海本地医院的胰腺CT图像进行分割, 最终得到的DSC分别为79.98%和81.30%。实验结果表明, 所提方法实现了对胰腺的有效分割。

Abstract

Automatic segmentation of pancreas has always been a challenging problem in medical image segmentation. The pancreas is an organ with a high degree of anatomical variability, and it is difficult for the current multi-atlas segmentation methods to accurately segment the edges of the pancreas. Focusing on this problem, a segmentation algorithm is adopted based on multi-atlas registration to segment the pancreas, and optimizes a post-processing method of local dynamic threshold. In the label fusion stage, four label fusion algorithms are used for comparison: probability threshold fusion algorithm, Majority voting (MV) algorithm, STAPLE algorithm and SIMPLE algorithm. In the post-processing stage, the local dynamic threshold processing method is adopted. First, the target area is extracted from the target image through the preliminary segmentation result, and then the threshold value is automatically determined to realize the binarization of the area. Finally, the intersection with the preliminary segmentation result is taken as the final segmentation result. A leave-one-out cross-validation strategy was used to segment 80 NIH pancreatic CT images and 22 pancreatic CT images from local hospital at Shanghai, and the final DSC obtained were 79.98% and 81.30%, respectively. The experimental results show that the proposed method achieves effective segmentation of the pancreas.

参考文献

[1] Yang N, Han Z, Li Z, et al. Automated pancreas segmentation using recurrent adversarial learning［C］∥ 2018 IEEE International Conference on Bioinformatics and Biomedicine (BIBM). Madrid,Spain:IEEE,2018:927-934.

[2] Karasawa K, Kitasaka T, Oda M, et al. Structure specific atlas generation and its application to pancreas segmentation from contrasted abdominal CT volumes［C］∥ International MICCAI Workshop on Medical Computer Vision. Munich,Germany: Springer,2015:47-56.

[3] Oda M, Shimizu N, Karasawa K, et al. Regression Forest-based atlas localization and direction specific atlas generation for pancreas segmentation［C］∥ International Conference on Medical Image Computing and Computer-Assisted Intervention.Athens,Greece:Springer,2016:556-563.

[4] Karasawa K, Oda M, Kitasaka T, et al. Multi-atlas pancreas segmentation: Atlas selection based on vessel structure［J］. Medical Image Analysis,2017,39:18-28.

[5] Ye C, Ma T, Dan W, et al. Atlas pre-selection strategies to enhance the efficiency and accuracy of multi-atlas brain segmentation tools［J］. Plos One,2018,13(7):1-16.

[6] Aganj Iman, Fischl Bruce. Multi-Atlas image soft segmentation via computation of the expected label value［J］. IEEE Transactions on Medical Imaging,2021,40(6):1702-1710.

[7] Wang H, Suh J W, Das S R, et al. Multi-atlas segmentation with joint label fusion［J］. IEEE Transactions on Pattern Analysis & Machine Intelligence,2013,35(3):611-623.

[8] Bai, W, Shi, et al. A probabilistic Patch-based label fusion model for Multi-atlas segmentation with registration refinement: application to cardiac MR images［J］. IEEE Transactions on Medical Imaging,2013,32(7):1302-1315.

[9] Asman A J, Landman B A. Hierarchical performance estimation in the statistical label fusion framework［J］. Medical Image Analysis,2014,18(7):1870-1881.

[10] Sun L, Zu C, Shao W, et al. Reliability-based robust Multi-atlas label fusion for brain MRI segmentation［J］. Artificial Intelligence in Medicine,2019,96:12-24.

[11] Saito A, Nawano S, Shimizu A. Joint optimization of segmentation and shape prior from level-set-based statistical shape model, and its application to the automated segmentation of abdominal organs［J］. Medical Image Analysis,2016,28:46-65.

[12] Okada T, Linguraru M G, Hori M, et al. Abdominal multi-organ segmentation from CT images using conditional shape–location and unsupervised intensity priors［J］. Medical Image Analysis,2015,26(1):1-18.

[13] 赵世峰, 何皙健. 基于OpenCV的复杂环境下图像二值化方法［J］. 电子测量技术,2018,41(06):55-59.

[14] Yogarajah P, Condell J, Curran K, et al. A dynamic threshold approach for skin segmentation in color images［J］. International Journal of Biometrics,2012,4(1):38-55.

[15] Shi Changfa, Xian Min, Zhou Xiancheng, et al. Multi-slice Low-rank tensor decomposition based Multi-atlas segmentation: application to automatic pathological liver CT segmentation［J］. Medical Image Analysis,2021,73:102152.

[16] Clark, Vendt, Smith, et al. The Cancer Imaging Archive (TCIA): maintaining and operating a public information repository［J］. Journal of Digital Imaging,2013,26(6):1045-1057.

[17] Beare R, Lowekamp B, Yaniv Z. Image segmentation, registration and characterization in R with simpleITK［J］. Journal of Statistical Software,2018,86(8):1-35.

[18] Awate S P, Zhu P, Whitaker R T. How many templates does it take for a good segmentation∶error analysis in multiatlas segmentation as a function of database size［C］∥ International Workshop on Multimodal Brain Image Analysis. Nice, France:Springer,2012:103-114.

[19] 蔡文琴, 王远军. 多项式展开配准的多图谱大脑磁共振图像分割［J］. 光学技术,2020,46(06):734-740.

[20] 江妍, 马瑜, 芦玥, 等. 基于ANTs配准的多图谱分割算法比较研究［J］. 液晶与显示,2021,36(05):723-732.

[21] Iglesias J E, Sabuncu M R. Multi-Atlas segmentation of biomedical images: A survey［J］. Medical Image Analysis,2015,24(1):205-219.

李进, 王远军. 基于多图谱配准的三维胰腺CT图像分割[J]. 光学技术, 2022, 48(3): 350. LI Jin, WANG Yuanjun. Segmentation of 3D pancreatic CT image based on multi-atlas registration[J]. Optical Technique, 2022, 48(3): 350.

基于多图谱配准的三维胰腺CT图像分割

关于本站 Cookie 的使用提示

全站搜索

基于多图谱配准的三维胰腺CT图像分割

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索