Li Yang, Zhao Yu-Qian, Zhang Fan, Liao Miao, Yu Ling-Li, Chen Bai-Fan, Wang Yan-Jin
School of Automation, Central South University, Changsha 410083, China; School of Computer Science and Engineering, Changsha 410083, China; Hunan Engineering Research Center of High Strength Fastener Intelligent Manufacturing, Changde 415701, China.
School of Automation, Central South University, Changsha 410083, China; School of Computer Science and Engineering, Changsha 410083, China; Hunan Engineering Research Center of High Strength Fastener Intelligent Manufacturing, Changde 415701, China; DeepBlue Technology (Shanghai) Co., Ltd, Shanghai, 200042.
Comput Methods Programs Biomed. 2020 Oct;195:105533. doi: 10.1016/j.cmpb.2020.105533. Epub 2020 May 22.
Liver segmentation from abdominal CT volumes is a primary step for computer-aided surgery and liver disease diagnosis. However, accurate liver segmentation remains a challenging task for intensity inhomogeneity and serious pathologies occurring in liver CT volume. This paper presents a novel framework for accurate liver segmentation from CT images.
Firstly, a novel level set integrated with intensity bias and position constraint is applied, and for normal liver, the generated liver regions are regarded as the final results. Then, for pathological liver, a sparse shape composition (SSC)-based method is presented to refine liver shapes, followed by an improved graph cut to further optimize segmentation results. The level set-based method is capable of overcoming intensity inhomogeneity in object regions, and the SSC- and graph cut-based strategy has outstanding power to address under-segmentation appearing in pathological livers.
The experiments conducted on public databases SLIVER07 and 3Dircadb show that the proposed method can segment both healthy and pathological liver effectively. The segmentation performance in terms of mean ASD, RMSD, MSD, VOE and RVD on SLIVER07 are 0.9mm, 1.8mm, 19.4mm, 5.1% and 0.1%, respectively, and on 3Dircadb are 1.6mm, 3.1mm, 27.2mm, 9.2% and 0.5%, respectively, which outperforms many existing methods.
The proposed method does not require complex training procedure on numerous liver samples, and has satisfying and robust segmentation performance on both normal and pathological liver in various shapes.
从腹部CT容积数据中分割肝脏是计算机辅助手术和肝脏疾病诊断的首要步骤。然而，由于肝脏CT容积数据中存在强度不均匀性和严重病变，准确的肝脏分割仍然是一项具有挑战性的任务。本文提出了一种从CT图像中准确分割肝脏的新框架。
首先，应用一种结合强度偏差和位置约束的新型水平集方法，对于正常肝脏，生成的肝脏区域被视为最终结果。然后，对于病变肝脏，提出一种基于稀疏形状合成（SSC）的方法来细化肝脏形状，接着采用改进的图割算法进一步优化分割结果。基于水平集的方法能够克服目标区域的强度不均匀性，而基于SSC和图割的策略在解决病变肝脏中出现的分割不足问题方面具有出色的能力。
在公共数据库SLIVER07和3Dircadb上进行的实验表明，所提出的方法能够有效地分割健康肝脏和病变肝脏。在SLIVER07上，平均绝对对称差（ASD）、均方根对称差（RMSD）、平均对称差（MSD）、体积重叠误差（VOE）和相对体积差（RVD）的分割性能分别为0.9mm、1.8mm、19.4mm、5.1%和0.1%，在3Dircadb上分别为1.6mm、3.1mm、27.2mm、9.2%和0.5%，优于许多现有方法。
所提出的方法不需要在大量肝脏样本上进行复杂的训练过程，并且在各种形状的正常和病变肝脏上都具有令人满意且稳健的分割性能。
