Life and Health Sciences Research Institute (ICVS), School of Medicine, University of Minho, Braga, Portugal; ICVS/3B's-PT Government Associate Laboratory, Braga/Guimarães, Portugal; Algoritmi Center, School of Engineering, University of Minho, Guimarães, Portugal.
Life and Health Sciences Research Institute (ICVS), School of Medicine, University of Minho, Braga, Portugal; ICVS/3B's-PT Government Associate Laboratory, Braga/Guimarães, Portugal; Algoritmi Center, School of Engineering, University of Minho, Guimarães, Portugal; Lab on Cardiovascular Imaging & Dynamics, Department of Cardiovascular Sciences, KULeuven-University of Leuven, Leuven, Belgium.
Comput Methods Programs Biomed. 2018 Apr;157:49-67. doi: 10.1016/j.cmpb.2018.01.014. Epub 2018 Jan 11.
Segmentation is an essential step in computer-aided diagnosis and treatment planning of kidney diseases. In recent years, several researchers proposed multiple techniques to segment the kidney in medical images from distinct imaging acquisition systems, namely ultrasound, magnetic resonance, and computed tomography. This article aims to present a systematic review of the different methodologies developed for kidney segmentation.
With this work, it is intended to analyze and categorize the different kidney segmentation algorithms, establishing a comparison between them and discussing the most appropriate methods for each modality. For that, articles published between 2010 and 2016 were analyzed. The search was performed in Scopus and Web of Science using the expressions "kidney segmentation" and "renal segmentation".
A total of 1528 articles were retrieved from the databases, and 95 articles were selected for this review. After analysis of the selected articles, the reviewed segmentation techniques were categorized according to their theoretical approach.
Based on the performed analysis, it was possible to identify segmentation approaches based on distinct image processing classes that can be used to accurately segment the kidney in images of different imaging modalities. Nevertheless, further research on kidney segmentation must be conducted to overcome the current drawbacks of the state-of-the-art methods. Moreover, a standardization of the evaluation database and metrics is needed to allow a direct comparison between methods.
分割是计算机辅助诊断和肾脏疾病治疗计划的重要步骤。近年来，一些研究人员提出了多种技术，用于对来自不同成像采集系统（即超声、磁共振和计算机断层扫描）的医学图像中的肾脏进行分割。本文旨在对不同的肾脏分割方法进行系统综述。
本研究旨在分析和分类不同的肾脏分割算法，在它们之间进行比较，并讨论每种模态的最合适方法。为此，分析了 2010 年至 2016 年期间发表的文章。在 Scopus 和 Web of Science 数据库中使用“肾脏分割”和“肾分割”的表述进行检索。
从数据库中检索到 1528 篇文章，从中选择了 95 篇文章进行综述。对所选文章进行分析后，根据其理论方法对综述的分割技术进行了分类。
根据进行的分析，可以识别出基于不同图像处理类别的分割方法，这些方法可用于准确分割不同成像模态的图像中的肾脏。然而，必须对肾脏分割进行进一步研究，以克服现有方法的当前缺点。此外，需要对评估数据库和指标进行标准化，以允许在方法之间进行直接比较。
