Kalantar Reza, Lin Gigin, Winfield Jessica M, Messiou Christina, Lalondrelle Susan, Blackledge Matthew D, Koh Dow-Mu
Division of Radiotherapy and Imaging, The Institute of Cancer Research, London SM2 5NG, UK.
Department of Medical Imaging and Intervention, Chang Gung Memorial Hospital at Linkou and Chang Gung University, 5 Fuhsing St., Guishan, Taoyuan 333, Taiwan.
Diagnostics (Basel). 2021 Oct 22;11(11):1964. doi: 10.3390/diagnostics11111964.
The recent rise of deep learning (DL) and its promising capabilities in capturing non-explicit detail from large datasets have attracted substantial research attention in the field of medical image processing. DL provides grounds for technological development of computer-aided diagnosis and segmentation in radiology and radiation oncology. Amongst the anatomical locations where recent auto-segmentation algorithms have been employed, the pelvis remains one of the most challenging due to large intra- and inter-patient soft-tissue variabilities. This review provides a comprehensive, non-systematic and clinically-oriented overview of 74 DL-based segmentation studies, published between January 2016 and December 2020, for bladder, prostate, cervical and rectal cancers on computed tomography (CT) and magnetic resonance imaging (MRI), highlighting the key findings, challenges and limitations.
深度学习（DL）的近期兴起及其在从大型数据集中捕捉非显性细节方面的前景广阔的能力，在医学图像处理领域引起了大量研究关注。DL为放射学和放射肿瘤学中计算机辅助诊断与分割的技术发展提供了基础。在近期已采用自动分割算法的解剖部位中，由于患者内部和患者之间软组织的巨大变异性，骨盆仍然是最具挑战性的部位之一。本综述对2016年1月至2020年12月期间发表的74项基于DL的分割研究进行了全面、非系统性且以临床为导向的概述，这些研究涉及计算机断层扫描（CT）和磁共振成像（MRI）上的膀胱癌、前列腺癌、宫颈癌和直肠癌，突出了关键发现、挑战和局限性。
