论文标题
U-NET及其用于医学图像细分的变体：简短的评论
U-Net and its variants for Medical Image Segmentation : A short review
论文作者
论文摘要
该论文是使用U-NET及其变体对医学图像进行分割的简短综述。据我们了解，对于任何临床医生，无论是放射科医生还是病理学家，都不是一件容易的事。分析医学图像是执行非侵入性诊断的唯一方法。细分感兴趣的区域在医学图像中具有重要的重要性，并且是诊断的关键。本文还可以看出医疗图像分割如何发展的鸟类视图。还讨论了深度神经体系结构的挑战和成功。遵循不同的混合体系结构如何建立在视觉识别任务中的强大技术基础上。最后，我们将看到当前的医学图像细分挑战和未来的方向（MIS）。
The paper is a short review of medical image segmentation using U-Net and its variants. As we understand going through a medical images is not an easy job for any clinician either radiologist or pathologist. Analysing medical images is the only way to perform non-invasive diagnosis. Segmenting out the regions of interest has significant importance in medical images and is key for diagnosis. This paper also gives a bird eye view of how medical image segmentation has evolved. Also discusses challenge's and success of the deep neural architectures. Following how different hybrid architectures have built upon strong techniques from visual recognition tasks. In the end we will see current challenges and future directions for medical image segmentation(MIS).
