【24h】

Call For Papers

机译:打电话给论文

获取原文
获取原文并翻译 | 示例
           

摘要

Medical imaging technology focuses mainly on the acquisition of information about the interior of a body, used for clinical analysis and medical intervention, as well as to gain a visual representation of the function of some organs or tissues. However, due to equipment limitations, working conditions, limited radiance energy, and generally narrow band width, medical images often suffer from issues including noise, missing data, and spatial resolution degradation. In addition, medical images often refer to data with high-dimensions, large volumes, and complex structures, which can pose a huge challenge for analysis. Recently though, we have witnessed the great success of deep learning methods in various computer vision and image processing tasks, such as denoising, inpainting, super-resolution, classification, detection, and segmentation. Deep learning methods leverage the huge computing power of GPUs to automatically extract robust and discriminative features of input images. It is natural that deep model may also provide a promising direction for medical image reconstruction and analysis. We aim to advance scientific research of deep learning methods in medical images and draw the attention of the broad medical image analysis community.
机译:医学成像技术主要集中在获取有关身体内部的信息,用于临床分析和医疗干预,以及获得一些器官或组织的功能的视觉表示。然而,由于设备限制,工作条件,限量光线能量和一般窄带宽度,医学图像经常遭受包括噪声,缺失数据和空间分辨率劣化的问题。此外,医学图像通常是指具有高维,大量的数据和复杂结构的数据,这可能会对分析构成巨大的挑战。尽管如此,我们目睹了各种计算机视觉和图像处理任务中深度学习方法的巨大成功,例如去噪,染色,超分辨率,分类,检测和分割。深度学习方法利用GPU的巨大计算能力自动提取输入图像的鲁棒和辨别特征。深度模型还可以为医学图像重建和分析提供有希望的方向。我们的目标是推进医学图像中深度学习方法的科学研究,并引起广泛的医学形象分析界的关注。

著录项

  • 来源
    《Sensing and imaging》 |2020年第1期|16.1-16.2|共2页
  • 作者

  • 作者单位
  • 收录信息
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类
  • 关键词

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号