• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>International Conference on Medical Image Computing and Computer-Assisted Intervention >ARS-Net: Adaptively Rectified Supervision Network for Automated 3D Ultrasound Image Segmentation
【24h】

ARS-Net: Adaptively Rectified Supervision Network for Automated 3D Ultrasound Image Segmentation

机译：ARS-Net：用于自动3D超声图像分割的自适应校正监督网络

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

3D Ultrasound (3DUS) has been widely used in clinical diagnosis. However, volume segmentation of 3DUS is very challenging due to relatively poor image quality and usually small datasets. We propose an efficient and robust method (ARS-Net) for single organ segmentation in 3DUS. Our contributions are twofold, (ⅰ) We propose a 2.5D framework based on a 2D segmentation network with 2.5D input which can provide more contextual and spatial information. The proposed framework also overcomes the limitation of 3D networks, such as small datasets, lack of pre-trained models and high memory cost, (ⅱ) To further enhance the performance in low signal-to-noise ratio (SNR) regions, we incorporate a new mechanism of adaptively rectified supervision (ARS) into the proposed 2.5D framework at training stage. Specifically, both pixel-wise reweighted dice loss and image-wise shape regu-larization loss are applied to improve the sensitivity and the specificity of segmentation. The experiment results on two representative and challenging datasets of 3DUS show that the proposed ARS-Net outperforms state-of-the-art methods with higher accuracy but lower complexity. The proposed novel network is robust to small datasets and can provide an accurate and fast volume segmentation tool for 3DUS.
机译：3D超声（3DUS）已被广泛用于临床诊断。然而，由于相对差的图像质量和通常较小的数据集，3DUS的体积分割非常具有挑战性。我们提出了一种有效且鲁棒的方法（ARS-Net），用于3DUS中的单器官分割。我们的贡献是双重的。（ⅰ）我们提出了一个基于带有2.5D输入的2D分割网络的2.5D框架，该框架可以提供更多的上下文和空间信息。所提出的框架还克服了3D网络的局限性，例如数据集小，缺乏预训练的模型和高存储成本。（ⅱ）为了进一步增强低信噪比（SNR）区域的性能，我们引入了在培训阶段将新的自适应纠正监督（ARS）机制引入拟议的2.5D框架。具体地，像素方向的加权骰子损失和图像方向的形状规整损失都被应用以提高分割的灵敏度和特异性。在3DUS的两个代表性且具有挑战性的数据集上的实验结果表明，所提出的ARS-Net优于最新方法，具有更高的准确性，但复杂度更低。所提出的新颖网络对于小型数据集具有鲁棒性，并且可以为3DUS提供准确而快速的体积分割工具。

著录项

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