...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Medical Physics >Deeply supervised 3D fully convolutional networks with group dilated convolution for automatic MRI MRI prostate segmentation
【24h】

Deeply supervised 3D fully convolutional networks with group dilated convolution for automatic MRI MRI prostate segmentation

机译：深度监督3D完全卷积网络，群体扩张卷积为自动MRI MRI前列腺细分

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Purpose Reliable automated segmentation of the prostate is indispensable for image‐guided prostate interventions. However, the segmentation task is challenging due to inhomogeneous intensity distributions, variation in prostate anatomy, among other problems. Manual segmentation can be time‐consuming and is subject to inter‐ and intraobserver variation. We developed an automated deep learning‐based method to address this technical challenge. Methods We propose a three‐dimensional (3D) fully convolutional networks ( FCN ) with deep supervision and group dilated convolution to segment the prostate on magnetic resonance imaging ( MRI ). In this method, a deeply supervised mechanism was introduced into a 3D FCN to effectively alleviate the common exploding or vanishing gradients problems in training deep models, which forces the update process of the hidden layer filters to favor highly discriminative features. A group dilated convolution which aggregates multiscale contextual information for dense prediction was proposed to enlarge the effective receptive field of convolutional neural networks, which improve the prediction accuracy of prostate boundary. In addition, we introduced a combined loss function including cosine and cross entropy, which measures similarity and dissimilarity between segmented and manual contours, to further improve the segmentation accuracy. Prostate volumes manually segmented by experienced physicians were used as a gold standard against which our segmentation accuracy was measured. Results The proposed method was evaluated on an internal dataset comprising 40 T2‐weighted prostate MR volumes. Our method achieved a Dice similarity coefficient ( DSC ) of 0.86?±?0.04, a mean surface distance ( MSD ) of 1.79?±?0.46 ? mm, 95% Hausdorff distance (95% HD ) of 7.98?±?2.91?mm, and absolute relative volume difference ( aRVD ) of 15.65?±?10.82. A public dataset ( PROMISE 12) including 50 T2‐weighted prostate MR volumes was also employed to evaluate our approach. Our method yielded a DSC of 0.88?±?0.05, MSD of 1.02?±?0.35?mm, 95% HD of 9.50?±?5.11?mm, and aRVD of 8.93?±?7.56. Conclusion We developed a novel deeply supervised deep learning‐based approach with a group dilated convolution to automatically segment the MRI prostate, demonstrated its clinical feasibility, and validated its accuracy against manual segmentation. The proposed technique could be a useful tool for image‐guided interventions in prostate cancer.
机译：目的可靠的前列腺自动分割对于图像引导的前列腺干预不可或缺。然而，分割任务由于不均匀的强度分布而挑战，前列腺解剖学的变化以及其他问题。手动分割可能是耗时的，并且受到间歇和互联网服务器变化。我们开发了一种自动化的基于深度学习的方法，以解决这一技术挑战。方法我们提出了一种具有深度监督和群体扩张卷积的三维（3D）完全卷积网络（FCN），以在磁共振成像（MRI）上分段前列腺。在该方法中，将深度监督机制引入3D FCN，以有效缓解训练深层模型中的共同爆炸或消失梯度问题，这迫使隐藏层过滤器的更新过程有利于高度辨别特征。提出了聚集多尺度上下文信息的组扩张卷积，以扩大卷积神经网络的有效接收领域，这提高了前列腺边界的预测准确性。此外，我们介绍了一个组合损失功能，包括余弦和交叉熵，其测量分段和手动轮廓之间的相似性和异化，以进一步提高分割精度。经验丰富的医生手动分割的前列腺卷被用作金标准，以测量我们的分割准确性。结果在包含40T2加权前列腺MR卷的内部数据集上评估所提出的方法。我们的方法达到了0.86Ω±0.04的骰子相似度系数（DSC），平均表面距离（MSD）为1.79？±0.46？ MM，95％Hausdorff距离（95％HD）为7.98？±2.91？mm，绝对相对体积差（ARVD）为15.65？±10.82。公共数据集（承诺12）还用于评估我们的方法，包括50 T2加权前列腺MR卷。我们的方法产生了0.88°的DSC为0.88？0.05，MSD为1.02？±0.35Ω·mm，95％HD为9.50？±5.11？mm，ARVD为8.93？7.56。结论我们开发了一种深入监督基于深度学习的深度学习方法，扩张卷积自动分割MRI前列腺，证明了其临床可行性，并验证了对手动细分的准确性。该提出的技术可能是前列腺癌中的图像引导干预的有用工具。

著录项

  • 来源
    《Medical Physics》 |2019年第4期|共12页
  • 作者

    Wang Bo; Lei Yang; Tian Sibo; Wang Tonghe; Liu Yingzi; Patel Pretesh; Jani Ashesh B.; Mao Hui; Curran Walter J.; Liu Tian; Yang Xiaofeng;

  • 作者单位

    Department of Radiation Oncology and Winship Cancer InstituteEmory UniversityAtlanta GA 30322 USA;

    Department of Radiation Oncology and Winship Cancer InstituteEmory UniversityAtlanta GA 30322 USA;

    Department of Radiation Oncology and Winship Cancer InstituteEmory UniversityAtlanta GA 30322 USA;

    Department of Radiation Oncology and Winship Cancer InstituteEmory UniversityAtlanta GA 30322 USA;

    Department of Radiation Oncology and Winship Cancer InstituteEmory UniversityAtlanta GA 30322 USA;

    Department of Radiation Oncology and Winship Cancer InstituteEmory UniversityAtlanta GA 30322 USA;

    Department of Radiation Oncology and Winship Cancer InstituteEmory UniversityAtlanta GA 30322 USA;

    Department of Radiology and Imaging Sciences and Winship Cancer InstituteEmory UniversityAtlanta GA;

    Department of Radiation Oncology and Winship Cancer InstituteEmory UniversityAtlanta GA 30322 USA;

    Department of Radiation Oncology and Winship Cancer InstituteEmory UniversityAtlanta GA 30322 USA;

    Department of Radiation Oncology and Winship Cancer InstituteEmory UniversityAtlanta GA 30322 USA;

  • 收录信息
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类 基础医学;
  • 关键词

    3D prostate segmentation; deeply supervised mechanism; fully convolutional networks ( FCN ); group dilated convolution;

    机译：3D前列腺细分;深受监督机制;完全卷积网络（FCN）;小组扩张卷积;

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