• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>Conference on Medical Imaging: Image Processing >Enhancing Reproductive Organ Segmentation in Pediatric CT via Adversarial Learning
【24h】

Enhancing Reproductive Organ Segmentation in Pediatric CT via Adversarial Learning

机译：通过对抗性学习增强儿科CT的生殖器官分割

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

摘要

Accurately segmenting organs in abdominal computed tomography (CT) scans is crucial for clinical applications such as pre-opcrative planning and dose estimation. With the recent advent of deep learning algorithms, many robust frameworks have been proposed for organ segmentation in abdominal CT images. However, many of these frameworks require large amounts of training data in order to achieve high segmentation accuracy. Pediatric abdominal CT images containing reproductive organs arc particularly hard to obtain since these organs arc extremely sensitive to ionizing radiation. Hence, it is extremely challenging to train automatic segmentation algorithms on organs such as the uterus and the prostate. To address these issues, we propose a novel segmentation network with a built-in auxiliary classifier generative adversarial network (ACGAN) that conditionally generates additional features during training. The proposed CFG-SegNet (conditional feature generation segmentation network) is trained on a single loss function which combines adversarial loss, reconstruction loss, auxiliary classifier loss and segmentation loss. 2.5D segmentation experiments are performed on a custom data set containing 24 female CT volumes containing the uterus and 40 male CT volumes containing the prostate. CFG-SegNet achieves an average segmentation accuracy of 0.929 DSC (Dice Similarity Coefficient) on the prostate and 0.724 DSC on the uterus with 4-fold cross validation. The results show that our network is high-performing and has the potential to precisely segment difficult organs with few available training images.
机译：腹部计算机断层扫描（CT）扫描中精确分割器官对诸如诸如葡萄糖规划和剂量估计的临床应用至关重要。随着最近深入学习算法的出现，已经提出了许多强大的框架，用于腹部CT图像中的器官分段。然而，许多这些框架需要大量的训练数据来实现高分性准确性。含有繁殖器官的小儿腹部CT图像特别难以获得，因为这些器官对电离辐射极敏感。因此，在诸如子宫和前列腺之类的器官上培训自动分段算法是非常具有挑战性的。为了解决这些问题，我们提出了一种新的分段网络，其内置辅助分类器生成的对冲网络（acgar），其在训练期间有条件地生成其他功能。所提出的CFG-SEGNET（条件特征生成分段网络）培训在单个损耗函数上培训，该函数结合了对抗性丢失，重建损耗，辅助分类器丢失和分割损耗。 2.5D分割实验在含有24个雌性CT体积的定制数据集上进行，含有含有前列腺的子宫和40个雄性CT体积。 CFG-SEGNET在子宫上的0.929dsc（骰子相似系数）的平均分割精度为0.929dsc（骰子相似系数），在子宫上有4倍交叉验证。结果表明，我们的网络是高性能的，并且有可能恰好分割困难的器官，只有很少的可用培训图像。

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