...
【24h】

Using manual prostate contours to enhance deformable registration of endorectal MRI

机译:使用手动前列腺轮廓增强直肠内MRI的可变形配准

获取原文
获取原文并翻译 | 示例

摘要

Background: Endorectal MRI provides detailed images of the prostate anatomy and is useful for radiation treatment planning. Here we describe a Demons field-initialized B-spline deformable registration of prostate MRI. Material and methods: T2-weighted endorectal MRIs of five patients were used. The prostate and the tumor of each patient were manually contoured. The planning MRIs and their segmentations were simulated by warping the corresponding endorectal MRIs using thin plate spline (TPS). Deformable registration was initialized using the deformation field generated using Demons algorithm to map the deformed prostate MRI to the non-deformed one. The solution was refined with B-Spline registration. Volume overlap similarity was used to assess the accuracy of registration and to suggest a minimum margin to account for the registration errors. Results: Initialization using Demons algorithm took about 15. min on a computer with 2.8. GHz Intel, 1.3. GB RAM. Refinement B-spline registration (200 iterations) took less than 5. min. Using the synthetic images as the ground truth, at zero margin, the average (S.D.) 98 (±0.4)% for prostate coverage was 97 (±1)% for tumor. The average (±S.D.) treatment margin required to cover the entire prostate was 1.5 (±0.2)mm. The average (± S.D.) treatment margin required to cover the tumor was 0.7 (±0.1)mm. We also demonstrated the challenges in registering an in vivo deformed MRI to an in vivo non-deformed MRI. Discussion: We here present a deformable registration scheme that can overcome large deformation. This platform is expected to be useful for prostate cancer radiation treatment planning.
机译:背景:直肠内MRI可提供前列腺解剖结构的详细图像,可用于放射治疗计划。在这里,我们描述了前列腺MRI的魔鬼场初始化B样条可变形配准。材料和方法:使用5例患者的T2加权直肠内MRI。手动绘制每个患者的前列腺和肿瘤轮廓。通过使用薄板样条(TPS)弯曲相应的直肠内MRI来模拟计划的MRI及其分割。使用通过恶魔算法生成的变形场初始化可变形配准,以将变形的前列腺MRI映射到未变形的MRI。通过B-Spline配准完善该解决方案。体积重叠相似度用于评估配准的准确性,并提出最小的余量来解决配准错误。结果:在装有2.8的计算机上,使用Demons算法初始化大约需要15分钟。 GHz Intel,1.3。 GB RAM。优化B样条配准(200次迭代)花费了不到5分钟的时间。使用合成图像作为基本事实,在零边界处,前列腺覆盖的平均(S.D.)98(±0.4)%为肿瘤的97(±1)%。覆盖整个前列腺所需的平均(±S.D。)治疗余量为1.5(±0.2)mm。覆盖肿瘤所需的平均(±S.D.)治疗余量为0.7(±0.1)mm。我们还证明了将体内变形MRI记录为体内非变形MRI所面临的挑战。讨论:我们在这里提出一种可以克服较大变形的可变形配准方案。该平台有望用于前列腺癌放射治疗计划。

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