Robust fetoscopic mosaicking from deep learned flow fields.
Robust fetoscopic mosaicking from deep learned flow fields.
复制标题
DOI：
10.1007/s11548-022-02623-1
复制
发表时间：
2022-06
影响因子：
3
通讯作者：
中科院分区：
文献类型：
--
作者：
胎儿镜激光光凝是一种通过阻止胎盘内不规则血流来治疗妊娠期间双胞胎对双胞胎输血综合征的微创手术。建立胎盘及其血管网络的图像马赛克可以帮助外科医生在手术过程中在具有挑战性的胎儿镜检环境中导航。我们提出了一种基于深度学习的光流和稳健估计相结合的胎儿视域拼接方法，用于过滤由于漂浮粒子和投射而发生的不一致运动。虽然目前技术水平的胎儿镜马赛克依赖于清晰可见的血管进行配准，但我们的方法通过考虑连续帧内所有一致像素的运动来克服这一限制。我们还克服了通过使用稳健估计和局部细化将现成的光流应用于胎儿镜马赛克的挑战。我们将我们提出的方法与最先进的基于血管和基于光流的图像配准方法以及稳健估计替代方法进行了比较。我们还使用不同的光流和稳健估计方案对我们提出的流水线进行了比较。通过分析我们的结果，我们的方法比基于血管的技术和LK都要好，特别是当血管很难看到或太薄而无法可靠识别时。因此，我们的方法能够在目前可用的替代方案失败的情况下建立一致的胎盘血管马赛克。网上版载有补充材料，可在10.1007/s11548-022-02623-1查阅。
Fetoscopic laser photocoagulation is a minimally invasive procedure to treat twin-to-twin transfusion syndrome during pregnancy by stopping irregular blood flow in the placenta. Building an image mosaic of the placenta and its network of vessels could assist surgeons to navigate in the challenging fetoscopic environment during the procedure. We propose a fetoscopic mosaicking approach by combining deep learning-based optical flow with robust estimation for filtering inconsistent motions that occurs due to floating particles and specularities. While the current state of the art for fetoscopic mosaicking relies on clearly visible vessels for registration, our approach overcomes this limitation by considering the motion of all consistent pixels within consecutive frames. We also overcome the challenges in applying off-the-shelf optical flow to fetoscopic mosaicking through the use of robust estimation and local refinement. We compare our proposed method against the state-of-the-art vessel-based and optical flow-based image registration methods, and robust estimation alternatives. We also compare our proposed pipeline using different optical flow and robust estimation alternatives. Through analysis of our results, we show that our method outperforms both the vessel-based state of the art and LK, noticeably when vessels are either poorly visible or too thin to be reliably identified. Our approach is thus able to build consistent placental vessel mosaics in challenging cases where currently available alternatives fail. The online version contains supplementary material available at 10.1007/s11548-022-02623-1.
登录
查看更多内容
影响因子：
2.4
作者：
Baschat, Ahmet;Chmait, Ramen H.;Ville, Yves
通讯作者：
Ville, Yves
DOI：
10.1117/1.jmi.5.2.021217
发表时间：
2018-04
期刊：
Journal of medical imaging (Bellingham, Wash.)
影响因子：
--
作者：
Tella-Amo M;Peter L;Shakir DI;Deprest J;Stoyanov D;Iglesias JE;Vercauteren T;Ourselin S
通讯作者：
Ourselin S
DOI：
10.1007/s11548-020-02242-8
发表时间：
2020-11
影响因子：
3
作者：
Bano S;Vasconcelos F;Tella-Amo M;Dwyer G;Gruijthuijsen C;Vander Poorten E;Vercauteren T;Ourselin S;Deprest J;Stoyanov D
通讯作者：
Stoyanov D
影响因子：
3.8
作者：
Lopriore, E.;Middeldorp, J. M.;Vandenbussche, F. P. H. A.
通讯作者：
Vandenbussche, F. P. H. A.
影响因子：
22.7
作者：
FISCHLER, MA;BOLLES, RC
通讯作者：
BOLLES, RC