留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

颅缝早闭手术中颅骨切割方案生成方法

罗杨宇 贺佳宾 谢东升 陆珅宇 宫剑

罗杨宇, 贺佳宾, 谢东升, 等 . 颅缝早闭手术中颅骨切割方案生成方法[J]. 北京航空航天大学学报, 2022, 48(4): 578-585. doi: 10.13700/j.bh.1001-5965.2020.0631
引用本文: 罗杨宇, 贺佳宾, 谢东升, 等 . 颅缝早闭手术中颅骨切割方案生成方法[J]. 北京航空航天大学学报, 2022, 48(4): 578-585. doi: 10.13700/j.bh.1001-5965.2020.0631
LUO Yangyu, HE Jiabin, XIE Dongsheng, et al. Skull cutting plan generation method in craniosynostosis surgery[J]. Journal of Beijing University of Aeronautics and Astronautics, 2022, 48(4): 578-585. doi: 10.13700/j.bh.1001-5965.2020.0631(in Chinese)
Citation: LUO Yangyu, HE Jiabin, XIE Dongsheng, et al. Skull cutting plan generation method in craniosynostosis surgery[J]. Journal of Beijing University of Aeronautics and Astronautics, 2022, 48(4): 578-585. doi: 10.13700/j.bh.1001-5965.2020.0631(in Chinese)

颅缝早闭手术中颅骨切割方案生成方法

doi: 10.13700/j.bh.1001-5965.2020.0631
基金项目: 

国家重点研发计划 2017YFE0121200

详细信息
    通讯作者:

    罗杨宇, E-mail: yangyu.luo@ia.ac.cn

  • 中图分类号: T24

Skull cutting plan generation method in craniosynostosis surgery

Funds: 

National Key R & D Program of China 2017YFE0121200

More Information
  • 摘要:

    为实现颅缝早闭手术方案制定的规范化,提出一种结合深度学习、立体视觉和点云处理技术的颅骨切割轨迹生成方法,用于建立切割方案模板库和生成新的病例切割方案。该方法将深度学习应用于颅骨外表面的实例分割中,利用Mask R-CNN对手术区域进行检测和分割,利用简化轮廓提取算法提取切割轨迹,并结合点云处理技术将切割轨迹坐标进行2D-3D映射,实现切割轨迹自动化提取;在此基础上建立典型病例模板库,通过模板匹配方法自动生成新病例的切割方案。实验证明:该轨迹提取方法可以准确高效地检测出颅骨切割轨迹,并将轨迹坐标进行3D映射,点云深度测量误差小于3 mm,达到临床可用标准;模板匹配方法也有效生成新病例的切割轨迹,符合资深医生的手术方案。

     

  • 图 1  婴儿颅缝示意图

    Figure 1.  Schematic diagram of infant cranial suture

    图 2  医生标注方案

    Figure 2.  Cutting plan marked by doctor

    图 3  训练过程中训练集上的L曲线

    Figure 3.  L curve of training dataset during training

    图 4  训练过程中验证集上的Lmask曲线

    Figure 4.  Lmask curve of validation dataset during training

    图 5  冠状缝早闭颅骨分割结果

    Figure 5.  Skull segmentation result for coronary craniosynostosis

    图 6  矢状缝早闭颅骨分割结果

    Figure 6.  Skull segmentation result for sagittal craniosynostosis

    图 7  变形情况下颅骨分割结果

    Figure 7.  Skull segmentation result under deformity circumstance

    图 8  冠状缝早闭简化轮廓提取算法提取结果

    Figure 8.  Extraction result of simplified contour extraction algorithm for coronary craniosynostosis

    图 9  矢状缝早闭简化轮廓提取算法提取结果

    Figure 9.  Extraction result of simplified contour extraction algorithm for sagittal craniosynostosis

    图 10  矢状缝早闭OpenCV轮廓提取算法提取结果

    Figure 10.  Extraction result of OpenCV contour extraction algorithm for sagittal craniosynostosis

    图 11  轮廓提取算法简化前后效率对比

    Figure 11.  Efficiency comparison between original and simplified contour extraction algorithm

    图 12  深度相机简单模型

    Figure 12.  Simplified model of depth camera vision

    图 13  冠状缝早闭手术方案的2D-3D映射效果

    Figure 13.  2D-3D mapping result of coronary craniosynostosis surgery plan

    图 14  矢状缝早闭手术方案的2D-3D映射效果

    Figure 14.  2D-3D mapping result of sagittal craniosynostosis surgery plan

    图 15  矢状缝早闭模板病例颅骨外观

    Figure 15.  Skull appearance of sagittal craniosynostosis template case

    图 16  冠状缝早闭模板病例颅骨外观

    Figure 16.  Skull appearance of coronary craniosynostosis template case

    图 17  矢状缝早闭测试病例颅骨点云与模板颅骨点云配准结果

    Figure 17.  Registration result of skull point cloud of sagittal craniosynostosis testing case with that of templates

    图 18  矢状缝早闭测试病例基于模板匹配生成的初步切割方案

    Figure 18.  Preliminary cutting plan of sagittal craniosynostosis testing case based on template matching

    图 19  冠状缝早闭测试病例颅骨点云与模板颅骨点云配准结果

    Figure 19.  Registration result of skull point cloud of coronary craniosynostosis testing case with that of templates

    图 20  冠状缝早闭测试病例基于模板匹配生成的初步切割方案

    Figure 20.  Preliminary cutting plan of coronary craniosynostosis testing case based on template matching

    表  1  模型精度

    Table  1.   Model precision

    模型 backbone 精度/% 召回率/% mAP/%
    Mask R-CNN ResNet-101 84.44 58.25 99.68
    下载: 导出CSV
  • [1] 沈卫民, 王刚, 吴玉新, 等. 先天性颅缝早闭的颅骨成形——附6例报道[J]. 实用美容整形外科杂志, 2002, 13(4): 180-183. doi: 10.3969/j.issn.1673-7040.2002.04.006

    SHEN W M, WANG G, WU Y X, et al. Plastic skull for craniosynostosis: A report of 6 cases[J]. Journal of Practical Aesthetic and Plastic Surgery, 2002, 13(4): 180-183(in Chinese). doi: 10.3969/j.issn.1673-7040.2002.04.006
    [2] 冯胜之, 张涤生. 先天性颅缝早闭症的治疗[J]. 中华整形烧伤外科杂志, 1995, 11(6): 406-411. https://www.cnki.com.cn/Article/CJFDTOTAL-ZHSA199506001.htm

    FENG S Z, ZHANG D S. Surgical treatment of craniosynostosis[J]. Chinese Journal of Plastic Surgery, 1995, 11(6): 406-411(in Chinese). https://www.cnki.com.cn/Article/CJFDTOTAL-ZHSA199506001.htm
    [3] KLEESIEK J, URBAN G, HUBERT A, et al. Deep MRI brain extraction: A 3D convolutional neural network for skull stripping[J]. NeuroImage, 2016, 129: 460-469. doi: 10.1016/j.neuroimage.2016.01.024
    [4] CHILAMKURTHY S, GHOSH R, TANAMALA S, et al. Deep learning algorithms for detection of critical findings in head CT scans: A retrospective study[J]. Lancet, 2018, 392(10162): 2388-2396. doi: 10.1016/S0140-6736(18)31645-3
    [5] HE K, GKIOXARI G, DOLLAR P, et al. Mask R-CNN[C]//Proceedings of the IEEE International Conference on Computer Vision. Piscataway: IEEE Press, 2017: 2961-2969.
    [6] HE K, ZHANG X Y, REN S Q, et al. Deep residual learning for image recognition[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE Press, 2016: 770-778.
    [7] LIN T Y, DOLLAR P, GIRSHICK R, et al. Feature pyramid networks for object detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE Press, 2017: 936-944.
    [8] REN S, HE K M, GIRSHICKR R, et al. Faster R-CNN: Towards real-time object detection with region proposal networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(6): 1137-1149. doi: 10.1109/TPAMI.2016.2577031
    [9] GIRSHICK R. Fast R-CNN[C]//Proceedings of the IEEE International Conference on Computer Vision. Piscataway: IEEE Press, 2015: 1440-1448.
    [10] ROSENFELD A, KAK A C. Digital picture processing[M]. New York: Academic Press, 1976: 113-116.
    [11] ROSENFELD A. Connectivity in digital pictures[J]. Journal of the ACM, 1970, 17(1): 146-160. doi: 10.1145/321556.321570
    [12] SUZUKI S, BE K. Topological structural analysis of digitized binary images by border following[J]. Computer Vision Graphics and Image Processing, 1985, 30(1): 32-46. doi: 10.1016/0734-189X(85)90016-7
    [13] LOWE D G. Distinctive image features from scale-invariant keypoints[J]. International Journal of Computer Vision, 2004, 60(2): 91-110. doi: 10.1023/B:VISI.0000029664.99615.94
    [14] MARR D, POGGIO T. A computational theory of human stereo vision[J]. Proceedings of the Royal Society of London, 1991, 204(1156): 301-328.
    [15] HEIKO H. Stereo processing by semi-global matching and mutual information[J]. IEEE Transactions on Pattern Analysis and Machine Intelligenc, 2008, 30(2): 328-341. doi: 10.1109/TPAMI.2007.1166
  • 加载中
图(20) / 表(1)
计量
  • 文章访问数:  110
  • HTML全文浏览量:  5
  • PDF下载量:  27
  • 被引次数: 0
出版历程
  • 收稿日期:  2020-11-12
  • 录用日期:  2021-02-10
  • 刊出日期:  2022-04-20

目录

    /

    返回文章
    返回
    常见问答