Scholarlink

Purpose <p>In laparoscopic liver surgery, registering preoperative CT-extracted 3D models with intraoperative laparoscopic video reconstructions of the liver surface can help surgeons predict critical liver anatomy. However, the registration process is challenged by non-rigid deformation of the organ due to intraoperative pneumoperitoneum pressure, partial visibility of the liver surface, and surface reconstruction noise.</p> Methods <p>First, we learn point-by-point descriptors and encode location information to alleviate the limitations of descriptors in location perception. In addition, we introduce a GeoTransformer to enhance the geometry perception to cope with the problem of inconspicuous liver surface features. Finally, we construct a deep graph matching module to optimize the descriptors and learn overlap masks to robustly estimate the transformation parameters based on representative overlap points.</p> Results <p>Evaluation of our method with comparative methods on both simulated and real datasets shows that our method achieves state-of-the-art results, realizing the lowest surface registration error(SRE) 4.12&#xa0;mm with the highest inlier ratios (IR) 53.31% and match scores (MS) 28.17%.</p> Conclusion <p>Highly accurate and robust initialized registration obtained from partial information can be achieved while meeting the speed requirement. Non-rigid registration can further enhance the accuracy of the registration process on this basis.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Preoperative and intraoperative laparoscopic liver surface registration using deep graph matching of representative overlapping points

  • 期刊论文

  • 发表日期：

    2024年12月31日

查看全文
  • Yue Dai,
  • Xiangyue Yang,
  • Junchen Hao,
  • Huoling Luo,
  • Guohui Mei,
  • Fucang Jia

摘要

Purpose

In laparoscopic liver surgery, registering preoperative CT-extracted 3D models with intraoperative laparoscopic video reconstructions of the liver surface can help surgeons predict critical liver anatomy. However, the registration process is challenged by non-rigid deformation of the organ due to intraoperative pneumoperitoneum pressure, partial visibility of the liver surface, and surface reconstruction noise.

Methods

First, we learn point-by-point descriptors and encode location information to alleviate the limitations of descriptors in location perception. In addition, we introduce a GeoTransformer to enhance the geometry perception to cope with the problem of inconspicuous liver surface features. Finally, we construct a deep graph matching module to optimize the descriptors and learn overlap masks to robustly estimate the transformation parameters based on representative overlap points.

Results

Evaluation of our method with comparative methods on both simulated and real datasets shows that our method achieves state-of-the-art results, realizing the lowest surface registration error(SRE) 4.12 mm with the highest inlier ratios (IR) 53.31% and match scores (MS) 28.17%.

Conclusion

Highly accurate and robust initialized registration obtained from partial information can be achieved while meeting the speed requirement. Non-rigid registration can further enhance the accuracy of the registration process on this basis.