Scholarlink

Purpose <p>Marker-based tracking of surgical instruments facilitates surgical navigation systems with high precision, but requires time-consuming preparation and is prone to stains or occluded markers. Deep learning promises marker-less tracking based solely on RGB videos to address these challenges. In this paper, object pose estimation is applied to surgical instrument tracking using a novel deep learning architecture.</p> Methods <p>We combine pose estimation from multiple views with recurrent neural networks to better exploit temporal coherence for improved tracking. We also investigate the performance under conditions where the instrument is obscured. We enhance an existing pose (distribution) estimation pipeline by a spatio-temporal feature extractor that allows for feature incorporation along an entire sequence of frames.</p> Results <p>On a synthetic dataset we achieve a mean tip error below 1.0&#xa0;mm and an angle error below 0.2<InlineEquation ID="IEq1"> <EquationSource Format="TEX">\(^{\circ }\)</EquationSource> <EquationSource Format="MATHML"><math> <mmultiscripts> <mrow /> <mrow /> <mo>∘</mo> </mmultiscripts> </math></EquationSource> </InlineEquation> using a four-camera setup. On a real dataset with four cameras we achieve an error below 3.0&#xa0;mm. Under limited instrument visibility our recurrent approach can predict the tip position approximately 3&#xa0;mm more precisely than the non-recurrent approach.</p> Conclusion <p>Our findings on a synthetic dataset of surgical instruments demonstrate that deep-learning-based tracking using multiple cameras simultaneously can be competitive with marker-based systems. Additionally, the temporal information obtained through the architecture’s recurrent nature is advantageous when the instrument is occluded. The synthesis of multi-view and recurrence has thus been shown to enhance the reliability and usability of high-precision surgical pose estimation.</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

Recurrent multi-view 6DoF pose estimation for marker-less surgical tool tracking

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年6月17日

查看全文
  • Niklas Agethen,
  • Janis Rosskamp,
  • Tom L. Koller,
  • Jan Klein,
  • Gabriel Zachmann

摘要

Purpose

Marker-based tracking of surgical instruments facilitates surgical navigation systems with high precision, but requires time-consuming preparation and is prone to stains or occluded markers. Deep learning promises marker-less tracking based solely on RGB videos to address these challenges. In this paper, object pose estimation is applied to surgical instrument tracking using a novel deep learning architecture.

Methods

We combine pose estimation from multiple views with recurrent neural networks to better exploit temporal coherence for improved tracking. We also investigate the performance under conditions where the instrument is obscured. We enhance an existing pose (distribution) estimation pipeline by a spatio-temporal feature extractor that allows for feature incorporation along an entire sequence of frames.

Results

On a synthetic dataset we achieve a mean tip error below 1.0 mm and an angle error below 0.2 \(^{\circ }\) ∘ using a four-camera setup. On a real dataset with four cameras we achieve an error below 3.0 mm. Under limited instrument visibility our recurrent approach can predict the tip position approximately 3 mm more precisely than the non-recurrent approach.

Conclusion

Our findings on a synthetic dataset of surgical instruments demonstrate that deep-learning-based tracking using multiple cameras simultaneously can be competitive with marker-based systems. Additionally, the temporal information obtained through the architecture’s recurrent nature is advantageous when the instrument is occluded. The synthesis of multi-view and recurrence has thus been shown to enhance the reliability and usability of high-precision surgical pose estimation.