Chen Wanwen, Schmidt Adam, Prisman Eitan, Salcudean Septimiu E
Department of Electrical and Computer Engineering, The University of British Columbia, Vancouver, BC, Canada.
Intuitive Surgical Inc., Sunnyvale, CA, USA.
Int J Comput Assist Radiol Surg. 2025 Jul;20(7):1345-1348. doi: 10.1007/s11548-025-03394-1. Epub 2025 May 10.
Intraoperative ultrasound (US) can enhance real-time visualization in transoral robotic surgery (TORS) and improve the safety of the surgery. To develop a US guidance system for TORS, US probe localization and US-preoperative image registration are essential. Image retrieval has the potential to solve these two problems in the same framework, and learning a discriminative US representation is key to successful image retrieval.
We propose a self-supervised contrastive learning approach to match intraoperative US views to a preoperative image database. We introduce a novel contrastive learning strategy that leverages intra-sweep similarity and US probe location to improve feature encoding. Additionally, our model incorporates a flexible threshold to reject unsatisfactory matches.
Our method achieves 92.30% retrieval accuracy on simulated data and outperforms state-of-the-art temporal-based contrastive learning approaches. We also test our approach on real patient data with preoperative US-CT registration to show the feasibility of the proposed US probe localization system, despite tissue deformation due to tongue retraction.
Our contrastive learning method, which utilizes intra-sweep similarity and US probe location, enhances US image representation learning. We also demonstrate the feasibility of using our image retrieval method to provide neck US localization on real patients US after tongue retraction. Total number of words: 2414 words.
术中超声（US）可增强经口机器人手术（TORS）中的实时可视化并提高手术安全性。要开发用于TORS的超声引导系统，超声探头定位和超声术前图像配准至关重要。图像检索有潜力在同一框架内解决这两个问题，而学习有判别力的超声表示是成功进行图像检索的关键。
我们提出一种自监督对比学习方法，将术中超声视图与术前图像数据库进行匹配。我们引入了一种新颖的对比学习策略，利用扫描内相似度和超声探头位置来改进特征编码。此外，我们的模型采用了灵活的阈值来拒绝不满意的匹配。
我们的方法在模拟数据上实现了92.30%的检索准确率，优于基于时间的对比学习方法。我们还在术前进行了超声-CT配准的真实患者数据上测试了我们的方法，以证明所提出的超声探头定位系统的可行性，尽管由于舌回缩会导致组织变形。
我们利用扫描内相似度和超声探头位置的对比学习方法增强了超声图像表示学习。我们还展示了使用我们的图像检索方法在舌回缩后的真实患者超声上提供颈部超声定位的可行性。总字数：2414字。
