Towards computer-assisted TTTS: Laser ablation detection for workflow segmentation from fetoscopic video

Abstract

Purpose

Intrauterine foetal surgery is the treatment option for several congenital malformations. For twin-to-twin transfusion syndrome (TTTS), interventions involve the use of laser fibre to ablate vessels in a shared placenta. The procedure presents a number of challenges for the surgeon, and computer-assisted technologies can potentially be a significant support. Vision-based sensing is the primary source of information from the intrauterine environment, and hence, vision approaches present an appealing approach for extracting higher level information from the surgical site.

Methods

In this paper, we propose a framework to detect one of the key steps during TTTS interventions—ablation. We adopt a deep learning approach, specifically the ResNet101 architecture, for classification of different surgical actions performed during laser ablation therapy.

Results

We perform a two-fold cross-validation using almost 50 k frames from five different TTTS ablation procedures. Our results show that deep learning methods are a promising approach for ablation detection.

Conclusion

To our knowledge, this is the first attempt at automating photocoagulation detection using video and our technique can be an important component of a larger assistive framework for enhanced foetal therapies. The current implementation does not include semantic segmentation or localisation of the ablation site, and this would be a natural extension in future work.