CVROOct 25, 2024

A-MFST: Adaptive Multi-Flow Sparse Tracker for Real-Time Tissue Tracking Under Occlusion

arXiv:2410.19996v15 citationsh-index: 65Int J Comput Assist Radiol Surg
Originality Incremental advance
AI Analysis

This work addresses occlusion handling for tissue tracking in robot-assisted surgery, representing an incremental improvement over existing methods.

The paper tackled the problem of tissue tracking under occlusion in robot-assisted surgery by extending the SENDD model with an Adaptive Multi-Flow Sparse Tracker and SAM2 for occlusion detection, resulting in a 12% reduction in Mean Endpoint Error and a 6% improvement in accuracy thresholds while maintaining real-time performance.

Purpose: Tissue tracking is critical for downstream tasks in robot-assisted surgery. The Sparse Efficient Neural Depth and Deformation (SENDD) model has previously demonstrated accurate and real-time sparse point tracking, but struggled with occlusion handling. This work extends SENDD to enhance occlusion detection and tracking consistency while maintaining real-time performance. Methods: We use the Segment Anything Model2 (SAM2) to detect and mask occlusions by surgical tools, and we develop and integrate into SENDD an Adaptive Multi-Flow Sparse Tracker (A-MFST) with forward-backward consistency metrics, to enhance occlusion and uncertainty estimation. A-MFST is an unsupervised variant of the Multi-Flow Dense Tracker (MFT). Results: We evaluate our approach on the STIR dataset and demonstrate a significant improvement in tracking accuracy under occlusion, reducing average tracking errors by 12 percent in Mean Endpoint Error (MEE) and showing a 6 percent improvement in the averaged accuracy over thresholds of 4, 8, 16, 32, and 64 pixels. The incorporation of forward-backward consistency further improves the selection of optimal tracking paths, reducing drift and enhancing robustness. Notably, these improvements were achieved without compromising the model's real-time capabilities. Conclusions: Using A-MFST and SAM2, we enhance SENDD's ability to track tissue in real time under instrument and tissue occlusions.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes