Learning Where to Look While Tracking Instruments in Robot-assisted Surgery

TL;DR

This paper introduces an end-to-end multitask learning model for real-time surgical instrument segmentation and attention prediction, improving accuracy and efficiency in robot-assisted surgery through novel loss functions and training strategies.

Contribution

It presents a novel multitask model with a shared encoder and task-specific decoders, incorporating batch-Wasserstein loss and a soft attention module for enhanced saliency learning.

Findings

Outperforms existing models on segmentation metrics

Achieves better saliency prediction accuracy

Demonstrates effective multitask training with two-phase optimization

Abstract

Directing of the task-specific attention while tracking instrument in surgery holds great potential in robot-assisted intervention. For this purpose, we propose an end-to-end trainable multitask learning (MTL) model for real-time surgical instrument segmentation and attention prediction. Our model is designed with a weight-shared encoder and two task-oriented decoders and optimized for the joint tasks. We introduce batch-Wasserstein (bW) loss and construct a soft attention module to refine the distinctive visual region for efficient saliency learning. For multitask optimization, it is always challenging to obtain convergence of both tasks in the same epoch. We deal with this problem by adopting `poly' loss weight and two phases of training. We further propose a novel way to generate task-aware saliency map and scanpath of the instruments on MICCAI robotic instrument segmentation dataset. Compared to the state of the art segmentation and saliency models, our model outperforms most of the evaluation metrics.