Exploring Deep Learning Methods for Real-Time Surgical Instrument Segmentation in Laparoscopy

TL;DR

This paper evaluates deep learning methods for real-time segmentation of surgical instruments in laparoscopy, highlighting DDANet's superior performance and real-time capability for tool tracking in minimally invasive surgery.

Contribution

It introduces and compares deep learning models for instrument segmentation, demonstrating DDANet's effectiveness and real-time speed on surgical datasets.

Findings

DDANet outperforms other models in segmentation accuracy.

Achieves real-time processing at over 101 frames per second.

Yields high Dice coefficient and IoU scores on ROBUST-MIS dataset.

Abstract

Minimally invasive surgery is a surgical intervention used to examine the organs inside the abdomen and has been widely used due to its effectiveness over open surgery. Due to the hardware improvements such as high definition cameras, this procedure has significantly improved and new software methods have demonstrated potential for computer-assisted procedures. However, there exists challenges and requirements to improve detection and tracking of the position of the instruments during these surgical procedures. To this end, we evaluate and compare some popular deep learning methods that can be explored for the automated segmentation of surgical instruments in laparoscopy, an important step towards tool tracking. Our experimental results exhibit that the Dual decoder attention network (DDANet) produces a superior result compared to other recent deep learning methods. DDANet yields a Dice coefficient of 0.8739 and mean intersection-over-union of 0.8183 for the Robust Medical Instrument Segmentation (ROBUST-MIS) Challenge 2019 dataset, at a real-time speed of 101.36 frames-per-second that is critical for such procedures.