AutoLaparo: A New Dataset of Integrated Multi-tasks for Image-guided Surgical Automation in Laparoscopic Hysterectomy

TL;DR

AutoLaparo is the first comprehensive multi-task dataset for image-guided surgical automation in hysterectomy, enabling advanced learning models for perception and scene understanding in minimally invasive surgery.

Contribution

This paper introduces AutoLaparo, a large-scale, multi-task dataset for surgical scene analysis, addressing the lack of high-quality data in computer-assisted minimally invasive surgery.

Findings

Benchmark results for state-of-the-art models on the dataset

Demonstration of multi-task learning benefits in surgical perception

Dataset availability for future research

Abstract

Computer-assisted minimally invasive surgery has great potential in benefiting modern operating theatres. The video data streamed from the endoscope provides rich information to support context-awareness for next-generation intelligent surgical systems. To achieve accurate perception and automatic manipulation during the procedure, learning based technique is a promising way, which enables advanced image analysis and scene understanding in recent years. However, learning such models highly relies on large-scale, high-quality, and multi-task labelled data. This is currently a bottleneck for the topic, as available public dataset is still extremely limited in the field of CAI. In this paper, we present and release the first integrated dataset (named AutoLaparo) with multiple image-based perception tasks to facilitate learning-based automation in hysterectomy surgery. Our AutoLaparo dataset is developed based on full-length videos of entire hysterectomy procedures. Specifically, three different yet highly correlated tasks are formulated in the dataset, including surgical workflow recognition, laparoscope motion prediction, and instrument and key anatomy segmentation. In addition, we provide experimental results with state-of-the-art models as reference benchmarks for further model developments and evaluations on this dataset. The dataset is available at https://autolaparo.github.io.