Benchmarking Pretrained Attention-based Models for Real-Time Recognition in Robot-Assisted Esophagectomy

TL;DR

This paper benchmarks eight real-time deep learning models, including attention-based networks, on a novel RAMIE dataset for surgical anatomy segmentation, highlighting the superiority of attention mechanisms and pretraining on ADE20k.

Contribution

It introduces the largest dataset for RAMIE anatomy segmentation and evaluates the performance of various models, emphasizing the benefits of attention-based architectures and specific pretraining datasets.

Findings

Attention-based models outperform traditional CNNs.

Pretraining on ADE20k yields better results than ImageNet.

SegNeXt and Mask2Former achieve top Dice scores.

Abstract

Esophageal cancer is among the most common types of cancer worldwide. It is traditionally treated using open esophagectomy, but in recent years, robot-assisted minimally invasive esophagectomy (RAMIE) has emerged as a promising alternative. However, robot-assisted surgery can be challenging for novice surgeons, as they often suffer from a loss of spatial orientation. Computer-aided anatomy recognition holds promise for improving surgical navigation, but research in this area remains limited. In this study, we developed a comprehensive dataset for semantic segmentation in RAMIE, featuring the largest collection of vital anatomical structures and surgical instruments to date. Handling this diverse set of classes presents challenges, including class imbalance and the recognition of complex structures such as nerves. This study aims to understand the challenges and limitations of current state-of-the-art algorithms on this novel dataset and problem. Therefore, we benchmarked eight real-time deep learning models using two pretraining datasets. We assessed both traditional and attention-based networks, hypothesizing that attention-based networks better capture global patterns and address challenges such as occlusion caused by blood or other tissues. The benchmark includes our RAMIE dataset and the publicly available CholecSeg8k dataset, enabling a thorough assessment of surgical segmentation tasks. Our findings indicate that pretraining on ADE20k, a dataset for semantic segmentation, is more effective than pretraining on ImageNet. Furthermore, attention-based models outperform traditional convolutional neural networks, with SegNeXt and Mask2Former achieving higher Dice scores, and Mask2Former additionally excelling in average symmetric surface distance.