Benchmarking and Enhancing Surgical Phase Recognition Models for Robotic-Assisted Esophagectomy
This work addresses the problem of providing intraoperative support to surgeons during complex esophageal cancer surgeries, representing an incremental improvement in a domain-specific application.
The researchers tackled surgical phase recognition in robotic-assisted esophagectomy by developing a new dataset of 27 videos and benchmarking existing models, then created a novel encoder-decoder model with causal hierarchical attention that achieved superior performance.
Robotic-assisted minimally invasive esophagectomy (RAMIE) is a recognized treatment for esophageal cancer, offering better patient outcomes compared to open surgery and traditional minimally invasive surgery. RAMIE is highly complex, spanning multiple anatomical areas and involving repetitive phases and non-sequential phase transitions. Our goal is to leverage deep learning for surgical phase recognition in RAMIE to provide intraoperative support to surgeons. To achieve this, we have developed a new surgical phase recognition dataset comprising 27 videos. Using this dataset, we conducted a comparative analysis of state-of-the-art surgical phase recognition models. To more effectively capture the temporal dynamics of this complex procedure, we developed a novel deep learning model featuring an encoder-decoder structure with causal hierarchical attention, which demonstrates superior performance compared to existing models.