Cholec80-port: A Geometrically Consistent Trocar Port Segmentation Dataset for Robust Surgical Scene Understanding

TL;DR

This paper introduces Cholec80-port, a high-quality dataset with geometrically consistent trocar port annotations, improving robustness in surgical scene understanding tasks like image stitching and 3D reconstruction.

Contribution

It provides a standardized, high-fidelity port segmentation dataset with a clear SOP, and unifies existing datasets for better generalization in surgical scene analysis.

Findings

Geometrically consistent annotations enhance cross-dataset robustness.

The dataset improves downstream surgical scene understanding tasks.

Unification of datasets under SOP increases annotation quality.

Abstract

Trocar ports are camera-fixed, pseudo-static structures that can persistently occlude laparoscopic views and attract disproportionate feature points due to specular, textured surfaces. This makes ports particularly detrimental to geometry-based downstream pipelines such as image stitching, 3D reconstruction, and visual SLAM, where dynamic or non-anatomical outliers degrade alignment and tracking stability. Despite this practical importance, explicit port labels are rare in public surgical datasets, and existing annotations often violate geometric consistency by masking the central lumen (opening), even when anatomical regions are visible through it. We present Cholec80-port, a high-fidelity trocar port segmentation dataset derived from Cholec80, together with a rigorous standard operating procedure (SOP) that defines a port-sleeve mask excluding the central opening. We additionally cleanse and unify existing public datasets under the same SOP. Experiments demonstrate that geometrically consistent annotations substantially improve cross-dataset robustness beyond what dataset size alone provides.