Mitigating Biases in Surgical Operating Rooms with Geometry

TL;DR

This paper identifies biases in surgical OR image models caused by visual artifacts and proposes a geometric 3D point cloud approach to improve robustness and accuracy in recognizing personnel.

Contribution

The paper introduces a 3D geometric representation method to mitigate biases caused by visual artifacts in surgical OR personnel recognition tasks.

Findings

CNN models fixate on incidental visual cues like footwear and eyewear.

RGB models' accuracy drops by 12% in realistic clinical settings.

Geometric representations outperform RGB in less diverse, real-world scenarios.

Abstract

Deep neural networks are prone to learning spurious correlations, exploiting dataset-specific artifacts rather than meaningful features for prediction. In surgical operating rooms (OR), these manifest through the standardization of smocks and gowns that obscure robust identifying landmarks, introducing model bias for tasks related to modeling OR personnel. Through gradient-based saliency analysis on two public OR datasets, we reveal that CNN models succumb to such shortcuts, fixating on incidental visual cues such as footwear beneath surgical gowns, distinctive eyewear, or other role-specific identifiers. Avoiding such biases is essential for the next generation of intelligent assistance systems in the OR, which should accurately recognize personalized workflow traits, such as surgical skill level or coordination with other staff members. We address this problem by encoding personnel as 3D point cloud sequences, disentangling identity-relevant shape and motion patterns from appearance-based confounders. Our experiments demonstrate that while RGB and geometric methods achieve comparable performance on datasets with apparent simulation artifacts, RGB models suffer a 12% accuracy drop in realistic clinical settings with decreased visual diversity due to standardizations. This performance gap confirms that geometric representations capture more meaningful biometric features, providing an avenue to developing robust methods of modeling humans in the OR.