RealSynCol: a high-fidelity synthetic colon dataset for 3D reconstruction applications

TL;DR

RealSynCol is a highly realistic synthetic colon dataset that enhances deep learning models for 3D reconstruction in colonoscopy by providing extensive ground truth data and improving generalization to clinical images.

Contribution

This paper introduces RealSynCol, a large-scale, realistic synthetic colon dataset with detailed ground truth, designed to improve deep learning methods for 3D colon reconstruction.

Findings

RealSynCol improves model generalization on clinical images.

High realism and variability enhance depth and pose estimation.

Benchmark results validate dataset's effectiveness for endoscopic applications.

Abstract

Deep learning has the potential to improve colonoscopy by enabling 3D reconstruction of the colon, providing a comprehensive view of mucosal surfaces and lesions, and facilitating the identification of unexplored areas. However, the development of robust methods is limited by the scarcity of large-scale ground truth data. We propose RealSynCol, a highly realistic synthetic dataset designed to replicate the endoscopic environment. Colon geometries extracted from 10 CT scans were imported into a virtual environment that closely mimics intraoperative conditions and rendered with realistic vascular textures. The resulting dataset comprises 28\,130 frames, paired with ground truth depth maps, optical flow, 3D meshes, and camera trajectories. A benchmark study was conducted to evaluate the available synthetic colon datasets for the tasks of depth and pose estimation. Results demonstrate that the high realism and variability of RealSynCol significantly enhance generalization performance on clinical images, proving it to be a powerful tool for developing deep learning algorithms to support endoscopic diagnosis.