# Lesion-centered 3D mapping of colonoscopy procedures: validation of a hierarchical ensemble pipeline on public benchmark videos

arXiv: https://arxiv.org/abs/2609.16672 · HTML: https://mlsanity.com/paper/2609.16672/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 27 references that are in the map.
- First posted on arXiv 15 Sep 2026.

## Builds on (most cited first, 21 of 21)

- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [VGGT: Visual Geometry Grounded Transformer](https://mlsanity.com/paper/2503.11651/) (2025)
- [LightGlue: Local Feature Matching at Light Speed](https://mlsanity.com/paper/2306.13643/) (2023)
- [Video Polyp Segmentation: A Deep Learning Perspective](https://mlsanity.com/paper/2203.14291/) (2022)
- [Colonoscopy 3D Video Dataset with Paired Depth from 2D-3D Registration](https://mlsanity.com/paper/2206.08903/) (2022)
- [Foundation Model for Endoscopy Video Analysis via Large-scale Self-supervised Pre-train](https://mlsanity.com/paper/2306.16741/) (2023)
- [EndoMapper dataset of complete calibrated endoscopy procedures](https://mlsanity.com/paper/2204.14240/) (2022)
- [DefSLAM: Tracking and Mapping of Deforming Scenes from Monocular Sequences](https://mlsanity.com/paper/1908.08918/) (2019)
- [REAL-Colon: A dataset for developing real-world AI applications in colonoscopy](https://mlsanity.com/paper/2403.02163/) (2024)
- [Semantic-SuPer: A Semantic-aware Surgical Perception Framework for Endoscopic Tissue Identification, Reconstruction, and Tracking](https://mlsanity.com/paper/2210.16674/) (2022)
- [SALI: Short-term Alignment and Long-term Interaction Network for Colonoscopy Video Polyp Segmentation](https://mlsanity.com/paper/2406.13532/) (2024)
- [Endo3R: Unified Online Reconstruction from Dynamic Monocular Endoscopic Video](https://mlsanity.com/paper/2504.03198/) (2025)
- [C3VDv2 -- Colonoscopy 3D video dataset with enhanced realism](https://mlsanity.com/paper/2506.24074/) (2025)
- [NR-SLAM: Non-Rigid Monocular SLAM](https://mlsanity.com/paper/2308.04036/) (2023)
- [CudaSIFT-SLAM: multiple-map visual SLAM for full procedure mapping in real human endoscopy](https://mlsanity.com/paper/2405.16932/) (2024)
- [Topological SLAM in colonoscopies leveraging deep features and topological priors](https://mlsanity.com/paper/2409.16806/) (2024)
- [ColonMapper: topological mapping and localization for colonoscopy](https://mlsanity.com/paper/2305.05546/) (2023)
- [3D Densification for Multi-Map Monocular VSLAM in Endoscopy](https://mlsanity.com/paper/2503.14346/) (2025)
- [PERSEUS: Perception with Semantic Endoscopic Understanding and SLAM](https://mlsanity.com/paper/2509.13541/) (2025)
- [EndoStreamDepth: Temporally Consistent Monocular Depth Estimation for Endoscopic Video Streams](https://mlsanity.com/paper/2512.18159/) (2025)
- [ColonSplat: Reconstruction of Peristaltic Motion in Colonoscopy with Dynamic Gaussian Splatting](https://mlsanity.com/paper/2603.06860/) (2026)

## Abstract (arXiv)

Background and Objective: Colonoscopy recording practice preserves text reports and still photographs, while the spatial information already present in the recorded video - where the scope traveled, where a lesion was observed, and whether the same lesion was seen again - is discarded when the procedure ends. This study determines whether a lesion-centered spatial record can be assembled and validated without full-colon 3D reconstruction. Methods: A four-layer hierarchical pipeline was assembled - (1) a global topological map, (2) lesion-level spatio-temporal tracks, (3) on-demand local 3D reconstruction, and (4) persistent lesion identity across repeated observations - and ran end to end on four public videos (two C3VDv2 sequences with ground-truth depth and two full REAL-Colon procedures; 40,245 frames). All components are published, individually validated methods; the contribution is their lesion-centered assembly, linking rules, and evaluation. Results: Revisits, impossible under forward-only mapping by construction, were detected by entry-map Bayesian localization: 5,614 and 4,043 revisit events (56 and 68 distinct nodes) in the two full procedures. Lesion-identity merging at the adopted threshold 0.5 maintained ground-truth purity 1.0 while auto-merging 20 of 231 candidate pairs. The endoscopy-specific geometry engine outperformed a general-purpose foundation model on all metrics (overall absolute relative error (AbsRel) 0.2276 vs. 0.3523). Conclusions: The results are partial but establish a concrete near-term path: revisit detection, lesion identity, and local 3D each returned quantitative, reproducible output without waiting for complete geometric reconstruction; validating the record on clinical data is the next step.