Driving · 2026-10-07

A Belief-State World Model for Catheter Navigation under Sparse Fluoroscopy: A Planar Proof of Concept

Damini Rijhwani

AI-assisted summary based on the paper. Consult the linked source for methods and limitations. Benchmark numbers appear after editor verification.

TL;DR

The authors present a POMDP “belief-state world model” for catheter navigation under sparse fluoroscopy, using a Cosserat rod simulator for transitions, sparse noisy projections for observations, and a particle filter to maintain belief and calibrated uncertainty. In a synthetic planar vessel phantom, the belief model tracks tip position with RMSE 1.30 mm at one-fifteenth frame rate and maintains near-nominal 90% credible coverage (0.92 empirical coverage).

Why it matters

The paper argues that sparse-imaging world models must maintain calibrated belief, not just low point-estimate error, because unsafe use of confident but wrong estimates is worse than no assistance. The authors evaluate uncertainty calibration (credible-region coverage) and safety-relevant contact-risk discrimination (AUROC) as observation sparsity increases, showing belief updates preserve calibration where an open-loop model becomes overconfident.

Method

Formulate sparse-fluoroscopy catheter navigation as a POMDP: Cosserat-rod-based transition model, sparse noisy 1D projection observations, and a belief over device state maintained by a particle filter.
In a planar proof-of-concept, use a quasi-static planar rod simulator and reduce the particle state to tip parameters (tip position, heading, inserted length) with a geometric contact proxy.
Evaluate belief calibration under sparsification by reporting tip RMSE, empirical coverage of 90% credible regions, and contact-risk AUROC across observation intervals.

Limitation

The experiments are a proof of concept in controlled planar simulation: synthetic planar phantom with quasi-static, pure-bending rod model; 1D projection with Gaussian noise omits fluoroscopic physics, segmentation errors, and occlusion; particle state tracks tip parameters rather than full rod, so the contact proxy cannot benefit from assimilation; no clinical/animal data and no human operator.

Abstract (from arXiv)

Endovascular catheter navigation relies on continuous fluoroscopy, exposing patients and clinical staff to ionizing radiation throughout the procedure. We investigate whether a physics-based world model can sustain the navigation task between deliberately sparse X-ray acquisitions, and whether the model can signal when its internal state estimate is no longer reliable. We formulate sparse-fluoroscopy navigation as a partially observable Markov decision process where a Cosserat rod simulator supplies transition dynamics, sparse noisy projections provide observations, and a particle filter maintains a belief over the device state, reduced in this implementation to a tip state with a geometric contact proxy. We evaluate this formulation in a deliberately simplified setting: a synthetic planar vessel phantom with a quasi-static rod model and simulated projections, without clinical or animal data. In this setting, the belief-state model tracks the simulated tip with a root mean square error of 1.30 mm while acquiring observations at one fifteenth of the continuous rate (0.97 mm at every frame, 1.51 mm at one thirtieth), reported 90 percent credible intervals achieve 0.92 empirical coverage, and the belief-derived contact risk estimate discriminates unsafe contact events with an AUROC of 0.68. These results constitute a proof of concept on a simplified simulation rather than a demonstration of clinical readiness; their purpose is to establish that calibrated belief, rather than point-estimate accuracy alone, is the essential property a sparse-imaging world model must deliver.

Publication record

Bibliographic evidence describes where and when a record appeared. It does not validate scientific claims.

First public release: 2026-10-06 · Indexed by Pub-AI: 2026-10-07 UTC

preprint