X-RAFT: Cross-Modal Non-Rigid Registration of Blue and White Light Neurosurgical Hyperspectral Images

TL;DR

X-RAFT is a novel deep learning model designed to accurately find dense correspondences between hyperspectral images captured under different lighting conditions in neurosurgery, improving fluorescence quantification.

Contribution

The paper introduces X-RAFT, a cross-modal optical flow model with modality-specific encoders and self-supervised fine-tuning for hyperspectral image registration in neurosurgery.

Findings

Achieved 36.6% error reduction over naive baseline

Reduced error by 27.83% compared to existing methods

Demonstrated effectiveness on neurosurgical hyperspectral data

Abstract

Integration of hyperspectral imaging into fluorescence-guided neurosurgery has the potential to improve surgical decision making by providing quantitative fluorescence measurements in real-time. Quantitative fluorescence requires paired spectral data in fluorescence (blue light) and reflectance (white light) mode. Blue and white image acquisition needs to be performed sequentially in a potentially dynamic surgical environment. A key component to the fluorescence quantification process is therefore the ability to find dense cross-modal image correspondences between two hyperspectral images taken under these drastically different lighting conditions. We address this challenge with the introduction of X-RAFT, a Recurrent All-Pairs Field Transforms (RAFT) optical flow model modified for cross-modal inputs. We propose using distinct image encoders for each modality pair, and fine-tune these in a self-supervised manner using flow-cycle-consistency on our neurosurgical hyperspectral data. We show an error reduction of 36.6% across our evaluation metrics when comparing to a naive baseline and 27.83% reduction compared to an existing cross-modal optical flow method (CrossRAFT). Our code and models will be made publicly available after the review process.