Out of distribution detection for intra-operative functional imaging

TL;DR

This paper introduces an information theory-based method using WAIC and invertible neural networks to detect out-of-distribution spectra in intra-operative multispectral imaging, enhancing reliability in surgical tissue analysis.

Contribution

It presents a novel OoD detection approach leveraging WAIC and invertible neural networks, tailored for real-time intra-operative multispectral imaging.

Findings

Effective OoD detection on in silico and in vivo data

Improves reliability of tissue parameter estimation during surgery

Potential to prevent spurious results in clinical settings

Abstract

Multispectral optical imaging is becoming a key tool in the operating room. Recent research has shown that machine learning algorithms can be used to convert pixel-wise reflectance measurements to tissue parameters, such as oxygenation. However, the accuracy of these algorithms can only be guaranteed if the spectra acquired during surgery match the ones seen during training. It is therefore of great interest to detect so-called out of distribution (OoD) spectra to prevent the algorithm from presenting spurious results. In this paper we present an information theory based approach to OoD detection based on the widely applicable information criterion (WAIC). Our work builds upon recent methodology related to invertible neural networks (INN). Specifically, we make use of an ensemble of INNs as we need their tractable Jacobians in order to compute the WAIC. Comprehensive experiments with in silico, and in vivo multispectral imaging data indicate that our approach is well-suited for OoD detection. Our method could thus be an important step towards reliable functional imaging in the operating room.