Towards Clinical Hyperspectral Imaging (HSI) Standards: Initial Design for a Microneurosurgical HSI Database

Abstract

Hyperspectral imaging (HSI) can enhance the recognition of normal and pathological tissues exposed during microscopic or endoscopic surgeries. However, robust HSI classification models would require meticulous documentation of the tissue-specific optical properties to account for individual variation and intraoperative factors. Publicly available HSI databases are yet scarce or lack relevant metadata, anatomical accuracy, and patients' characteristics which limits the clinical utility of the data. The essential problem is that clinical standards for HSI acquisition and archival do not exist. We collected a total of 52 microsurgical HSI images from 10 patients using our customized HSI system for the operation microscopes. We annotated the relevant microanatomical structures and labeled the tissue areas intended for HSI analyses. Using the collected HSI data, we developed the initial design of the microneurosurgical HSI database. The HSI database allows to display and query anatomical annotations, localizing magnetic resonance imaging (MRI) scans, operation videos, tissue labels, and HSI spectra per individual patient. Here we present the fundamental structures and functions of the HSI database in development. Our clinical HSI database will provide grounds for further development of HSI algorithms and machine-learning applications in microscopic and endoscopic surgery. Future collaborative research will establish clinical HSI standards with approved supporting technologies.