Intraoperative Guidance Using Hyperspectral Imaging: A Review for Surgeons

Abstract

Hyperspectral imaging (HSI) is a novel optical imaging modality, which has recently found diverse applications in the medical field. HSI is a hybrid imaging modality, combining a digital photographic camera with a spectrographic unit, and it allows for a contactless and non-destructive biochemical analysis of living tissue. HSI provides quantitative and qualitative information of the tissue composition at molecular level in a contrast-free manner, hence making it possible to objectively discriminate between different tissue types and between healthy and pathological tissue. Over the last two decades, HSI has been increasingly used in the medical field, and only recently it has found an application in the operating room. In the last few years, several research groups have used this imaging modality as an intraoperative guidance tool within different surgical disciplines. Despite its great potential, HSI still remains far from being routinely used in the daily surgical practice, since it is still largely unknown to most of the surgical community. The aim of this study is to provide clinical surgeons with an overview of the capabilities, current limitations, and future directions of HSI for intraoperative guidance.

Review on the Application of Hyperspectral Imaging Technology of the Exposed Cortex in Cerebral Surgery

“…Although machine learning methods and deep learning method are used extensively in brain cancer diagnosis, the integrity of data information and the timeliness of data processing are still the shortcomings of these methods ( Barberio et al, 2021 ). More recently, several research groups are focusing on hybrid deep learning method for clinical diagnosis of brain cancer ( Rinesh et al, 2022 ).…”

AI-based segmentation of intraoperative glioblastoma hyperspectral images

“…Stages-1, 2 and 3 denote cells which are cancerous and spreading rapidly. In Stage-4, cancer spreads throughout the body 2,4 . Glioblastoma (GB -grade IV) is the most deadly and typical brain tumour retaining a 5-year survival rate of 5.5%.…”

Staging of Skin Cancer Based on Hyperspectral Microscopic Imaging and Machine Learning

“…The spectral data in the HMI cube reveal the internal microenvironment changes in the samples through parameters such as waveform and intensity, and the microscopic image data can intuitively reflect the sample’s differences in structure with high spatial resolution. At the same time, the combination of HMI and machine learning can assist doctors in diagnosis and greatly improve the efficiency and accuracy of the diagnosis, as well as having a wide field of application in the future [ 3 , 4 , 5 , 6 , 7 ].…”