Hyperspectral imaging benchmark based on machine learning for intraoperative brain tumour detection

Abstract

Brain surgery is one of the most common and effective treatments for brain tumour. However, neurosurgeons face the challenge of determining the boundaries of the tumour to achieve maximum resection, while avoiding damage to normal tissue that may cause neurological sequelae to patients. Hyperspectral (HS) imaging (HSI) has shown remarkable results as a diagnostic tool for tumour detection in different medical applications. In this work, we demonstrate, with a robust k-fold cross-validation approach, that HSI combined with the proposed processing framework is a promising intraoperative tool for in-vivo identification and delineation of brain tumours, including both primary (high-grade and low-grade) and secondary tumours. Analysis of the in-vivo brain database, consisting of 61 HS images from 34 different patients, achieve a highest median macro F1-Score result of 70.2 ± 7.9% on the test set using both spectral and spatial information. Here, we provide a benchmark based on machine learning for further developments in the field of in-vivo brain tumour detection and delineation using hyperspectral imaging to be used as a real-time decision support tool during neurosurgical workflows.

Spectral Analysis Comparison of Pushbroom and Snapshot Hyperspectral Cameras forIn-VivoBrain Tissues and Chromophores Identification

“…Moreover, observations show how the contribution of Hb is slightly higher in pathological tissue than in healthy tissue at λ = 756 nm, which may be related to increased perfusion of tumor tissue, especially in high-grade tumors, or may even be related to lack of oxygen to brain tissue or tumor hypoxia due to abnormalities in tumor vessel structure. 37 Such behaviour was found in other studies using HSI for in-vivo human brain 29 and might also indicate hypoxia from glioma cells. 38 The analysis conducted in Subsection 3.3 aimed to identify any chromophore absorption peaks in the absorbance measurements of the cameras.…”

“…To analyze the absorbance (A) spectral signatures and look for patterns that might indicate the presence of certain chromophores, we will use the reflectance (R) measured by the cameras. A is commonly derived, [27][28][29] for each wavelength, from R using Eq. 4:…”

“…All things considered, the snapshot camera can provide reasonable measurements to describe brain tissue behaviour when compared with the typical linescan cameras used for brain tumor detection. 15,29,39,40 Likewise, the snapshot camera offers great opportunities to provide real-time solutions as employed in other studies. 19 However, combining multiple snapshot cameras to increase the spectral range can lead to a better reconstruction of the spectral behaviour of biological tissues as shown in other works.…”