Hyperspectral imaging for noninvasive tissue perfusion measurements of the lower leg: review of literature and introduction of a standardized measurement protocol with a portable system

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

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.

Determination of Changes in Tissue Perfusion at Home with Hyperspectral and Thermal Imaging in the First Six Weeks after Endovascular Therapy in Patients with Peripheral Arterial Disease

The aims of this study were to assess changes in tissue perfusion up to 6 weeks after endovascular therapy (EVT), in hospital and at home, and to determine differences in tissue perfusion between patients with and without clinical improvement or good angiographic result. This single-center prospective cohort study included patients undergoing EVT for Rutherford stages two to six. Hyperspectral and thermal imaging were performed at the dorsal and plantar sides of the foot. These measurements consisted of a baseline measurement pre-EVT, and six follow-up measurements obtained at 1 and 4 h and 6 weeks in hospital, and 1 day, 7 days, and 14 days at home. Clinical improvement was defined as a decrease of one or more Rutherford class or decrease in the wound surface area and a good angiographic result was accomplished when a Transatlantic Inter-Society Consensus for the Management of PAD II C or D lesion was treated and uninterrupted flow continued in at least one below-the-knee artery in continuation with the inframalleolar arteries. The study included 34 patients with 41 treated limbs. Deoxyhemoglobin values were lower 1 h post-EVT compared with baseline and increased over time up to 6 weeks post-EVT. Significant differences in deoxyhemoglobin levels at 7 and 14 days post-EVT were determined between patients with and without clinical or angiographic success. This prospective pilot study shows the feasibility of hyperspectral imaging and thermal imaging post-EVT at home, which may decrease the need for hospital visits.

VNIR-NIR hyperspectral imaging fusion targeting intraoperative brain cancer detection

Currently, intraoperative guidance tools used for brain tumor resection assistance during surgery have several limitations. Hyperspectral (HS) imaging is arising as a novel imaging technique that could offer new capabilities to delineate brain tumor tissue in surgical-time. However, the HS acquisition systems have some limitations regarding spatial and spectral resolution depending on the spectral range to be captured. Image fusion techniques combine information from different sensors to obtain an HS cube with improved spatial and spectral resolution. This paper describes the contributions to HS image fusion using two push-broom HS cameras, covering the visual and near-infrared (VNIR) [400–1000 nm] and near-infrared (NIR) [900–1700 nm] spectral ranges, which are integrated into an intraoperative HS acquisition system developed to delineate brain tumor tissue during neurosurgical procedures. Both HS images were registered using intensity-based and feature-based techniques with different geometric transformations to perform the HS image fusion, obtaining an HS cube with wide spectral range [435–1638 nm]. Four HS datasets were captured to verify the image registration and the fusion process. Moreover, segmentation and classification methods were evaluated to compare the performance results between the use of the VNIR and NIR data, independently, with respect to the fused data. The results reveal that the proposed methodology for fusing VNIR–NIR data improves the classification results up to 21% of accuracy with respect to the use of each data modality independently, depending on the targeted classification problem.