HELICoiD project: a new use of hyperspectral imaging for brain cancer detection in real-time during neurosurgical operations

Abstract

Hyperspectral images allow obtaining large amounts of information about the surface of the scene that is captured by the sensor. Using this information and a set of complex classification algorithms is possible to determine which material or substance is located in each pixel. The HELICoiD (HypErspectraL Imaging Cancer Detection) project is a European FET project that has the goal to develop a demonstrator capable to discriminate, with high precision, between normal and tumour tissues, operating in real-time, during neurosurgical operations. This demonstrator could help the neurosurgeons in the process of brain tumour resection, avoiding the excessive extraction of normal tissue and unintentionally leaving small remnants of tumour. Such precise delimitation of the tumour boundaries will improve the results of the surgery. The HELICoiD demonstrator is composed of two hyperspectral cameras obtained from Headwall. The first one in the spectral range from 400 to 1000 nm (visible and near infrared) and the second one in the spectral range from 900 to 1700 nm (near infrared). The demonstrator also includes an illumination system that covers the spectral range from 400 nm to 2200 nm. A data processing unit is in charge of managing all the parts of the demonstrator, and a high performance platform aims to accelerate the hyperspectral image classification process. Each one of these elements is installed in a customized structure specially designed for surgical environments. Preliminary results of the classification algorithms offer high accuracy (over 95%) in the discrimination between normal and tumour tissues.

Intraoperative multispectral and hyperspectral label‐free imaging: A systematic review of in vivo clinical studies

“…Their pilot studies demonstrated that HSI renal oxygenation data may help to predict those patients at risk of postoperative renal insufficiency and may distinguish between patients with otherwise similar baseline characteristics such as eGFR . To date, the HELICoiD group are the only ones to have used HSI to perform in vivo intraoperative tissue characterization and successfully demonstrated that HSI may be used to discriminate between normal brain tissue, tumour tissue, hypervascularised tissue, and background with high specificity and sensitivity using an intra‐patient 10‐fold cross‐validation method.…”

“…Based on the available data, the time taken to acquire a complete hyperspectral cube dataset was calculated to take between 5 and 30 seconds. The size and bulkiness of some of the standalone systems, such as the one used in HELICoiD studies , also made it difficult to easily integrate its use into the standard surgical workflow which in turn reduced the amount of training data acquired and the image processing speed.…”

Porting a PCA-based hyperspectral image dimensionality reduction algorithm for brain cancer detection on a manycore architecture

“…Likewise, the eigenvectors associated to these eigenvalues can be calculated as depicted in (8), where the eigenvectors are placed in the columns of E.…”

“…Related literature shows an increasing research interest concerning the performance of in-vivo HI processing during medical procedures to assist surgeons in discerning between tumor tissues and healthy tissues [8] [9]. Furthermore, to help surgeons in determining the margins of the tumor during surgery, a real-time analysis of the hyperspectral image becomes compulsory, considering this real-time as the time needed for the hyperspectral sensor to capture a new image.…”

“…As nowadays hyperspectral sensors usually present a push-broom scanning mechanism, real-time in this context can be set to a maximum of 1 picture per minute. Neurosurgeons have stated that a processing time of one image per minute is sufficient to assist them during an operation [8]. Processing a diagnostic helping image in less than 1 minute is not possible with the existing alternative to HI, which is the Intraoperative Magnetic Resonance Imaging (iMRI) that usually needs more than thirty minutes to acquire one image [10].…”