Descripción
|
|
---|---|
Hyperspectral Imaging (HI) involves collection of a massive amount of spectral and spatial information structured in hundreds of bands, with each band covering a narrow and contiguous portion of the electromagnetic spectrum. This approach provides a data-cube of spectral information which consists of a series of optical images recorded at various wavelengths of interest. By analysing the reflectance, emittance or fluorescence of every spatial pixel in the hyperspectral image, a better determination of the chemical structure of the material under evaluation is achieved. The main goal of Helicoid is to apply hyperspectral imaging techniques for the precise localization of malignant tumours during surgical procedures. This project will develop an experimental intraoperative setup based on non-invasive hyperspectral cameras connected to a platform running a set of algorithms capable of discriminate between healthy or pathological tissues. This information will be provided, through different display devices, to the surgeon, overlapping normal viewing images with simulated colours that will indicate the cancer probability of the tissue presently exposed during throughout the surgical procedure. A prototype will be developed with the aim of recognising cancer tissues during the surgical procedure. HI requires extensive data processing. To meet the real-time and in-vivo cancer detection requirement, a hardware/software partition of the final platform will be derived from the computational load required by the final developed algorithms. This project is expected to open new avenues in the diagnosis of cancer. If hyperspectral imaging demonstrates to be a reliable method for cancer detection and it can be done in real-time, the following aspects could be envisioned: Accurate assistance on cancer detection during specific surgical procedures, i.e. surgical procedures intended for cancer resection. Automatic monitoring of different surgical procedures, i.e. having the proposed system active during other surgical procedures to detect cancer presence. This will help in the prevention of cancer on its very early stages. Moreover, the surgeon will pay attention to the current clinical target while the cancer detection system will be on automatic mode. Cross-fertilization of the main results to other fields of the medicine, not only restricted to cancer. Hyperspectral Imaging Systems (HIS) have demonstrated to properly detect ischemia and is able to discriminate between arterial and venous blood. The potential of HIS applied to medicine is something to be still fully analysed and developed. Facilitate the creation of a European industry based on HIS for medical applications. From the detailed analysis of the results obtained in this project, a more economical and efficient solution for industrial exploitation could be obtained. On the one side, removing the use of frequencies not directly involved in the cancer detection and sampling with higher precision those frequencies which have demonstrated to play a crucial role in the algorithms for cancer detection. On the other side, with an optimization of the computing platform, keeping only the computing cores and accelerators needed for the cancer detection. This dual shrinkage would lead to a cheaper final system, making the system to be profitable. | |
Internacional
|
Si |
Tipo de proyecto
|
Proyectos y convenios en convocatorias públicas competitivas |
Entidad financiadora
|
UE/FP7 |
Nacionalidad Entidad
|
Sin nacionalidad |
Tamaño de la entidad
|
Desconocido |
Fecha concesión
|
09/09/2013 |