The main goal of brain cancer surgery is to perform an accurate resection of the tumor, preserving as much normal brain tissue as possible for the patient. The development of a non-contact and label-free method to provide reliable support for tumor resection in real-time during neurosurgical procedures is a current clinical need. Hyperspectral imaging is a non-contact, non-ionizing, and label-free imaging modality that can assist surgeons during this challenging task without using any contrast agent. In this work, we present a deep learning-based framework for processing hyperspectral images of in vivo human brain tissue. The proposed framework was evaluated by our human image database, which includes 26 in vivo hyperspectral cubes from 16 different patients, among which 258,810 pixels were labeled. The proposed framework is able to generate a thematic map where the parenchymal area of the brain is delineated and the location of the tumor is identified, providing guidance to the operating surgeon for a successful and precise tumor resection. The deep learning pipeline achieves an overall accuracy of 80% for multiclass classification, improving the results obtained with traditional support vector machine (SVM)-based approaches. In addition, an aid visualization system is presented, where the final thematic map can be adjusted by the operating surgeon to find the optimal classification threshold for the current situation during the surgical procedure.

Hyperspectral imaging (HSI) allows for the acquisition of large numbers of spectral bands throughout the electromagnetic spectrum (within and beyond the visual range) with respect to the surface of scenes captured by sensors. Using this information and a set of complex classification algorithms, it is possible to determine which material or substance is located in each pixel. The work presented in this paper aims to exploit the characteristics of HSI to develop a demonstrator capable of delineating tumor tissue from brain tissue during neurosurgical operations. Improved delineation of tumor boundaries is expected to improve the results of surgery. The developed demonstrator is composed of two hyperspectral cameras covering a spectral range of 400–1700 nm. Furthermore, a hardware accelerator connected to a control unit is used to speed up the hyperspectral brain cancer detection algorithm to achieve processing during the time of surgery. A labeled dataset comprised of more than 300,000 spectral signatures is used as the training dataset for the supervised stage of the classification algorithm. In this preliminary study, thematic maps obtained from a validation database of seven hyperspectral images of in vivo brain tissue captured and processed during neurosurgical operations demonstrate that the system is able to discriminate between normal and tumor tissue in the brain. The results can be provided during the surgical procedure (~1 min), making it a practical system for neurosurgeons to use in the near future to improve excision and potentially improve patient outcomes.

The detection of (moving or static) targets in remotely sensed hyperspectral images often requires real-time responses for swift decisions that depend upon high computing performance of algorithm analysis. The automatic target detection and classification algorithm (ATDCA) has been widely used for this purpose. In this letter, we develop several optimizations for accelerating the computational performance of ATDCA. The first one focuses on the use of the Gram-Schmidt orthogonalization method instead of the orthogonal projection process adopted by the classic algorithm. The second one is focused on the development of a new implementation of the algorithm on commodity graphics processing units (GPUs). The proposed GPU implementation properly exploits the GPU architecture at low level, including shared memory, and provides coalesced accesses to memory that lead to very significant speedup factors, thus taking full advantage of the computational power of GPUs. The GPU implementation is specifically tailored to hyperspectral imagery and the special characteristics of this kind of data, achieving real-time performance of ATDCA for the first time in the literature. The proposed optimizations are evaluated not only in terms of target detection accuracy but also in terms of computational performance using two different GPU architectures by NVIDIA: Tesla C1060 and GeForce GTX 580, taking advantage of the performance of operations in single-precision floating point. Experiments are conducted using hyperspectral data sets collected by three different hyperspectral imaging instruments. These results reveal considerable acceleration factors while retaining the same target detection accuracy for the algorithm.

One of the main problems in the analysis of remotely sensed hyperspectral data cubes is the presence of mixed pixels, which arise when the spatial resolution of the sensor is not able to separate spectrally distinct materials. Due to this reason, spectral unmixing has become one of the most important tasks for hyperspectral data exploitation. However, unmixing algorithms can be computationally very expensive, a fact that compromises their use in applications under real-time constraints. For this purpose, in this paper we develop two efficient implementations of a full hyperspectral unmixing chain on two different kinds of high performance computing architectures: graphics processing units (GPUs) and multi-core processors. The proposed full unmixing chain is composed for three stages: (i) estimation of the number of pure spectral signatures or endmembers, (ii) automatic identification of the estimated endmembers, and (iii) estimation of the fractional abundance of each endmember in each pixel of the scene. The two computing platforms used in this work are inter-compared in the context of hyperspectral unmixing applications. The GPU implementation of the proposed methodology has been implemented using the compute devide unified architecture (CUDA) and the cuBLAS library, and tested on two different GPU architectures: NVidia™ GeForce GTX 580 and NVidia™ Tesla C1060. It provides real-time unmixing performance in two different analysis scenarios using hyperspectral data collected by NASA's Airborne Visible Infra-Red Imaging Spectrometer (AVIRIS) over the Cuprite mining district in Nevada and the World Trade Center complex in New York City. The multi-core implementation, developed using the applications program interface (API) OpenMP and the Intel Math Kernel Library (MKL) used for matrix multiplications, achieved near real-time performance in the same scenarios. A comparison of both architectures in terms of performance, cost and mission payload considerations is given based on the results obtained in the two considered data analysis scenarios.

The use of hyperspectral imaging (HSI) in the medical field is an emerging approach to assist physicians in diagnostic or surgical guidance tasks. However, HSI data processing involves very high computational requirements due to the huge amount of information captured by the sensors. One of the stages with higher computational load is the K-Nearest Neighbors (KNN) filtering algorithm. The main goal of this study is to optimize and parallelize the KNN algorithm by exploiting the GPU technology to obtain real-time processing during brain cancer surgical procedures. This parallel version of the KNN performs the neighbor filtering of a classification map (obtained from a supervised classifier), evaluating the different classes simultaneously. The undertaken optimizations and the computational capabilities of the GPU device throw a speedup up to 66.18× when compared to a sequential implementation.

In this paper, a performance evaluation of the state-of-the-art H.264/AVC video coding standard is carried out with the aim of determining its feasibility when applied to hyperspectral image compression. Results are obtained based on configuring diverse parameters in the encoder in order to achieve an optimal trade-off between compression ratio, accuracy of unmixing and computation time. In this sense, simulations are developed in order to measure the spectral angles and signal-to-noise ratio (SNR), achieving compression ratios up to 0.13 bits per pixel per band (bpppb) for real hyperspectral images. Moreover, in this work it is detected which blocks in the encoder contribute the most to performance improvements of the compression task for the particular case of this type of images, and which ones are not relevant at all and hence could be removed. This conclusion yields to reduce the future design complexities of potential low-power/real-time hyperspectral encoders based on H.264/AVC for remote sensing applications.