Parallel Implementations Assessment of a Spatial-Spectral Classifier for Hyperspectral Clinical Applications

Abstract

Hyperspectral (HS) imaging presents itself as a non-contact, non-ionizing and non-invasive technique, proven to be suitable for medical diagnosis. However, the volume of information contained in these images makes difficult providing the surgeon with information about the boundaries in real-time.To that end, High-Performance-Computing (HPC) platforms become necessary. This paper presents a comparison between the performances provided by five different HPC platforms while processing a spatialspectral approach to classify HS images, assessing their main benefits and drawbacks. To provide a complete study, two different medical applications, with two different requirements, have been analyzed. The first application consists of HS images taken from neurosurgical operations; the second one presents HS images taken from dermatological interventions. While the main constraint for neurosurgical applications is the processing time, in other environments, as the dermatological one, other requirements can be considered. In that sense, energy efficiency is becoming a major challenge, since this kind of applications are usually developed as hand-held devices, thus depending on the battery capacity. These requirements have been considered to choose the target platforms: on the one hand, three of the most powerful Graphic Processing Units (GPUs) available in the market; and, on the other hand, a low-power GPU and a manycore architecture, both specifically thought for being used in battery-dependent environments.INDEX TERMS Hyperspectral imaging, high performance computing, parallel processing, parallel architectures, image processing, biomedical engineering, medical diagnostic imaging, cancer detection, supervised classification, support vector machines, K-nearest neighbors, principal component analysis, graphic processing unit, manycore.

Parallel Classification Pipelines for Skin Cancer Detection Exploiting Hyperspectral Imaging on Hybrid Systems

“…The state of the art relies on hybrid systems including multicore and many-core devices. The choice of hybrid systems is justified by the features of the processing chains that typically include algorithms with different levels of complexity [17][18][19][20]. The key idea is that each algorithm is managed by the device that best meets the processing constraints.…”

Gradient Boosting Ensembled Method for in-Vivo Brain Tumour Classification Using Hyperspectral Images

“…In-vitro, exvivo, and in-vivo investigations i.e., whether the scene is obtained from a resected sample (in-vitro, ex-vivo) or directly collected from the patient have all exploited the ability to identify the components inside a gathered image (in vivo). In particular, there is an increasing interest in doing In-Vivo HSI processing during operations to aid in the differentiation of malignant and healthy tissues [Lazcano et al (2019)].…”

GoRG: Towards a GPU-Accelerated Multiview Hyperspectral Depth Estimation Tool for Medical Applications

“…In the particular case of brain cancer detection, addressed in this paper, several works benefited from using HS images in the operation room [13][14][15] to precisely detect the borders of a tumor and to help neurosurgeons during the resection process. All of these works aimed to improve both (i) the quality of the classification maps and the results of HS images, and (ii) the acceleration of the algorithms as much as possible, so the process can be executed in real time.…”