Hyperspectral imaging techniques (HSI) do not require contact with patients and are non-ionizing as well non-invasive. As a consequence, they have been extensively applied in the medical field. HSI is being combined machine learning (ML) processes to obtain models assist diagnosis. In particular, combination of these has proven be reliable aid differentiation healthy tumor tissue during brain surgery. ML algorithms such support vector (SVM), random forest (RF) convolutional neural networks...

Future video coding (FVC) will be the next generation standard. Yet in first stages of standardization process, it is expected to replace high efficiency beyond 2020. One enhancements discussion adaptive multiple core transform, which uses five different types 2-D discrete sine/cosine transforms (DCT-II, DCT-V, DCT-VIII, DST-I, and DST-VII) up 64 x transform unit sizes. This schema, increases computational complexity both, encoder decoder. In this paper, a deeply pipelined performance...

Versatile video coding (VVC) will be the next generation standard, which is expected to replace HEVC in CE devices, such as tablets, smartphones, and TV sets beyond 2020. The new standard still based on transform, quantization, entropy coding, but a multiple transform selection scheme has been proposed, involving three different types of 2-D Discrete Sine/Cosine transforms (DCT-II, DCT-VIII, DST-VII), unit sizes range from 4×4 64×64. To handle computational complexity these algorithms, it...

Over the last two decades, augmented reality (AR) has led to rapid development of new interfaces in various fields social and technological application domains. One such domain is medicine, a higher extent surgery, where these visualization techniques help improve effectiveness preoperative intraoperative procedures. Following this trend, paper presents SLIMBRAIN, real-time acquisition processing AR system suitable classify display brain tumor tissue from hyperspectral (HS) information. This...

Magnetic resonance imaging (MRI) is a common technique in image-guided neurosurgery (IGN). Recent research explores the integration of methods like ultrasound and tomography, among others, with hyperspectral (HS) gaining attention due to its non-invasive real-time tissue classification capabilities. The main challenge registration process, often requiring manual intervention. This work introduces an automatic, markerless method for aligning HS images MRI.

High Efficiency Video Coding (HEVC) is a new video coding standard created by the JCT-VC group within ISO/IEC and ITU-T. HEVC targeted to provide same quality as H.264 at about half of bit-rate will replace soon its predecessor in multimedia consumer applications. Up now, only few decoder implementations have been reported, most them oriented carry out complexity analysis. In this paper, DSP-based implementation HM9.0 presented. best our knowledge, it first shown scientific literature....

Versatile video coding (VVC) will be released by 2020, and it is expected to the nextgeneration standard. One of its enhancements multiple transform selection (MTS) for core transform. MTS uses three different types 2D discrete sine/cosine transforms (DCT-II, DCT-VIII DST-VII) up 64 × unit sizes. With this schema, significant compression ratio are obtained at expense more computational complexity on both encoders decoders. In paper, a deeply pipelined high-performance architecture proposed...

<title>Abstract</title> <bold>Purpose</bold>: This study proposes a generalization of markerless patient registration in image-guided neurosurgery based on depth information. The work builds previous research to evaluate the performance range commercial cameras and two different algorithms this context. <bold>Methods</bold>: A multimodal experimental setup was used, testing five seven configurations. Fiducial Registration Error (FRE) Target (TRE) metrics were calculated using Iterative...

Abstract Purpose This study proposes a generalization of markerless patient registration in image-guided neurosurgery based on depth information. The work builds previous research to evaluate the performance range commercial cameras and two different algorithms this context. Methods A multimodal experimental setup was used, testing five seven configurations. Fiducial error (FRE) target (TRE) metrics were calculated using iterative closest point (ICP) deep global (DGR) algorithms. phantom...

Abstract In recent years, the global demand for high-resolution videos and emergence of new multimedia applications have created need a video coding standard. Therefore, in July 2020, versatile (VVC) standard was released, providing up to 50% bit-rate savings same quality compared its predecessor high-efficiency (HEVC). However, these come at cost high computational complexity, particularly live on resource-constrained embedded devices. This paper evaluates two optimized VVC software...

During the last decades, new video compression standards arose every few years with always higher gains and considerable increases on computational cost. Single core processors have reached their limit multicore are there to overcome this issue give more processing power. In order accelerate implementation of coding standards, MPEG has standardized an alternative framework describe decoders. It is based reference decoders written in RVC CAL dataflow actor language. From these descriptions, a...

Video coding is one of the most demanding applications, in terms computational cost, for portable multimedia terminals. In last years, new video standards, like High Efficiency Coding (HEVC), and increasing resolutions codecs have overtaken capacities single core processors embedded systems. consequence, multicore architectures are used current Besides, methodologies frameworks arising to speed-up design cycle. this paper, a methodology based on Reconfigurable CAL Actor Language (RVC-CAL)...

The current state-of-the-art video coding standard versatile (VVC) offers 50% bit rate savings over its predecessor high efficiency (HEVC) while maintaining the same quality at cost of a significant increase in computational complexity. In this work, an Embedded General Purpose Processor (EGPP) with Single Instruction Multiple Data (SIMD) optimisations suite was used to accelerate open-source software decoder for achieving real-time decoding embedded multi-core platform 8 cores. speedup has...

Hyperspectral (HS) imaging (HSI) techniques have demonstrated to be useful in the medical field characterize tissues without any contact and ionizing patient. Besides, HSI combined with supervised machine learning (ML) algorithms proven an effective technique assist neurosurgeons resect brain tumors. This research looks at effects of hyperparameter optimization on two common ML used for tumor classification: support vector machines (SVM) random forest (RF). Correctly classifying HS data...

Hyperspectral Imaging (HSI) can be used as a non invasive medical diagnostic method when in combination with Machine Learning (ML) algorithms. The significant captured data HSI useful for classifying different types of brain tissues, since they gather reflectance values from band widths below and beyond the visual spectrum. This allows ML algorithms like Support Vector Machines (SVM) Random Forest (RF) to classify tissues such tumors. Predicted results create visualizations support...

This paper explains how the Open Reconfigurable Video Coding CAL Actor Language compiler framework (Orcc) has been used, along with Multi-Processing (OpenMP) API, to implement an HEVC video decoder based on multicore DSP technology. Currently, two cores have though technique may be applied development of N-core implementations. The core presented in this outperforms a single implementation by 70%.

HyperSpectral (HS) images have been successfully used for brain tumor boundary detection during resection operations. Nowadays, these classification maps coexist with other technologies such as MRI or IOUS that improve a neurosurgeon’s action, their incorporation being task. The project in which this work is framed generates an unified and more accurate 3D immersive model using HS, MRI, information. To do so, the HS need to include information it needs be generated real-time operating room...

<title>Abstract</title> Gliomas constitute a significant challenge in neurosurgery due to their high incidence and poor prognosis. Despite advancements tumor detection techniques using machine learning approach with hyperspectral imaging, accurately distinguishing between healthy tumoral tissues remains challenging. Following this trend, paper introduces Libra, low spectral resolution classifier designed for brain detection, leveraging ensemble enhance classification performance. Evaluated...

The Open RVC CAL compiler infrastructure allows the definition and simulation of complex algorithms as a set interconnected dataflow actors using RVC-CAL actor language well automatic generation C code for number target processors, like ARM or x86 based cores. Though multicore processors may also be generated, mapping among cores is carried out by hand. With algorithms, usually described with tens actors, this procedure requires expertise deep knowledge algorithms. In paper, an tool to...

This paper explains the design of a new back-end for Open Reconfigurable Video Coding CAL Actor Language compiler framework (Orcc). uses OpenMP API instead pthreads library to automatically generate C code any multicore architecture with support. With this back-end, implementations an HEVC decoder have been generated and tested three different target architectures. The does not introduce performance penalty regarding actual enables use architectures, such as DSPs.