Severity of Disorganization of Retinal Layers and Visual Function Impairment in Diabetic Retinopathy.

PURPOSE: To evaluate best-corrected visual acuity (BCVA), retina sensitivity (RS), and fixation impairment by microperimetry (MP) due to the presence and severity of disorganization of retinal inner and outer layers (DRIL/DROL) and ischemia in OCT/OCT angiography (OCTA) in diabetic retinopathy (DR). DESIGN: Retrospective case-control study. SUBJECTS: Seventy-six eyes (65 patients) with DR were analyzed. Major exclusion criteria were: center-involving diabetic macular edema (DME), significant media opacity, nondiabetic macular pathology, and active proliferative DR. Patients with DRIL and DROL within central 3 mm were enrolled as cases. Patients with DR and no retina disorganization were considered as controls. METHODS: A detailed grading of MP and OCT/OCTA images using Image J software, and specific Image Manipulation Program was applied to colocalize the presence of retina disorganization and RS. Best-corrected visual acuity and RS were correlated with the disorganization of retina layers' characteristics and grading (grade 1-DRIL; grade 2-DROL; grade 3-DROL plus, with involvement of the ellipsoid zone). The same procedure of colocalization was applied to the vascular layers on OCTA using MATLAB. MAIN OUTCOME MEASURES: Correlation between BCVA and MP parameters with disorganization of retina layers grading and OCTA parameters. RESULTS: Best-corrected visual acuity, mean RS within 1 mm and central 3 mm (overall RS [oRS]), perfusion density, vessel density, and geometric perfusion deficit in intermediate and deep capillary plexuses were lower in cases versus controls (P < 0.001). Mean RS within 1 mm (21.4 decibels [dB] ± 2.4 vs. 13.8 dB ± 5.4, P = 0.002), oRS (22.0 dB ± 2.1 vs. 14.4 dB ± 4.6, P < 0.001), and BCVA (76.1 ± 7.4 vs. 61.2 ± 20.4 ETDRS letters; P = 0.02), had a significant decrease from grade 1 to grade 3 retina disorganization. Choriocapillaris flow voids (CC-FVs) increased from grade 1 to grade 3 (DROL plus) (P = 0.004). Overall retina sensitivity and CC-FV were identified as significant predictors of retina disorganization grade with an adjusted coefficient of determination, R2 = 0.45. Cases had more dense scotomas (P = 0.03) than controls with a positive correlation between the worsening of fixation stability and the severity of DRIL/DROL (P = 0.04). CONCLUSIONS: Microperimetry and BCVA documented a reduction in visual function in patients with DR and disorganization of retina layers at different grades, with greater functional impairment when outer retina layers and photoreceptors are involved. The severity of retina disorganization and the presence of ischemia could serve as a potential biomarker of functional impairment. FINANCIAL DISCLOSURES: Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

Acceleration of Hyperspectral Skin Cancer Image Classification through Parallel Machine-Learning Methods.

Hyperspectral imaging (HSI) has become a very compelling technique in different scientific areas; indeed, many researchers use it in the fields of remote sensing, agriculture, forensics, and medicine. In the latter, HSI plays a crucial role as a diagnostic support and for surgery guidance. However, the computational effort in elaborating hyperspectral data is not trivial. Furthermore, the demand for detecting diseases in a short time is undeniable. In this paper, we take up this challenge by parallelizing three machine-learning methods among those that are the most intensively used: Support Vector Machine (SVM), Random Forest (RF), and eXtreme Gradient Boosting (XGB) algorithms using the Compute Unified Device Architecture (CUDA) to accelerate the classification of hyperspectral skin cancer images. They all showed a good performance in HS image classification, in particular when the size of the dataset is limited, as demonstrated in the literature. We illustrate the parallelization techniques adopted for each approach, highlighting the suitability of Graphical Processing Units (GPUs) to this aim. Experimental results show that parallel SVM and XGB algorithms significantly improve the classification times in comparison with their serial counterparts.

Ambient assisted living for frail people through human activity recognition: state-of-the-art, challenges and future directions.

Ambient Assisted Living is a concept that focuses on using technology to support and enhance the quality of life and well-being of frail or elderly individuals in both indoor and outdoor environments. It aims at empowering individuals to maintain their independence and autonomy while ensuring their safety and providing assistance when needed. Human Activity Recognition is widely regarded as the most popular methodology within the field of Ambient Assisted Living. Human Activity Recognition involves automatically detecting and classifying the activities performed by individuals using sensor-based systems. Researchers have employed various methodologies, utilizing wearable and/or non-wearable sensors, and employing algorithms ranging from simple threshold-based techniques to more advanced deep learning approaches. In this review, literature from the past decade is critically examined, specifically exploring the technological aspects of Human Activity Recognition in Ambient Assisted Living. An exhaustive analysis of the methodologies adopted, highlighting their strengths and weaknesses is provided. Finally, challenges encountered in the field of Human Activity Recognition for Ambient Assisted Living are thoroughly discussed. These challenges encompass issues related to data collection, model training, real-time performance, generalizability, and user acceptance. Miniaturization, unobtrusiveness, energy harvesting and communication efficiency will be the crucial factors for new wearable solutions.

LONGITUDINAL MICROVASCULAR AND NEURONAL RETINAL EVALUATION IN PATIENTS WITH DIABETES MELLITUS TYPES 1 AND 2 AND GOOD GLYCEMIC CONTROL.

PURPOSE: To evaluate microvascular and neuronal changes over 3 years in patients with Type 1/2 diabetes mellitus (DM1/DM2), good metabolic control, and no signs of diabetic retinopathy. METHODS: In this prospective, longitudinal study, 20 DM1, 48 DM2, and 24 controls underwent macular optical coherence tomography and optical coherence tomography angiography at baseline and after 3 years. Following parameters were considered: thickness of the central macula, retinal nerve fiber layer, ganglion cell (GCL+/GCL++) complex; perfusion and vessel density and fractal dimension at the superficial and deep capillary plexuses; choriocapillaris flow deficits; and foveal avascular zone metrics. MATLAB and ImageJ were used for optical coherence tomography angiography scans analyses. RESULTS: The mean HbA1c was 7.4 ± 0.8% in DM1 and 7.2 ± 0.8% in DM2 at baseline, with no change at 3 years. No eye developed diabetic retinopathy. In longitudinal analyses, perfusion density at superficial capillary plexuses ( P = 0.03) and foveal avascular zone area and perimeter ( P < 0.0001) significantly increased in DM2 compared with other groups. No longitudinal changes occurred in optical coherence tomography parameters. In comparisons within groups, DM2 had a significant thinning of GCL++ in the outer ring, decreased perfusion density at deep capillary plexuses and choriocapillaris flow deficits, and increase in foveal avascular zone perimeter and area in deep capillary plexuses; DM1 had an increase in foveal avascular zone perimeter in deep capillary plexuses ( P < 0.001 for all comparisons). CONCLUSION: Longitudinal data showed significant microvascular retinal changes in DM2. No changes were detected in neuronal parameters and in DM1. Longer and larger studies are needed to confirm these preliminary data.

Perceptive SARS-CoV-2 End-To-End Ultrasound Video Classification through X3D and Key-Frames Selection.

The SARS-CoV-2 pandemic challenged health systems worldwide, thus advocating for practical, quick and highly trustworthy diagnostic instruments to help medical personnel. It features a long incubation period and a high contagion rate, causing bilateral multi-focal interstitial pneumonia, generally growing into acute respiratory distress syndrome (ARDS), causing hundreds of thousands of casualties worldwide. Guidelines for first-line diagnosis of pneumonia suggest Chest X-rays (CXR) for patients exhibiting symptoms. Potential alternatives include Computed Tomography (CT) scans and Lung UltraSound (LUS). Deep learning (DL) has been helpful in diagnosis using CT scans, LUS, and CXR, whereby the former commonly yields more precise results. CXR and CT scans present several drawbacks, including high costs. Radiation-free LUS imaging requires high expertise, and physicians thus underutilise it. LUS demonstrated a strong correlation with CT scans and reliability in pneumonia detection, even in the early stages. Here, we present an LUS video-classification approach based on contemporary DL strategies in close collaboration with Fondazione IRCCS Policlinico San Matteo's Emergency Department (ED) of Pavia. This research addressed SARS-CoV-2 patterns detection, ranked according to three severity scales by operating a trustworthy dataset comprising ultrasounds from linear and convex probes in 5400 clips from 450 hospitalised subjects. The main contributions of this study are related to the adoption of a standardised severity ranking scale to evaluate pneumonia. This evaluation relies on video summarisation through key-frame selection algorithms. Then, we designed and developed a video-classification architecture which emerged as the most promising. In contrast, the literature primarily concentrates on frame-pattern recognition. By using advanced techniques such as transfer learning and data augmentation, we were able to achieve an F1-Score of over 89% across all classes.

Evaluation of Preprocessing Methods on Independent Medical Hyperspectral Databases to Improve Analysis.

Currently, one of the most common causes of death worldwide is cancer. The development of innovative methods to support the early and accurate detection of cancers is required to increase the recovery rate of patients. Several studies have shown that medical Hyperspectral Imaging (HSI) combined with artificial intelligence algorithms is a powerful tool for cancer detection. Various preprocessing methods are commonly applied to hyperspectral data to improve the performance of the algorithms. However, there is currently no standard for these methods, and no studies have compared them so far in the medical field. In this work, we evaluated different combinations of preprocessing steps, including spatial and spectral smoothing, Min-Max scaling, Standard Normal Variate normalization, and a median spatial smoothing technique, with the goal of improving tumor detection in three different HSI databases concerning colorectal, esophagogastric, and brain cancers. Two machine learning and deep learning models were used to perform the pixel-wise classification. The results showed that the choice of preprocessing method affects the performance of tumor identification. The method that showed slightly better results with respect to identifing colorectal tumors was Median Filter preprocessing (0.94 of area under the curve). On the other hand, esophagogastric and brain tumors were more accurately identified using Min-Max scaling preprocessing (0.93 and 0.92 of area under the curve, respectively). However, it is observed that the Median Filter method smooths sharp spectral features, resulting in high variability in the classification performance. Therefore, based on these results, obtained with different databases acquired by different HSI instrumentation, the most relevant preprocessing technique identified in this work is Min-Max scaling.

Neural Networks-Based On-Site Dermatologic Diagnosis through Hyperspectral Epidermal Images.

Cancer originates from the uncontrolled growth of healthy cells into a mass. Chromophores, such as hemoglobin and melanin, characterize skin spectral properties, allowing the classification of lesions into different etiologies. Hyperspectral imaging systems gather skin-reflected and transmitted light into several wavelength ranges of the electromagnetic spectrum, enabling potential skin-lesion differentiation through machine learning algorithms. Challenged by data availability and tiny inter and intra-tumoral variability, here we introduce a pipeline based on deep neural networks to diagnose hyperspectral skin cancer images, targeting a handheld device equipped with a low-power graphical processing unit for routine clinical testing. Enhanced by data augmentation, transfer learning, and hyperparameter tuning, the proposed architectures aim to meet and improve the well-known dermatologist-level detection performances concerning both benign-malignant and multiclass classification tasks, being able to diagnose hyperspectral data considering real-time constraints. Experiments show 87% sensitivity and 88% specificity for benign-malignant classification and specificity above 80% for the multiclass scenario. AUC measurements suggest classification performance improvement above 90% with adequate thresholding. Concerning binary segmentation, we measured skin DICE and IOU higher than 90%. We estimated 1.21 s, at most, consuming 5 Watts to segment the epidermal lesions with the U-Net++ architecture, meeting the imposed time limit. Hence, we can diagnose hyperspectral epidermal data assuming real-time constraints.

Towards the Simulation of a Realistic Large-Scale Spiking Network on a Desktop Multi-GPU System.

The reproduction of the brain 'sactivity and its functionality is the main goal of modern neuroscience. To this aim, several models have been proposed to describe the activity of single neurons at different levels of detail. Then, single neurons are linked together to build a network, in order to reproduce complex behaviors. In the literature, different network-building rules and models have been described, targeting realistic distributions and connections of the neurons. In particular, the Granular layEr Simulator (GES) performs the granular layer network reconstruction considering biologically realistic rules to connect the neurons. Moreover, it simulates the network considering the Hodgkin-Huxley model. The work proposed in this paper adopts the network reconstruction model of GES and proposes a simulation module based on Leaky Integrate and Fire (LIF) model. This simulator targets the reproduction of the activity of large scale networks, exploiting the GPU technology to reduce the processing times. Experimental results show that a multi-GPU system reduces the simulation of a network with more than 1.8 million neurons from approximately 54 to 13 h.

Deep Convolutional Generative Adversarial Networks to Enhance Artificial Intelligence in Healthcare: A Skin Cancer Application.

In recent years, researchers designed several artificial intelligence solutions for healthcare applications, which usually evolved into functional solutions for clinical practice. Furthermore, deep learning (DL) methods are well-suited to process the broad amounts of data acquired by wearable devices, smartphones, and other sensors employed in different medical domains. Conceived to serve the role of diagnostic tool and surgical guidance, hyperspectral images emerged as a non-contact, non-ionizing, and label-free technology. However, the lack of large datasets to efficiently train the models limits DL applications in the medical field. Hence, its usage with hyperspectral images is still at an early stage. We propose a deep convolutional generative adversarial network to generate synthetic hyperspectral images of epidermal lesions, targeting skin cancer diagnosis, and overcome small-sized datasets challenges to train DL architectures. Experimental results show the effectiveness of the proposed framework, capable of generating synthetic data to train DL classifiers.

Deep learning and lung ultrasound for Covid-19 pneumonia detection and severity classification.

The Covid-19 European outbreak in February 2020 has challenged the world's health systems, eliciting an urgent need for effective and highly reliable diagnostic instruments to help medical personnel. Deep learning (DL) has been demonstrated to be useful for diagnosis using both computed tomography (CT) scans and chest X-rays (CXR), whereby the former typically yields more accurate results. However, the pivoting function of a CT scan during the pandemic presents several drawbacks, including high cost and cross-contamination problems. Radiation-free lung ultrasound (LUS) imaging, which requires high expertise and is thus being underutilised, has demonstrated a strong correlation with CT scan results and a high reliability in pneumonia detection even in the early stages. In this study, we developed a system based on modern DL methodologies in close collaboration with Fondazione IRCCS Policlinico San Matteo's Emergency Department (ED) of Pavia. Using a reliable dataset comprising ultrasound clips originating from linear and convex probes in 2908 frames from 450 hospitalised patients, we conducted an investigation into detecting Covid-19 patterns and ranking them considering two severity scales. This study differs from other research projects by its novel approach involving four and seven classes. Patients admitted to the ED underwent 12 LUS examinations in different chest parts, each evaluated according to standardised severity scales. We adopted residual convolutional neural networks (CNNs), transfer learning, and data augmentation techniques. Hence, employing methodological hyperparameter tuning, we produced state-of-the-art results meeting F1 score levels, averaged over the number of classes considered, exceeding 98%, and thereby manifesting stable measurements over precision and recall.

Towards a Bio-Inspired Real-Time Neuromorphic Cerebellum.

This work presents the first simulation of a large-scale, bio-physically constrained cerebellum model performed on neuromorphic hardware. A model containing 97,000 neurons and 4.2 million synapses is simulated on the SpiNNaker neuromorphic system. Results are validated against a baseline simulation of the same model executed with NEST, a popular spiking neural network simulator using generic computational resources and double precision floating point arithmetic. Individual cell and network-level spiking activity is validated in terms of average spike rates, relative lead or lag of spike times, and membrane potential dynamics of individual neurons, and SpiNNaker is shown to produce results in agreement with NEST. Once validated, the model is used to investigate how to accelerate the simulation speed of the network on the SpiNNaker system, with the future goal of creating a real-time neuromorphic cerebellum. Through detailed communication profiling, peak network activity is identified as one of the main challenges for simulation speed-up. Propagation of spiking activity through the network is measured, and will inform the future development of accelerated execution strategies for cerebellum models on neuromorphic hardware. The large ratio of granule cells to other cell types in the model results in high levels of activity converging onto few cells, with those cells having relatively larger time costs associated with the processing of communication. Organizing cells on SpiNNaker in accordance with their spatial position is shown to reduce the peak communication load by 41%. It is hoped that these insights, together with alternative parallelization strategies, will pave the way for real-time execution of large-scale, bio-physically constrained cerebellum models on SpiNNaker. This in turn will enable exploration of cerebellum-inspired controllers for neurorobotic applications, and execution of extended duration simulations over timescales that would currently be prohibitive using conventional computational platforms.

Granular layEr Simulator: Design and Multi-GPU Simulation of the Cerebellar Granular Layer.

In modern computational modeling, neuroscientists need to reproduce long-lasting activity of large-scale networks, where neurons are described by highly complex mathematical models. These aspects strongly increase the computational load of the simulations, which can be efficiently performed by exploiting parallel systems to reduce the processing times. Graphics Processing Unit (GPU) devices meet this need providing on desktop High Performance Computing. In this work, authors describe a novel Granular layEr Simulator development implemented on a multi-GPU system capable of reconstructing the cerebellar granular layer in a 3D space and reproducing its neuronal activity. The reconstruction is characterized by a high level of novelty and realism considering axonal/dendritic field geometries, oriented in the 3D space, and following convergence/divergence rates provided in literature. Neurons are modeled using Hodgkin and Huxley representations. The network is validated by reproducing typical behaviors which are well-documented in the literature, such as the center-surround organization. The reconstruction of a network, whose volume is 600 × 150 × 1,200 µm3 with 432,000 granules, 972 Golgi cells, 32,399 glomeruli, and 4,051 mossy fibers, takes 235 s on an Intel i9 processor. The 10 s activity reproduction takes only 4.34 and 3.37 h exploiting a single and multi-GPU desktop system (with one or two NVIDIA RTX 2080 GPU, respectively). Moreover, the code takes only 3.52 and 2.44 h if run on one or two NVIDIA V100 GPU, respectively. The relevant speedups reached (up to ~38× in the single-GPU version, and ~55× in the multi-GPU) clearly demonstrate that the GPU technology is highly suitable for realistic large network simulations.

Subthreshold Micropulse Laser in Diabetic Macular Edema: 1-Year Improvement in OCT/OCT-Angiography Biomarkers.

Purpose: The aim of this study was to evaluate 1-year quantitative changes in specific inflammatory parameters on optical coherence tomography (OCT) / optical coherence tomography angiography (OCTA) in diabetic macular edema (DME) treated with subthreshold micropulse laser (SMPL). Methods: Thirty-seven patients / eyes with previously treatment-naïve DME treated with SMPL were prospectively evaluated at 3, 6, and 12 months. Fifteen fellow eyes with only microaneurysms (MAS) not eligible for treatment were controls. Evaluated OCT / OCTA parameters included: central macular thickness (CMT); hyper-reflective retinal spots (HRS); disorganization of inner retinal layers (DRILs); MA in the superficial / deep capillary plexuses (SCP/DCP); cysts in the area at the SCP / DCP; and macular perfusion parameters (MATLAB, version 2017b). Results: In the treated group, mean best corrected visual acuity (BCVA) progressively increased from 69.4 ± 12.0 to 76.0 ± 9.1 Early Treatment Diabetic Retinopathy Study (ETDRS) letters (P < 0.001) at 12 months; HRS decreased from baseline (80.75 ± 20.41) at 3 (73.81 ± 17.1, P = 0.002), 6 (69.16 ± 16.48, P < 0.0001), and 12 months (66.29 ± 18.53, P < 0.0001). MA decreased at 3 months in the DCP (P = 0.015), at 6 and 12 months in both plexuses (P ≤ 0.0007). BCVA, HRS, and MA remained stable in the controls during all follow-ups. DRIL was present in 18 of 37 patients at baseline and progressively decreased from 557.0 ± 238.7 to 387.1 ± 282.1 µm (P = 0.01). The area of cyst decreased both in the SCP (P = 0.03) and the DCP (P = 0.02). CMT and perfusion parameters did not change. Conclusions: SMPL reduced the number of HRS (sign of activated microglia cells in the retina), MA, DRIL extension, and the area of cysts. Further studies are needed to confirm these preliminary data on the anti-inflammatory effect of SMPL, and to explore the mechanism of action. Translational Relevance: The follow-up of OCT/OCTA noninvasive biomarkers offers a unique insight in the mechanism of laser action, suggesting an anti-inflammatory effect of SMPL.

Raman Spectroscopy Reveals That Biochemical Composition of Breast Microcalcifications Correlates with Histopathologic Features.

Breast microcalcifications are a common mammographic finding. Microcalcifications are considered suspicious signs of breast cancer and a breast biopsy is required, however, cancer is diagnosed in only a few patients. Reducing unnecessary biopsies and rapid characterization of breast microcalcifications are unmet clinical needs. In this study, 473 microcalcifications detected on breast biopsy specimens from 56 patients were characterized entirely by Raman mapping and confirmed by X-ray scattering. Microcalcifications from malignant samples were generally more homogeneous, more crystalline, and characterized by a less substituted crystal lattice compared with benign samples. There were significant differences in Raman features corresponding to the phosphate and carbonate bands between the benign and malignant groups. In addition to the heterogeneous composition, the presence of whitlockite specifically emerged as marker of benignity in benign microcalcifications. The whole Raman signature of each microcalcification was then used to build a classification model that distinguishes microcalcifications according to their overall biochemical composition. After validation, microcalcifications found in benign and malignant samples were correctly recognized with 93.5% sensitivity and 80.6% specificity. Finally, microcalcifications identified in malignant biopsies, but located outside the lesion, reported malignant features in 65% of in situ and 98% of invasive cancer cases, respectively, suggesting that the local microenvironment influences microcalcification features. This study confirms that the composition and structural features of microcalcifications correlate with breast pathology and indicates new diagnostic potentialities based on microcalcifications assessment. SIGNIFICANCE: Raman spectroscopy could be a quick and accurate diagnostic tool to precisely characterize and distinguish benign from malignant breast microcalcifications detected on mammography.

Diabetic macular edema with neuroretinal detachment: OCT and OCT-angiography biomarkers of treatment response to anti-VEGF and steroids.

PURPOSE: To assess and compare early changes in neuroinflammatory and vascular parameters in diabetic macular edema (DME) with subfoveal neuroretinal detachment (SND) after treatment with intravitreal dexamethasone (DEX-I) and ranibizumab (IVR). METHODS: Thirty-three eyes (33 patients) with treatment naïve DME with SND were retrospectively evaluated at baseline and 2 months after DEX-I (15 eyes) and 1 month after 3 monthly IVR injections (18 eyes). Inclusion criteria were: complete eye examination, good quality OCT and OCT-A images. OCT parameters included: central macular thickness (CMT); number of hyper-reflective retinal spots (HRS) in inner, outer (IR, OR) and full retina; choroidal thickness (CT), extent of disorganization of inner retinal layers (DRIL), outer retina integrity (OR). On OCT-A: foveal avascular zone (FAZ) parameters in the superficial capillary plexus (SCP); cysts area and perfusion density (PD) in SCP and deep capillary plexus (DCP) and flow voids (FV) in choriocapillaris. FAZ was analyzed using ImageJ, perfusion parameters and FV using MATLAB. RESULTS: BCVA increased equally after both treatments (13.0 ± 10.0 ETDRS letters, p < 0.0001). There was a similar decrease (p < 0.05) in: height of SND, cysts area at SCP, central and mean CT, increase in FAZ perimeter and OR integrity, after both treatments. A greater decrease in DEX-I versus IVR group was found in: CMT (- 38.7% vs. - 22.2%, p = 0.012), HRS number in IR (- 29.2% vs. - 14.0%, p = 0.05) and full retina (- 24.7% vs. - 8.0%, p = 0.03), DRIL extension (- 62.0% vs. - 24%, p = 0.008), cysts area at DCP (- 68.7% vs. - 26.1%, p = 0.03), FAZ-CI (- 19.1% vs. - 8.3%, p = 0.02), PD at DCP (- 27.5% vs. + 4.9%, p = 0.02). FV did not change. CONCLUSIONS: More pronounced changes in specific inflammatory parameters in the inner retina are documented after steroid versus anti-VEGF treatment. These include reduction in HRS number, DRIL extension, CMT, cysts area at DCP. These data may help in further study of noninvasive imaging biomarkers for better evaluation of treatment response.

Accelerating the K-Nearest Neighbors Filtering Algorithm to Optimize the Real-Time Classification of Human Brain Tumor in Hyperspectral Images.

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.