Coronavirus disease 2019 (COVID-19) is a novel disease that affects healthcare on a global scale and cannot be ignored because of its high fatality rate. Computed tomography (CT) images are presently being employed to assist doctors in detecting COVID-19 in its early stages. In several scenarios, a combination of epidemiological criteria (contact during the incubation period), the existence of clinical symptoms, laboratory tests (nucleic acid amplification tests), and clinical imaging-based tests are used to diagnose COVID-19. This method can miss patients and cause more complications. Deep learning is one of the techniques that has been proven to be prominent and reliable in several diagnostic domains involving medical imaging. This study utilizes a convolutional neural network (CNN), stacked autoencoder, and deep neural network to develop a COVID-19 diagnostic system. In this system, classification undergoes some modification before applying the three CT image techniques to determine normal and COVID-19 cases. A large-scale and challenging CT image dataset was used in the training process of the employed deep learning model and reporting their final performance. Experimental outcomes show that the highest accuracy rate was achieved using the CNN model with an accuracy of 88.30%, a sensitivity of 87.65%, and a specificity of 87.97%. Furthermore, the proposed system has outperformed the current existing state-of-the-art models in detecting the COVID-19 virus using CT images.

Automated System for Identifying COVID-19 Infections in Computed Tomography Images Using Deep Learning Models

This article describes commonly used experimental and clinical biomarkers of neuronal injury and neurodegeneration for the evaluation of neuropathology and monitoring of therapeutic interventions. Biomarkers are vital for diagnostics of brain disease and therapeutic monitoring. A biomarker can be objectively measured and evaluated as a proxy indicator for the pathophysiological process or response to therapeutic interventions. There are complex hurdles in understanding the molecular pathophysiology of neurological disorders and the ability to diagnose them at initial stages. Novel biomarkers for neurological diseases may surpass these issues, especially for early identification of disease risk. Validated biomarkers can measure the severity and progression of both acute neuronal injury and chronic neurological diseases such as epilepsy, migraine, Alzheimer’s disease, Parkinson’s disease, Huntington’s disease, traumatic brain injury, amyotrophic lateral sclerosis, multiple sclerosis, and other brain diseases. Biomarkers are deployed to study progression and response to treatment, including noninvasive imaging tools for both acute and chronic brain conditions. Neuronal biomarkers are classified into four core subtypes: blood-based, immunohistochemical-based, neuroimaging-based, and electrophysiological biomarkers. Neuronal conditions have progressive stages, such as acute injury, inflammation, neurodegeneration, and neurogenesis, which can serve as indices of pathological status. Biomarkers are critical for the targeted identification of specific molecules, cells, tissues, or proteins that dramatically alter throughout the progression of brain conditions. There has been tremendous progress with biomarkers in acute conditions and chronic diseases affecting the central nervous system.

/pdf/experimental-and-clinical-biomarkers-for-progressive-s7n8nk46.pdf

Experimental and Clinical Biomarkers for Progressive Evaluation of Neuropathology and Therapeutic Interventions for Acute and Chronic Neurological Disorders

Introduction: Developing novel diagnostic and screening tools for exploring intracranial injuries following minor head trauma is a necessity. This study aimed to evaluate the diagnostic value of serum glial fibrillary acidic protein (GFAP) in detecting intracranial injuries following minor head trauma. Methods: An extensive search was performed in Medline, Embase, Scopus, and Web of Science databases up to the end of April 2022. Human observational studies were chosen, regardless of sex and ethnicity of their participants. Pediatrics studies, report of diagnostic value of GFAP combined with other biomarkers (without reporting the GFAP alone), articles including patients with all trauma severity, defining minor head trauma without intracranial lesions as the outcome of the study, not reporting sensitivity/specificity or any other values essential for computation of true positive, true negative, false positive and false-negative, being performed in the prehospital setting, assessing the prognostic value of GFAP, duplicated reports, preclinical studies, retracted articles, and review papers were excluded. The result was provided as pooled sensitivity, specificity, diagnostic score and diagnostic odds ratio, and area under the summary receiver operating characteristic (SROC) curve with a 95% confidence interval (95% CI). Results: Eventually, 11 related articles were introduced into the meta-analysis. The pooled analysis implies that the area under the SROC curve for serum GFAP level in minor traumatic brain injuries (TBI) was 0.75 (95% CI: 0.71 to 0.78). Sensitivity and specificity of this biomarker in below 100 pg/ml cut-off were 0.83 (95% CI: 0.78 to 0.89) and 0.39 (95% CI: 0.24 to 0.53), respectively. The diagnostic score and diagnostic odds ratio of GFAP in detection of minor TBI were 1.13 (95% CI: 0.53 to 1.74) and 3.11 (95% CI: 1.69 to 5.72), respectively. The level of evidence for the presented results were moderate. Conclusion: The present study's findings demonstrate that serum GFAP can detect intracranial lesions in mild TBI patients. The optimum cut-off of GFAP in detection of TBI was below 100 pg/ml. As a result, implementing serum GFAP may be beneficial in mild TBI diagnosis for preventing unnecessary computed tomography (CT) scans and their related side effects.

Serum Glial Fibrillary Acidic Protein in Detecting Intracranial Injuries Following Minor Head Trauma; a Systematic Review and Meta-Analysis

Serum zinc levels in the acute stages after traumatic brain injury (TBI) may be capable of predicting cinical and functional prognoses. This study aimed to evaluate the association between serum zinc levels and long-term survival and neurological outcomes in TBI patients with intracranial injury. This multicenter prospective cohort study enrolled adult TBI patients with intracranial injury who visited emergency departments between December 2018 and June 2020. Serum zinc levels drawn within 24 h after injury were categorized into four groups: low (<80.0 mcg/dL), low–normal (80.0–100.0 mcg/dL), high–normal (100.1–120.0 mcg/dL), and high (>120.0 mcg/dL). The study outcomes were 6-month mortality and disability (Glasgow Outcome Scale, 1–3). A multilevel multivariable logistic regression analysis was conducted to estimate associations between serum zinc and study outcomes. From the eligible TBI patients (N = 487), the median (interquartile range) serum zinc level was 112.0 mcg/dL (95.0–142.0). Six-month mortality and disability were 21.1% (103/487) and 29.6% (144/487), respectively. Compared to the high–normal zinc group, there were significant associations with 6-month mortality and disability observed in the low zinc group (aORs (95% CIs): 1.91 (1.60–2.28) and 1.95 (1.62–2.36) for the low group; 1.14 (0.67–1.94) and 1.15 (0.91–1.46) for the low–normal group; and 0.72 (0.44–1.16) and 0.88 (0.61–1.27) for the high group, respectively). Among the 122 TBI patients with diabetes mellitus, the low zinc group showed a higher incidence of 6-month mortality (aOR (95% CI): 9.13 (4.01–20.81)) compared to the high–normal zinc group. Moreover, the low and low–normal groups had higher odds for 6-month disability (aORs (95% CIs): 6.63 (3.61–12.15) for the low group and 2.37 (1.38–4.07) for the low–normal group). Serum zinc deficiency is associated with a higher incidence of 6-month mortality and disability after injury for TBI patients with intracranial injury.

/pdf/serum-zinc-and-long-term-prognosis-after-acute-traumatic-fs7wfq45.pdf

Serum Zinc and Long-Term Prognosis after Acute Traumatic Brain Injury with Intracranial Injury: A Multicenter Prospective Study

Traumatic brain injury (TBI) is characterized by neuroinflammation and structural damage leading to symptoms and altered brain function. Biomarkers are useful in understanding neuroinflammation and correlations with TBI sequalae. The purpose of this paper is to identify and discuss biomarkers of neuroinflammation used to study TBI and its sequalae. A systematic review was conducted using PubMed, CINAHL, Embase, and Web of Science. A total of 350 articles met criteria; 70 used biomarkers. PRISMA criteria were used for Quality Assessment. Articles included reviews (n = 17), case-control (n = 25), cross-sectional (n = 25) studies, and randomized controlled trials (n = 3). Twenty-seven biomarkers were identified, including inflammasomes, cytokines, neuropeptides, complement complexes, miRNA and exosomes, and glial cell-specific proteins. Biomarkers aid in predicting morbidity and mortality and advance our understanding of neuroinflammation in TBI. This systematic review advances our understanding of the neuroinflammatory response to better enable nurses and clinicians to provide informed care of TBI patients.

Biomarkers of Neuroinflammation in Traumatic Brain Injury

http://www.scielo.org.co/pdf/rca/v48n3/2256-2087-rca-48-03-155.pdf

Utility of biomarkers in traumatic brain injury: a narrative review

Stroke is the second-leading cause of death world around. The immediate attention is key to patient prognosis. Ischemic stroke diagnosis typically involves neuroimaging studies (MRI and CT scans) and clinical protocols to characterize lesions and support decisions about treatment to be administered to the patient. Nowadays, multiparametric MRI images are the standard tool to visualize core and penumbra of ischemic stroke, supporting diagnosis and lesion prognosis. Specially, DWI modality (Diffusion Weighted Imaging) allows to quantify the cellular density of the tissue, and therefore allowing to quantify the lesion aggressiveness, and the recognition of micro-circulation properties. Nevertheless, MRI availability at hospitals is not widespread, and acquisition require special conditions requiring considerable time. Contrary, CT scans commonly have major availability but brain structures are poorly delineated, and even worse, ischemic lesions are only visible at advanced stages of the disease. This work introduces a deep generative strategy that allows ischemic stroke lesion translation over synthetic DWI-MRI images. This encoder-decoder architecture, include U-net modules, hierarchically organized, with inter-level connections that preserve brain structures, while codifying an embedding representation. Then a cyclic loss was here implemented to receive CT inputs and decode DWI-MRI images. To avoid mode collapse, this learning is inversely propagated, i.e., from synthetic DWI-MRI images to original CT-scans. Finally, an embedding projection is recovered to show a proper lesion-slice discrimination, regarding control studies. Clinical relevance- To recover synthetic DWI-MRI that preserved ischemic lesion using CT scans as an input and following an unpaired image translation setup.

A deep CT to MRI unpaired translation that preserve ischemic stroke lesions

Abstract Introduction: The coronavirus disease 2019 (COVID-19) has become a significant public health problem worldwide. In this context, CT-scan automatic analysis has emerged as a COVID-19 complementary diagnosis tool allowing for radiological finding characterization, patient categorization, and disease follow-up. However, this analysis depends on the radiologist’s expertise, which may result in subjective evaluations. Objective: To explore deep learning representations, trained from thoracic CT-slices, to automatically distinguish COVID-19 disease from control samples. Materials and methods: Two datasets were used: SARS-CoV-2 CT Scan (Set-1) and FOSCAL clinic’s dataset (Set-2). The deep representations took advantage of supervised learning models previously trained on the natural image domain, which were adjusted following a transfer learning scheme. The deep classification was carried out: (a) via an end-to-end deep learning approach and (b) via random forest and support vector machine classifiers by feeding the deep representation embedding vectors into these classifiers. Results: The end-to-end classification achieved an average accuracy of 92.33% (89.70% precision) for Set-1 and 96.99% (96.62% precision) for Set-2. The deep feature embedding with a support vector machine achieved an average accuracy of 91.40% (95.77% precision) and 96.00% (94.74% precision) for Set-1 and Set-2, respectively. Conclusion: Deep representations have achieved outstanding performance in the identification of COVID-19 cases on CT scans demonstrating good characterization of the COVID-19 radiological patterns. These representations could potentially support the COVID-19 diagnosis in clinical settings.

Deep learning representations to support COVID-19 diagnosis on CT slices

Computed tomography (CT) is the first-line imaging modality for evaluation of patients suspected of stroke. Specially, such modality is key as screening test between ischemia and hemorrhage strokes. Despite remarkable support of encoder-decoder architectures, the delineation of ischemic lesions remains challenging on CT studies, reporting poor sensitivity, especially in the acute stage. Among others, these nets are affected because of the low scan quality, the challenging stroke geometry, and the variable textural representation. This work introduces a boundary-focused attention U-Net that takes advantage of cross-attention mechanism, that along multiple levels allows to recover stroke segmentation on CT scans. The proposed architecture is enriched with skip connections, that help in the recovering of saliency lesion maps and motivated the preservation of morphology. Besides, an auxiliary class is herein introduced with a weighted special loss function that remark lesion tissue, alleviating the negative impact of class unbalance. The proposed approach was validated on the public ISLES2018 dataset achieving an average dice score of 0.42 and a precision of 0.48.

An attentional unet with an auxiliary class learning to support acute ischemic stroke segmentation on CT

The key component of stroke diagnosis is the localization and delineation of brain lesions, especially from MRI studies. Nonetheless, this manual delineation is time-consuming and biased by expert opinion. The main purpose of this study is to introduce an autoencoder architecture that effectively integrates cross-attention mechanisms, together with hierarchical deep supervision to delineate lesions under scenarios of remarked unbalance tissue classes, challenging geometry of the shape, and a variable textural representation. This work introduces a cross-attention deep autoencoder that focuses on the lesion shape through a set of convolutional saliency maps, forcing skip connections to preserve the morphology of affected tissue. Moreover, a deep supervision training scheme was herein adapted to induce the learning of hierarchical lesion details. Besides, a special weighted loss function remarks lesion tissue, alleviating the negative impact of class imbalance. The proposed approach was validated on the public ISLES2017 dataset outperforming state-of-the-art results, achieving a dice score of 0.36 and a precision of 0.42. Deeply supervised cross-attention autoencoders, trained to pay more attention to lesion tissue, are better at estimating ischemic lesions in MRI studies. The best architectural configuration was achieved by integrating ADC, TTP and Tmax sequences. The contribution of deeply supervised cross-attention autoencoders allows better support the discrimination between healthy and lesion regions, which in consequence results in favorable prognosis and follow-up of patients.

Daniela S. Mantilla

Papers

Utility of biomarkers in traumatic brain injury: a narrative review

A deep CT to MRI unpaired translation that preserve ischemic stroke lesions

Deep learning representations to support COVID-19 diagnosis on CT slices

An attentional unet with an auxiliary class learning to support acute ischemic stroke segmentation on CT

A deep supervised cross-attention strategy for ischemic stroke segmentation in MRI studies