scholarly journals Automated Intracranial Hematoma Classification in Traumatic Brain Injury (TBI) Patients Using Meta-Heuristic Optimization Techniques

Informatics ◽  
2022 ◽  
Vol 9 (1) ◽  
pp. 4
Author(s):  
Vidhya V ◽  
U. Raghavendra ◽  
Anjan Gudigar ◽  
Praneet Kasula ◽  
Yashas Chakole ◽  
...  

Traumatic Brain Injury (TBI) is a devastating and life-threatening medical condition that can result in long-term physical and mental disabilities and even death. Early and accurate detection of Intracranial Hemorrhage (ICH) in TBI is crucial for analysis and treatment, as the condition can deteriorate significantly with time. Hence, a rapid, reliable, and cost-effective computer-aided approach that can initially capture the hematoma features is highly relevant for real-time clinical diagnostics. In this study, the Gray Level Occurrence Matrix (GLCM), the Gray Level Run Length Matrix (GLRLM), and Hu moments are used to generate the texture features. The best set of discriminating features are obtained using various meta-heuristic algorithms, and these optimal features are subjected to different classifiers. The synthetic samples are generated using ADASYN to compensate for the data imbalance. The proposed CAD system attained 95.74% accuracy, 96.93% sensitivity, and 94.67% specificity using statistical and GLRLM features along with KNN classifier. Thus, the developed automated system can enhance the accuracy of hematoma detection, aid clinicians in the fast interpretation of CT images, and streamline triage workflow.

2019 ◽  
Vol 7 (1) ◽  
pp. 12 ◽  
Author(s):  
Iris Pélieu ◽  
Corey Kull ◽  
Bernhard Walder

Traumatic brain injury (TBI) is a major healthcare problem and a major burden to society. The identification of a TBI can be challenging in the prehospital setting, particularly in elderly patients with unobserved falls. Errors in triage on scene cannot be ruled out based on limited clinical diagnostics. Potential new mobile diagnostics may decrease these errors. Prehospital care includes decision-making in clinical pathways, means of transport, and the degree of prehospital treatment. Emergency care at hospital admission includes the definitive diagnosis of TBI with, or without extracranial lesions, and triage to the appropriate receiving structure for definitive care. Early risk factors for an unfavorable outcome includes the severity of TBI, pupil reaction and age. These three variables are core variables, included in most predictive models for TBI, to predict short-term mortality. Additional early risk factors of mortality after severe TBI are hypotension and hypothermia. The extent and duration of these two risk factors may be decreased with optimal prehospital and emergency care. Potential new avenues of treatment are the early use of drugs with the capacity to decrease bleeding, and brain edema after TBI. There are still many uncertainties in prehospital and emergency care for TBI patients related to the complexity of TBI patterns.


10.36469/9893 ◽  
2014 ◽  
Vol 2 (2) ◽  
pp. 108-118
Author(s):  
Pankaj A. Patel ◽  
Peter J. Mallow ◽  
Mary Vassar ◽  
John A. Rizzo ◽  
Bhavik J. Pandya ◽  
...  

Background: Traumatic brain injury (TBI) is an increasingly diagnosed condition, but the trends in TBI visits and the cost of which have not been quantified from the hospital perspective. Objectives: To quantify the costs of TBI stratified by inpatient and outpatient visits and to examine trends in TBI incidence over time. Methods: This descriptive study utilized data for 2007-2012 from the Premier hospital database, which includes clinical and utilization information from hospitals across the United States. TBI was identified through International Classification of Diseases, 9th Revision, Clinical Modification (ICD-9-CM) codes. Descriptive data were obtained to identify the TBI costs, visit costs, patient characteristics, and intertemporal trends in TBI rates. Results: TBI patients were treated on an outpatient basis 88% of the time. Nearly 45% (44.3%) of TBI patients requiring inpatient admissions were age 65 or over, and 20% of TBI patients treated as an outpatient were age 75 or over. Children aged 4 or younger accounted for nearly 14% of TBI cases treated on an outpatient basis. TBI patients treated in the inpatient setting incurred fairly long hospital visits (mean 4.8 days; median 3.0 days) and substantial hospital costs (mean $12,717; median $8,176). The rate of TBI visits have risen substantially over time, especially among children under age 18 years and patients in the Northeast US Census Region. Conclusion: TBI is a serious medical condition that appears to be on the rise. Large differences exist between the hospital costs associated with TBIs treated in the inpatient and outpatient settings. Further research to understand factors affecting the costs and clinical outcomes of TBI can help refine treatment strategies to enhance patient outcomes while providing cost effective care.


2016 ◽  
Vol 16 (01) ◽  
pp. 1640006 ◽  
Author(s):  
SAMANTA ROSATI ◽  
KRISTEN MARIKO MEIBURGER ◽  
GABRIELLA BALESTRA ◽  
U. RAJENDRA ACHARYA ◽  
FILIPPO MOLINARI

Aim of this paper is to develop an automated system for the classification and characterization of carotid wall status and to develop a robust system based on local texture descriptors. A database of 200 longitudinal ultrasound images of carotid artery is used. One-hundred images with Intima-Media Thickness (IMT) value higher than 0.8[Formula: see text]mm are considered as high risk. Six different rectangular pixel neighborhoods were considered: four areas centered on the selected element, with sizes [Formula: see text], [Formula: see text], [Formula: see text], and [Formula: see text] pixels, and two noncentered areas with sizes [Formula: see text] pixels upwards and downwards. We have extracted various texture descriptors (31 based on the co-occurrence gray level matrix, 13 based on the spatial gray level dependence matrix, and 20 based on the gray level run length matrix (GLRLM) from neighborhood. We have used Quick Reduct Algorithm to select 12 most discriminant features from extracted 211 features. Each pixel is then assigned to the vessel lumen, to the intima-media complex, or to the adventitia by using an integrated system of three feed-forward neural networks. The boundaries between the three regions are used to estimate the IMT value. The texture features associated with GLRLM are found to be clinically most significant. We have obtained an overall classification accuracy of 79.5%, sensitivity of 87%, and specificity of 72%. We observed a unique classification pattern between low risk and high risk images: in the latter ones, a considerable number of pixels of the intima–media complex ([Formula: see text]) was classified as belonging to the adventitia. This percentage is statistically higher than that of low risk images ([Formula: see text]; [Formula: see text]). Locally extracted and pixel-based descriptors are able to capture the inner characteristics of the carotid wall. The presence of misclassified pixels in the intima–media complex is associated to higher cardiovascular risk.


Author(s):  
Eduardo Martínez-Morillo ◽  
Charmaine Childs ◽  
Belén Prieto García ◽  
Francisco V. Álvarez Menéndez ◽  
Alexander D. Romaschin ◽  
...  

AbstractBrain injury is a medical emergency that needs to be diagnosed and treated promptly. Several proteins have been studied as biomarkers of this medical condition. The aims of this study were to: 1) evaluate the selectivity and precision of a commercial ELISA kit for neurofilament medium polypeptide (NFM) protein; and 2) evaluate the concentration in cerebrospinal fluid (CSF) and serum of healthy individuals and patients with brain damage.An ELISA from Elabscience was used. The selectivity was evaluated using size-exclusion chromatography and mass spectrometry. Intra- and inter-batch coefficients of variation (CV) were also studied. Fifty-one CSF samples from 36 age-matched patients with hemorrhagic stroke (HS) (n=30), ischemic stroke (IS) (n=11) and healthy individuals (n=10) were assayed. In addition, serum samples from healthy volunteers (n=47), 68 serum samples from seven patients with HS, 106 serum samples from 12 patients with traumatic brain injury (TBI) and 68 serum samples from 68 patients with mild traumatic brain injury (mTBI) were also analyzed.NFM was identified in the chromatographic fraction with highest immunoreactivity. The intra- and inter-batch CVs were ≤10% and ≤13%, respectively. The CSF-NFM concentration in HS was significantly higher (p<0.0001) than in IS and controls. Serum NFM concentration ranged from 0.26 to 8.57 ng/mL in healthy individuals (median=2.29), from 0.97 to 42.4 ng/mL in HS (median=10.8) and from 3.48 to 45.4 ng/mL in TBI (median=14.7). Finally, 44% of patients with mTBI had increased NFM concentration, with significantly higher levels (p=0.01) in patients with polytrauma.To our knowledge this is the first study describing increased NFM levels in CSF and serum from patients with brain damage.


2016 ◽  
Vol 33 (S1) ◽  
pp. S626-S626
Author(s):  
A. Amorim

IntroductionA traumatic brain injury (TBI) can cause numerous psychiatric complications. Humor and anxious disorders, personality disorders and psychoses are some of those possible problems. The diagnosis of psychosis due to traumatic brain injury (PDTBI), although controversial, has been subject of crescent debate and the idea that a TBI could cause a psychosis is gaining credibility. Diagnosing a PDTBI can be difficult. DSM-5 criteria are rather vague and there are many potential confounding factors due to similarities with other etiological psychosis.Objectives and aimsAlert clinicians to the diagnosis of PDTBI, clarify this clinical entity and define features that may allow them to do the differential diagnosis with other etiologic psychotic disorders.MethodsThe authors performed a research in PubMed using the keywords psychosis and traumatic brain injury and selected the adequate articles to meet the objectives proposed.ResultsDifferential diagnosis of PDTBI should be done with schizophrenia, schizoaffective psychosis, delusional disorder, substance-induced psychosis, psychosis due to other medical condition and with posttraumatic stress disorder. Differentiating PDTBI and schizophrenia can be particularly difficult. Some features have been proposed in the literature as potentially differentiating, namely the presence of negative symptoms (more common in schizophrenia), findings in MRI/CT and EEG.ConclusionsEstablishing PDTBI diagnosis can be difficult. While awaiting new studies, clinicians should, in cases of TBI related psychosis, achieve a meticulous clinical history and mental exam, in order to ensure a correct diagnosis and, therefore, determine an appropriate intervention.Disclosure of interestThe author has not supplied his/her declaration of competing interest.


2019 ◽  
Vol 42 ◽  
Author(s):  
Colleen M. Kelley ◽  
Larry L. Jacoby

Abstract Cognitive control constrains retrieval processing and so restricts what comes to mind as input to the attribution system. We review evidence that older adults, patients with Alzheimer's disease, and people with traumatic brain injury exert less cognitive control during retrieval, and so are susceptible to memory misattributions in the form of dramatic levels of false remembering.


2020 ◽  
Vol 5 (1) ◽  
pp. 88-96
Author(s):  
Mary R. T. Kennedy

Purpose The purpose of this clinical focus article is to provide speech-language pathologists with a brief update of the evidence that provides possible explanations for our experiences while coaching college students with traumatic brain injury (TBI). Method The narrative text provides readers with lessons we learned as speech-language pathologists functioning as cognitive coaches to college students with TBI. This is not meant to be an exhaustive list, but rather to consider the recent scientific evidence that will help our understanding of how best to coach these college students. Conclusion Four lessons are described. Lesson 1 focuses on the value of self-reported responses to surveys, questionnaires, and interviews. Lesson 2 addresses the use of immediate/proximal goals as leverage for students to update their sense of self and how their abilities and disabilities may alter their more distal goals. Lesson 3 reminds us that teamwork is necessary to address the complex issues facing these students, which include their developmental stage, the sudden onset of trauma to the brain, and having to navigate going to college with a TBI. Lesson 4 focuses on the need for college students with TBI to learn how to self-advocate with instructors, family, and peers.


2019 ◽  
Vol 28 (3) ◽  
pp. 1363-1370 ◽  
Author(s):  
Jessica Brown ◽  
Katy O'Brien ◽  
Kelly Knollman-Porter ◽  
Tracey Wallace

Purpose The Centers for Disease Control and Prevention (CDC) recently released guidelines for rehabilitation professionals regarding the care of children with mild traumatic brain injury (mTBI). Given that mTBI impacts millions of children each year and can be particularly detrimental to children in middle and high school age groups, access to universal recommendations for management of postinjury symptoms is ideal. Method This viewpoint article examines the CDC guidelines and applies these recommendations directly to speech-language pathology practices. In particular, education, assessment, treatment, team management, and ongoing monitoring are discussed. In addition, suggested timelines regarding implementation of services by speech-language pathologists (SLPs) are provided. Specific focus is placed on adolescents (i.e., middle and high school–age children). Results SLPs are critical members of the rehabilitation team working with children with mTBI and should be involved in education, symptom monitoring, and assessment early in the recovery process. SLPs can also provide unique insight into the cognitive and linguistic challenges of these students and can serve to bridge the gap among rehabilitation and school-based professionals, the adolescent with brain injury, and their parents. Conclusion The guidelines provided by the CDC, along with evidence from the field of speech pathology, can guide SLPs to advocate for involvement in the care of adolescents with mTBI. More research is needed to enhance the evidence base for direct assessment and treatment with this population; however, SLPs can use their extensive knowledge and experience working with individuals with traumatic brain injury as a starting point for post-mTBI care.


ASHA Leader ◽  
2010 ◽  
Vol 15 (13) ◽  
pp. 38-38
Author(s):  
G. Gayle Kelley

Sign in / Sign up

Export Citation Format

Share Document