High-yield criteria for urgent cranial computed tomography scans

OBJECTIVE: To verify the prevalence of acute hyperglycemia in children with head trauma stratified by the Glasgow coma scale (GCS). METHOD: A prospective cross-sectional study carried out with information from medical records of pediatric patients presenting with head injury in the emergency room of a referral emergency hospital during a one year period. We considered the cut-off value of 150 mg/dL to define hyperglycemia. RESULTS: A total of 340 children were included and 60 (17.6%) had admission hyperglycemia. Hyperglycemia was present in 9% of mild head trauma cases; 30.4% of those with moderate head trauma and 49% of severe head trauma. We observed that among children with higher blood glucose levels, 85% had abnormal findings on cranial computed tomography scans. CONCLUSION: Hyperglycemia was more prevalent in patients with severe head trauma (GCS <8), regardless if they had or not multiple traumas and in children with abnormal findings on head computed tomography scans.

Download Full-text

Hybrid Convolutional Neural Network-Based Diagnosis System for Intracranial Hemorrhage

BRAIN. BROAD RESEARCH IN ARTIFICIAL INTELLIGENCE AND NEUROSCIENCE ◽

10.18662/brain/12.4/236 ◽

2021 ◽

Vol 12 (4) ◽

pp. 01-27

Author(s):

Sezin Barin ◽

Murat Saribaş ◽

Beyza Gülizar Çiltaş ◽

Gür Emre Güraksin ◽

Utku Köse

Keyword(s):

Computed Tomography ◽

Deep Learning ◽

Early Diagnosis ◽

Intracranial Hemorrhage ◽

Hybrid Method ◽

Computer Aided Design ◽

Cranial Computed Tomography ◽

Critical Problem ◽

Computed Tomography Scans ◽

Aided Design

Early diagnosis of intracranial hemorrhage significantly reduces mortality. Hemorrhage is diagnosed by using various imaging methods and the most time-efficient one among them is computed tomography (CT). However, it is clear that accurate CT scans requires time, diligence, and experience. Computer-aided design methods are vital for the treatment because they facilitate early diagnosis of intracranial hemorrhage. At this point, deep learning can provide effective outcomes through an automated diagnosis way. However, as different from the known solutions, diagnosis of five different hemorrhage subtypes is a critical problem to be solved.This study focused on deep learning methods and employed cranial computed tomography scans in order to detect intracranial hemorrhage. The diagnosis approach in the study aimed to detect five subtypes of hemorrhage. In detail, EfficientNet-B3 and ResNet-Inception-V2 architectures were used for diagnosis purposes. Eventually, the study also proposed a two-architecture hybrid method for the diagnosis purpose. The obtained findings by the hybrid method were evaluated in terms of a comparative perspective.Results showed that the newly designed hybrid method was quite effective in terms of increasing classification rates of detecting intracranial hemorrhage according to the subtypes. Briefly, an accuracy of 98.5%, which is higher than those of the EfficientNet-B3 and the Inception-ResNet-V2, were obtained thanks to the developed hybrid method.

Download Full-text