Skull fracture

Classification of skull fracture is a challenging task for both radiologists and researchers. Skull fractures result in broken pieces of bone, which can cut into the brain and cause bleeding and other injury types. So it is vital to detect and classify the fracture very early. In real world, often fractures occur at multiple sites. This makes it harder to detect the fracture type where many fracture types might summarize a skull fracture. Unfortunately, manual detection of skull fracture and the classification process is time-consuming, threatening a patient's life. Because of the emergence of deep learning, this process could be automated. Convolutional Neural Networks (CNNs) are the most widely used deep learning models for image categorization because they deliver high accuracy and outstanding outcomes compared to other models. We propose a new model called SkullNetV1 comprising a novel CNN by taking advantage of CNN for feature extraction and lazy learning approach which acts as a classifier for classification of skull fractures from brain CT images to classify five fracture types. Our suggested model achieved a subset accuracy of 88%, an F1 score of 93%, the Area Under the Curve (AUC) of 0.89 to 0.98, a Hamming score of 92% and a Hamming loss of 0.04 for this seven-class multi-labeled classification.

The objective of this study was to determine the responses of 5th-percentile female, and 50th- and 95thpercentile male human heads during lateral impacts at different velocities and determine the role of the stiffness and shape of the impacting surface on peak forces and derived skull fracture metrics. A state-of-the-art validated finite element (FE) head model was used to study the influence of different population human heads on skull fracture for lateral impacts. The mass of the FE head model was altered to match the adult size dummies. Numerical simulations of lateral head impacts for 45 cases (15
experiments X3 different population human heads) were performed at velocities ranging from 2.4 to 6.5 m/s and three impacting conditions (flat and cylindrical 90D; and flat 40D padding). The entire forcetime signals from simulations were compared with experimental mean and upper/lower corridors at each velocity, stiffness (40 and 90 durometer) and shapes (flat and cylindrical) of the impacting surfaces. Average deviation of peak force from the 50th male to 95th male and 5th female were 6.4% and 10.6% considering impacts on the three impactors. These results indicate hierarchy of variables which can be used in injury mitigation efforts.

Background: Head injuries rank high among morbidities due to trauma. Computerized tomography is an important modality in the investigation of these cases. However, there is no literature on the importance of computerized tomography in the diagnosis of head injury in Ethiopia. This study therefore is aimed to document the computerized tomographic features of patients with head injury managed at the University of Gondar Teaching Hospital. Materials and Methods: A cross sectional study involving 96 patients with head injury who had CT scan of the head in the UOG hospital over a 12-month period. Results: Most of the patients were male (74%).  Majority (58%) were in the age range of 20 to 40 years with a mean age of 31yrs. The most common abnormal findings were skull fracture (52%) and intracerebral hemorrhage and contusions (51%). It is followed by subdural hemorrhage (33%) soft tissue swelling 32% and epidural hemorrhage 10%. Conclusion:  Skull fracture and intra cerebral hemorrhage were the most common abnormal findings. This study has demonstrated the importance of CT scan in the evaluation of head injury by giving visibility of intracranial post traumatic injuries in a high proportion of patients which would be difficult to reach in to diagnosis clinically or using skull radiography alone. This obviously will have a significant role in improving patient management. Taking this in to account expansion of CT scan service for moderate to severe head injury patients is recommended in Ethiopia.

Background: Head injury is one of the commonest causes of mortality in motorcycle
accidents. This study aims to determine the pattern of injuries in fatal cases of pillion rider
accidents, because few studies have been conducted on this topic.
Methods: A total of 34 cases of pillion rider fatalities in Pondicherry, India were included in
the study.
Results: Scalp injuries and fractures were more commonly seen over the occipital (41% and
47%, respectively) and temporal region (21% and 38%, respectively) of the head especially in
females, also slip and fall off motorcycle (38%) was the commonest mode of injury.
Conclusion: Slip and fall was significantly higher (92%) in females as the position adopted
by female pillion riders was usually the side saddle position and the impact part of the head,
in falls from this position, usually involves the occipital or temporal region of the head. To
prevent the slip and fall off the bike, a safety belt/harness can be used to control the fall of the
pillion rider seated in a side saddle position, and this could reduce the mortality and morbidity
in pillion riders to some extent.