Logistic Regression Analysis of the Mechanism of Blunt Brain Injury Inference Based on CT Images.

OBJECTIVES: To study the correlation between CT imaging features of acceleration and deceleration brain injury and injury degree. METHODS: A total of 299 cases with acceleration and deceleration brain injury were collected and divided into acceleration brain injury group and deceleration brain injury group according to the injury mechanism. Subarachnoid hemorrhage (SAH) and Glasgow coma scale (GCS), combined with skull fracture, epidural hematoma (EDH), subdural hematoma (SDH) and brain contusion on the same and opposite sides of the stress point were selected as the screening indexes. χ2 test was used for primary screening, and binary logistic regression analysis was used for secondary screening. The indexes with the strongest correlation in acceleration and deceleration injury mechanism were selected. RESULTS: χ2 test showed that skull fracture and EDH on the same side of the stress point; EDH, SDH and brain contusion on the opposite of the stress point; SAH, GCS were correlated with acceleration and deceleration injury (P<0.05). According to binary logistic regression analysis, the odds ratio (OR) of EDH on the same side of the stress point was 2.697, the OR of brain contusion on the opposite of the stress point was 0.043 and the OR of GCS was 0.238, suggesting there was statistically significant (P<0.05). CONCLUSIONS: EDH on the same side of the stress point, brain contusion on the opposite of the stress point and GCS can be used as key indicators to distinguish acceleration and deceleration injury mechanism. In addition, skull fracture on the same side of the stress point, EDH and SDH on the opposite of the stress point and SAH were relatively weak indicators in distinguishing acceleration and deceleration injury mechanism.

Automatic Identification of Brain Injury Mechanism Based on Deep Learning.

OBJECTIVES: To apply the convolutional neural network (CNN) Inception_v3 model in automatic identification of acceleration and deceleration injury based on CT images of brain, and to explore the application prospect of deep learning technology in forensic brain injury mechanism inference. METHODS: CT images from 190 cases with acceleration and deceleration brain injury were selected as the experimental group, and CT images from 130 normal brain cases were used as the control group. The above-mentioned 320 imaging data were divided into training validation dataset and testing dataset according to random sampling method. The model classification performance was evaluated by the accuracy rate, precision rate, recall rate, F1-value and AUC value. RESULTS: In the training process and validation process, the accuracy rate of the model to classify acceleration injury, deceleration injury and normal brain was 99.00% and 87.21%, which met the requirements. The optimized model was used to test the data of the testing dataset, the result showed that the accuracy rate of the model in the test set was 87.18%, and the precision rate, recall rate, F1-score and AUC of the model to recognize acceleration injury were 84.38%, 90.00%, 87.10% and 0.98, respectively, to recognize deceleration injury were 86.67%, 72.22%, 78.79% and 0.92, respectively, to recognize normal brain were 88.57%, 89.86%, 89.21% and 0.93, respectively. CONCLUSIONS: Inception_v3 model has potential application value in distinguishing acceleration and deceleration injury based on brain CT images, and is expected to become an auxiliary tool to infer the mechanism of head injury.