ABSTRACT
Objective To investigate the recognition efficiency of AI model based on deep learning for cardiac conduction system(CCS).Methods HE staining sections of cardiac muscle and CCS of 17 cases of non-sudden death were selected,and the gold standard was unanimous recognition by 2 forensic pathologists with more than 20 years of CCS diagnosis experience.Inception V3 algorithm was used to establish AI model and complete CCS identification training and testing.Confusion matrix,accuracy,precision,recall,F1 score,ROC curve and AUC value were used to evaluate the effectiveness of AI model,and accuracy,sensitivity and specificity were used to evaluate the efficiency of manual independent and AI-assisted manual recognition for CCS.Results The accuracy of AI model was 87.3%,the precision was 91.9%,the recall was 81.9%,the F1 score was 86.6%,and the AUC value was 95.3%.The accuracy of AI model was higher than that of senior forensic pathologists.There was no statistical significance in the accuracy of AI-assisted senior forensic pathologists in identifying CCS compared with manual independent detection(P>0.05),while the accuracy of AI-assisted intermediate and junior forensic pathologists in identifying CCS was increased by 8%and 14.33%,respectively,with statistical significance(P<0.05).The accuracy rate of AI-assisted junior forensic pathologists to identify CCS was higher than that of intermediate forensic pathologists in self-diagnosis.Conclusion The AI model could be used for the automatic recognition of CCS,and could improve the diagnostic efficiency of CCS and narrow the gap between the forensic pathologists with low experience and that with high experience.
ABSTRACT
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.