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.

Evolutionary transitions in body plan and reproductive mode alter maintenance metabolism in squamates.

BACKGROUND: Energy (resources) acquired by animals should be allocated towards competing demands, maintenance, growth, reproduction and fat storage. Reproduction has the second lowest priority in energy allocation and only is allowed after meeting the energetic demands for maintenance and growth. This hierarchical allocation of energy suggests the hypothesis that species or taxa with high maintenance costs would be less likely to invest more energy in reproduction or to evolve an energetically more expensive mode of reproduction. Here, we used data on standard metabolic rate so far reported for 196 species of squamates to test this hypothesis. RESULTS: We found that maintenance costs were lower in snakes than in lizards, and that the costs were lower in viviparous species than in oviparous species. As snakes generally invest more energy per reproductive episode than lizards, and viviparity is an energetically more expensive mode of reproduction than oviparity, our results are consistent with the hypothesis tested. CONCLUSION: The transition from lizard-like to snake-like body form and the transition from oviparity to viviparity are major evolutionary transitions in vertebrates, which likely alter many aspects of biology of the organisms involved. Our study is the first to demonstrate that evolutionary transitions in body plan and reproductive mode alter maintenance metabolism in squamates.

[Analysis of 21 autopsy cases of aortic dissection with disputes].

OBJECTIVE: To explore procedures and methods of forensic investigation for the death cases of aortic dissection with disputes. METHODS: Twenty-one death cases of aortic dissection with disputes from 2006 to 2011 were collected. All the data were analyzed to investigate the reasons and features of the disputes. RESULTS: The main causes of the disputes were clinical misdiagnosis or slight force. The pathologic type of De Bakey (I and II) or Stanford A were common in each case. For the cases dying of aortic dissection, it was significantly important to detect the rupture of entry and exit and observe the dissection of arterial wall. CONCLUSION: The main causes of clinical misdiagnosis are insufficient experiences, careless observation and curtness in medical treatment. The difficult points in these cases are confirmation of the relationships between injury and disease, the primary affection and complication.

Prediction of binding motifs in hepatitis C virus NS5A and human proteins.

From the extensive analysis, we identified three highly conserved sequence segments in HCV NS5A proteins and one binding motif in human proteins. The binding motif of human proteins often forms a full helix or an extended strand-loop structure, and is in good agreement with the experimental findings of previous studies.

Hepatitis C virus contact map prediction based on binary encoding strategy.

Inter-residue contact map is an important two-dimensional representation of protein spatial structure, and has much potential application in the area of understanding protein fold mechanism. In the present note, a 19-bit binary input encoding strategy, integrating with residue pair conformational features (possible residue pairwise, residue classification, secondary structure, sequence length, and sequence separation information), is proposed for the purpose of capturing mapping relationship of protein sequence. Simulation results on a set of 61 hepatitis C virus (HCV) retrieved from the protein data bank (PDB) demonstrate that the proposed encoding scheme could precisely capture conformational patterns within HCV protein sequence. This promising result could provide some useful insights into the nature of HCV protein fold mechanism.

[Following up investigation of forensic psychiatry judicial expert mental testimony].

OBJECTIVE: To study different viewpoints to the conclusion and treatment, And the following up factors concerning social effect after the judgment of forensic psychiatry. METHODS: By letters, calls, visits and by investigation forms made by myself, 208 testimonied cases were followed up separately from judicial organ or other organizations and institutes, individuals testimonied or their family members, victims and their family members. RESULTS: Most testimonied individuals were married man of 30 years old or so whose average education were 4.84 years and testimonied by the public security organs. In criminal cases, violental criminals (129 cases, 83.77%) were much more than non-violental criminals (25 cases, 16.23%) and homicide criminals (44 cases, 28.57%) were most common in the former but civil cases were few. The rate of retstinvony was 2.93%. The testimonied individuals and their family members thought the condemn were appropriate (76.47%) for the people without criminal capacity and thought the condemn were appropriate (41.94%) or not appropriate (41.94%) for the people with criminal capacity. The opinions of the condemn for partial criminal capacity were between the former two cases. And they thought the condemn for 28 cases of non-guilty were appropriate (71.43%) and not appropriate (10.7%). 7 victims were dead. 10 victims were crippled. 10 victims restored to health. In 41 persons testimonied and set free with a verdict of "not guilty", 4 homicided again (4.87%), 2 set on fire (4.87%), 2 stealed (4.87%) and 3 had wrecked behavior (7.31%). CONCLUSION: So it is suggested that the department concerned should keep criminals with mental disorder under control and treatment.

Prediction of protein secondary structure using improved two-level neural network architecture.

In this paper we propose constructing an improved two-level neural network to predict protein secondary structure. Firstly, we code the whole protein composition information as the inputs to the first-level network besides the evolutionary information. Secondly, we calculate the reliability score for each residue position based on the output of the first-level network, and the role of the second-level network is to take full advantage of the residues with a higher reliability score to impact the neighboring residues with a lower one for improving the whole prediction accuracy. Thirdly, considering it is indeed a problem that the target protein can be lost in the multiple sequence alignment we propose to code single sequence into the second-level network. The experimental results show that our proposed method can efficiently improve the prediction accuracy.

Inter-residue spatial distance map prediction by using integrating GA with RBFNN.

The spatial ordering information of amino acid residue in protein primary sequence is an important determinant of protein three-dimensional structure. In this paper, we describe a radial basis function neural network (RBFNN), whose hidden centers and basis function widths are optimized by a genetic algorithm (GA), for the purpose of predicting three dimensional spatial distance location from primary sequence information. Experimental evidence on soybean protein sequences indicates the utility of this approach.

Prediction of inter-residue contacts map based on genetic algorithm optimized radial basis function neural network and binary input encoding scheme.

Inter-residue contacts map prediction is one of the most important intermediate steps to the protein folding problem. In this paper, we focus on the problem of protein inter-residue contacts map prediction based on neural network technique. Firstly, we use a genetic algorithm (GA) to optimize the radial basis function widths and hidden centers of a radial basis function neural network (RBFNN), then a novel binary encoding scheme is employed to train the network for the purpose of learning and predicting the inter-residue contacts patterns of protein sequences got from the protein data bank (PDB). The experimental evidence indicates the utility of our proposed encoding strategy and GA optimized RBFNN. Moreover, the simulation results demonstrate that the network got a better performance for these proteins, whose residue length falls into the area of (100, 300), and the predicted accuracy with a contact threshold of 7 Angstroms scores higher than the other 3 values with 5, 6, and 8 Angstroms.