RESUMEN
Objective To reconstruct a vehicle-bicycle-cyclist crash accident and analyse the injuries us-ing 3D laser scanning technology, multi-rigid-body dynamics and optimized genetic algorithm, and to provide biomechanical basis for the forensic identification of death cause. Methods The vehicle was measured by 3D laser scanning technology. The multi-rigid-body models of cyclist, bicycle and vehicle were developed based on the measurements. The value range of optimal variables was set. A multi-ob-jective genetic algorithm and the nondominated sorting genetic algorithm were used to find the optimal solutions, which were compared to the record of the surveillance video around the accident scene. Re-sults The reconstruction result of laser scanning on vehicle was satisfactory. In the optimal solutions found by optimization method of genetic algorithm, the dynamical behaviours of dummy, bicycle and ve-hicle corresponded to that recorded by the surveillance video. The injury parameters of dummy were consistent with the situation and position of the real injuries on the cyclist in accident. Conclusion The motion status before accident, damage process by crash and mechanical analysis on the injury of the victim can be reconstructed using 3D laser scanning technology, multi-rigid-body dynamics and opti-mized genetic algorithm, which have application value in the identification of injury manner and analysis of death cause in traffic accidents.
RESUMEN
Deep learning and neural network models have been new research directions and hot issues in the fields of machine learning and artificial intelligence in recent years. Deep learning has made a breakthrough in the applications of image and speech recognitions, and also has been extensively used in the fields of face recognition and information retrieval because of its special superiority. Bone X-ray images express different variations in black-white-gray gradations, which have image features of black and white contrasts and level differences. Based on these advantages of deep learning in image recognition, we combine it with the research of bone age assessment to provide basic datum for constructing a forensic automatic system of bone age assessment. This paper reviews the basic concept and network architectures of deep learning, and describes its recent research progress on image recognition in different research fields at home and abroad, and explores its advantages and application prospects in bone age assessment.
RESUMEN
Objective To explore and evaluate the clinical value of MRI for status of axillary lymph node after neoadju-vant chemotherapy (NAC) in patients with breast cancer. Methods Forty-four patients with 1ocally advanced breast cancer (LABC) were underwent NAC for four cycles. The longest diameter of axillary lymph node (ALN) measured by MRI scan. Val-ue of apparent diffusion coefficient (ADC) and their correlation were compared before NAC and four cycles after NAC. Re-sults of MRI and pathological data for ALN were compared between two groups of patients. Results All patients finished four cycles of NAC. The total response rate (CR+PR) was 72.7% (32/44), and the total non-response rate (SD+PD) was 27.3%(12/44). The longest diameter of ALN was significantly shortened in response group. The longest diameter was (1.37± 1.06) cm before NAC and (0.90±0.76) cm after NAC (P<0.01). The ADC value of the tumor was significantly increased in re-sponse group [(0.91±0.28) ×10-3 mm2/s before NAC and (1.01±0.32)×10-3 mm2/s after NAC, P<0.01)]. There was no signifi-cant correlation between ADC value change (△ADC) and the longest diameter change of ALN (△L, r=0.131, P=0.413). The sensitivity, specificity and Kappa value of ALN evaluation after NAC were 100%, 62.5%and 0.68 measured by MRI. Con-clusion The change of tumor longest diameter reflects the effect of chemotherapy directly. The tumor ADC value of MRI can not be used as an independent indicator of chemotherapy effect of ALN, eventhouth MRI was the sensitive index for eval-uating the status of axillary lymph node after neoadjuvant chemotherapy for breast cancer.