Research Progress of Age Estimation in the Living by Knee Joint MRI / 法医学杂志

Bone development shows certain regularity with age. The regularity can be used to infer age and serve many fields such as justice, medicine, archaeology, etc. As a non-invasive evaluation method of the epiphyseal development stage, MRI is widely used in living age estimation. In recent years, the rapid development of machine learning has significantly improved the effectiveness and reliability of living age estimation, which is one of the main development directions of current research. This paper summarizes the analysis methods of age estimation by knee joint MRI, introduces the current research trends, and future application trend.

The Value of VR-PVEP in Objective Evaluation of Monocular Refractive Visual Impairment / 法医学杂志

OBJECTIVES@#To study the virtual reality-pattern visual evoked potential (VR-PVEP) P100 waveform characteristics of monocular visual impairment with different impaired degrees under simultaneous binocular perception and monocular stimulations.@*METHODS@#A total of 55 young volunteers with normal vision (using decimal recording method, far vision ≥0.8 and near vision ≥0.5) were selected to simulate three groups of monocular refractive visual impairment by interpolation method. The sum of near and far vision ≤0.2 was Group A, the severe visual impairment group; the sum of near and far vision <0.8 was Group B, the moderate visual impairment group; and the sum of near and far vision ≥0.8 was Group C, the mild visual impairment group. The volunteers' binocular normal visions were set as the control group. The VR-PVEP P100 peak times measured by simultaneous binocular perception and monocular stimulation were compared at four spatial frequencies 16×16, 24×24, 32×32 and 64×64.@*RESULTS@#In Group A, the differences between P100 peak times of simulant visual impairment eyes and simultaneous binocular perception at 24×24, 32×32 and 64×64 spatial frequencies were statistically significant (P<0.05); and the P100 peak time of normal vision eyes at 64×64 spatial frequency was significantly different from the simulant visual impairment eyes (P<0.05). In Group B, the differences between P100 peak times of simulant visual impairment eyes and simultaneous binocular perception at 16×16, 24×24 and 64×64 spatial frequencies were statistically significant (P<0.05); and the P100 peak time of normal vision eyes at 64×64 spatial frequency was significantly different from the simulant visual impairment eyes (P<0.05). In Group C, there was no significant difference between P100 peak times of simulant visual impairment eyes and simultaneous binocular perception at all spatial frequencies (P>0.05). There was no significant difference in the P100 peak times measured at all spatial frequencies between simulant visual impairment eyes and simultaneous binocular perception in the control group (P>0.05).@*CONCLUSIONS@#VR-PVEP can be used for visual acuity evaluation of patients with severe and moderate monocular visual impairment, which can reflect the visual impairment degree caused by ametropia. VR-PVEP has application value in the objective evaluation of visual function and forensic clinical identification.

Value of ocular trauma score and ocular structural parameters in the assessment of healing visual acuity from ocular trauma / 国际眼科杂志(Guoji Yanke Zazhi)

AIM: To explore the value of ocular trauma score(OTS), initial visual acuity, and ocular structural parameters in the assessment of healing visual acuity from ocular trauma.METHOD: A total of 302 cases(302 eyes)of ocular trauma were selected as subjects, which were accepted and issued clear appraisal opinions by the Academy of Forensic Science from June 2015 to June 2021. The subjects were grouped according to the healing best corrected visual acuity(BCVA)from ocular trauma. Group Ⅰ included 63 cases(63 eyes)with BCVA &#x0026;#x003C;3.7; Group Ⅱ included 70 cases(70 eyes)with 3.7≤ BCVA &#x0026;#x003C;4.5; Group Ⅲ included 78 cases(78 eyes)with 4.5≤ BCVA &#x0026;#x003C;4.9; Group Ⅳ included 91 cases(91 eyes)with BCVA≥4.9. In addition, 77 cases(77 healthy eyes)of ocular trauma were selected as the control group, namely Group Ⅴ. The healing BCVA and ocular structural parameters from ocular trauma and theirs correlation were analyzed, and the random forest(RF)and support vector machine(SVM)model of healing visual acuity was established by the IBM SPSS Modeler 18.0.RESULTS: The initial visual acuity, OTS, the grading of corneas, lenses, and fundus, and the thickness of the retinal never fiber layer of ocular trauma patients were correlated with the healing BCVA(P&#x0026;#x003C;0.01). There were significant differences in ocular structural parameters among groups, except the central subfield thickness(P&#x0026;#x003C;0.001). The SVM model had higher accuracy of predicting healing visual acuity than the RF model, and the accuracy rate was over 80% when the error was within 0.15.CONCLUSION:OTS and ocular structural examination can provide effective information for the clinical forensic medicine appraisal of visual dysfunction after ocular trauma, and they are valuable in discriminating camouflage of visual dysfunction.

Pelvic Injury Discriminative Model Based on Data Mining Algorithm / 法医学杂志

OBJECTIVES@#To reduce the dimension of characteristic information extracted from pelvic CT images by using principal component analysis (PCA) and partial least squares (PLS) methods. To establish a support vector machine (SVM) classification and identification model to identify if there is pelvic injury by the reduced dimension data and evaluate the feasibility of its application.@*METHODS@#Eighty percent of 146 normal and injured pelvic CT images were randomly selected as training set for model fitting, and the remaining 20% was used as testing set to verify the accuracy of the test, respectively. Through CT image input, preprocessing, feature extraction, feature information dimension reduction, feature selection, parameter selection, model establishment and model comparison, a discriminative model of pelvic injury was established.@*RESULTS@#The PLS dimension reduction method was better than the PCA method and the SVM model was better than the naive Bayesian classifier (NBC) model. The accuracy of the modeling set, leave-one-out cross validation and testing set of the SVM classification model based on 12 PLS factors was 100%, 100% and 93.33%, respectively.@*CONCLUSIONS@#In the evaluation of pelvic injury, the pelvic injury data mining model based on CT images reaches high accuracy, which lays a foundation for automatic and rapid identification of pelvic injuries.