基于深度学习的MRI骨龄评估研究进展

骨龄作为年龄认定的重要依据之一，是法医学的重点研究内容。现有主流骨龄评估方法多基于骨关节X线片，虽已达到较高的准确性，但此类方法主要基于人工阅片，耗时、依赖经验，且非诊疗目的的放射性检查当下备受争议。磁共振成像（magnetic resonance imaging,MRI）是无辐射的三维断层图像，具有优越的骺板软骨成像能力，可清晰显示骨骺生长发育情况，将骨骼MRI用于骨龄评估已成为解决辐射风险的可行策略。同时，随着深度学习的不断进步与发展，使其在图像分析和大数据处理方面的优势逐渐显现。因此，将深度学习与骨骼MRI有机融合进行骨龄评估已成为近年来法医骨龄评估领域新的研究前沿和热点。基于此，通过综述近年来国内外基于深度学习的MRI骨龄评估研究，系统总结了基于深度学习及骨骼MRI的骨龄评估新技术、新方法，以期为骨龄评估研究提供新的思路与参考。     

X线骨龄评估方法研究进展与展望

骨龄评估的传统方法主要包括计数法、图谱法及计分法等,近年来又有一些学者不断提出其他新的方法。利用骨骼X线片影像学特征推断骨龄是当前法医学工作者进行骨龄评估的主要手段。但是,将此骨龄推断结论作为"证据"直接提供给司法审判机关,因其存在着一定的误差尚值得商榷。因此,为了提高骨龄鉴定结论的精确度,还需进行更多方法学的研究。经参阅国内、外大量相关文献,现就X线片骨龄评估方法的研究与进展进行综述。     

深度学习在图像识别及骨龄评估中的优势及应用前景

深度学习以及神经网络模型是近年来机器学习及人工智能领域新的研究方向及热点问题。深度学习在图像识别、语音识别应用中已取得了突破性进展,在人脸识别、信息检索等领域也展示出独特优势,得到了广泛应用。骨骼X线图像显示黑白灰不同阶度的变化,具有黑白对比、层次差异的图像特征,基于深度学习在图像识别中的优势,我们将其与骨龄评估研究有机结合,旨在为构建法医学骨龄自动化评估系统提供基础性数据。本文综述了深度学习的基本概念及其网络结构,阐述了近年来深度学习在国内外不同研究领域图像识别中的研究进展,以及深度学习在骨龄评估中的优势及应用前景。     

薄层CT扫描技术在锁骨胸骨端骨龄评估中的应用进展

评估锁骨胸骨端骨龄对于推断青少年是否已满18周岁法定责任年龄具有实用价值,传统的研究方法主要基于X线检查,但由于锁骨胸骨端与相邻的肺、支气管、胸骨、肋骨及胸椎横突等解剖结构相互重叠,通过X线观察锁骨胸骨端骨骺发育时,较易出现假阴性或假阳性的阅片结果,直接影响骨龄鉴定意见的科学性与准确性。近年来,国内外已有学者运用薄层CT扫描技术评估锁骨胸骨端骨龄,并通过联合CT二维、三维图像重组技术,使骨骺形状、大小及位置得以清晰显示,提高了结果的准确性。据此,本文综述了国内外关于薄层CT扫描技术在锁骨胸骨端骨龄评估中的应用及研究进展,分析薄层CT扫描技术运用于锁骨胸骨端骨龄研究的优势以及价值所在。     

机器学习在骨龄评估中的研究进展及展望

骨龄评估一直是法医学研究领域的重点及难点问题之一。近年来,随着机器学习在诸多行业内的逐渐兴起,其已被广泛引入影像学、基因组学、肿瘤学、病理学以及外科学等医学研究领域中。上述研究领域之所以能与机器学习紧密结合,主要是由于上述医学分支学科中的研究对象属于计算机视觉范畴,而机器学习对于计算机视觉研究有着得天独厚的优势,并在医学图像识别中取得突破性进展。基于机器学习在图像识别中的优势,将其与骨龄评估研究有机结合,旨在为构建适用于法医学骨骼影像图片的识别模型。基于此,本文将对近年来国内外学者运用机器学习技术在骨龄评估中的研究进展进行综述。     

基于MRI推断青少年活体骨龄的研究现状与展望

青少年活体骨龄推断在司法审判、儿童生长发育、竞技体育等多领域具有重要价值,但目前骨龄鉴定实践囿于放射性检查的伦理学困境,且现有标准体系难以满足我国新近刑事责任年龄节点下调的现实需求,是当下法医学骨龄推断理论与实践的瓶颈.本文从MRI这一无辐射影像技术出发,阐述其近年来应用MRI推断青少年活体骨龄的研究现状,并分析目前存...     

基于深度学习实现维吾尔族青少年左手腕关节骨龄自动化评估

目的将深度学习运用于维吾尔族青少年左手腕关节数字化X线摄影(digital radiography,DR)图像识别中,实现骨龄评估的自动化,探索该方法在法医骨龄鉴定中的应用价值。方法在我国新疆维吾尔自治区采集13.0~19.0岁维吾尔族男性青少年245例、女性青少年227例左手腕关节DR图像,将预处理后的图像作为研究对象,将AlexNet作为图像识别的回归模型。在上述总样本中分别选取男、女性60%左手腕关节DR图像样本作为网络训练集,10%的样本作为验证集,余30%作为测试集,获取与样本真实年龄误差范围分别在±1.0岁、±0.7岁以内的图像识别准确率。结果深度学习的内测结果:误差范围在±1.0岁及±0.7岁以内的网络训练集准确率,男性分别为81.4%和75.6%,女性分别为80.5%和74.8%。误差范围在±1.0岁及±0.7岁以内的测试集准确率,男性分别为79.5%和71.2%,女性分别为79.4%和66.2%。结论青少年左手腕关节骨龄研究与深度学习相结合,具有较高的准确性及较好的可行性,为躯体其余骨关节的骨龄自动化评估体系奠定研究基础。     

司法鉴定中303例骨龄小于“年龄”分析

目的探讨司法鉴定中骨龄小于"年龄"的现象和可能原因。方法参考中国人手腕骨发育标准CHN法附带的检验样本所提供的骨龄验证值,结合鉴定时公安机关提供的"年龄"、"户籍"等相关资料,并追踪回访部分案例,对829例使用CHN法行骨龄司法鉴定资料进行回顾性分析。结果骨龄小于"年龄"共303例,占(303/829)36.6%,在742例有"年龄"案例组中占(303/742)40.8%。如以两者差值小于0.5岁(含0.5岁)为正常范围内计则降至190例,所占比例为(190/829)22.9%和(190/742)25.6%。差值在0.5岁以内时与骨龄值相近的"年龄"可信度最高,在0.6～2.0岁时难以确定何者有误,但随差值增大"年龄"有误可能性上升。"年龄"和骨龄本身诸多不确定因素均可导致骨龄小于"年龄",并可能是多种因素共同影响的结果。结论在鉴定实践中骨龄小于"年龄"发生率不低;鉴定结论以综合评估后谨慎使用为宜。     

青少年骨龄鉴定及其相关问题

本文综述了骨龄研究和应用历史,以及骨龄评测的新方法和新技术,讨论了骨骼发育的影响因素、骨龄标准时效性、骨龄评测部位选择及法医骨龄鉴定等相关问题。     

青少年骨龄标准身高、体重和体重指数生长图表

目的制订青少年骨龄标准身高、体重和体重指数生长图表,为年龄推测时评价青少年基本发育状况提供参考。方法研究样本为2005年中国5城市抽取的3-19岁汉族正常青少年和儿童16570名（男8282,女8288）。应用RUS-CHN法评价受试者手腕部骨龄,由Box-Cox幂指数分布（Box-Cox power exponential distribution,BCPE）模型估价以骨龄分组的身高、体重和体重指数（Body mass index,BMI）百分位数。结果根据最小Akaike信息准测（Akaike Information Criterion,AIC）和广义AIC（Generalized AIC）选择了身高、体重和BMI BCPE模型μ,σ,ν,τ参数的自由度,依据BCPE模型所估价的百分位数曲线下样本例数的百分数与理论期望值相差在0.01%-1.21%之间。结论所选择的BCPE模型符合青少年儿童样本以骨龄分组的身高、体重和BMI数据的实际分布,所提出的生长图表可用于年龄推测中青少年基本生长发育状况的评价。     

CT技术在法医人类学研究中应用的进展

近年来,将计算机断层扫描(CT)等影像学新技术应用于法医人类学个体识别的研究受到国内外法医人类学家的重视。CT具有清晰快速的成像能力以及强大的后处理功能,无需骨骼前处理就能提供高分辨率模型图像,对法医人类学具有重要的研究和应用价值。本文就CT技术在法医人类学研究中应用的进展进行综述,以期为相关研究和实践提供参考和借鉴。     

Risk of sexual recidivism as a function of age and actuarial risk

Abstract

The study of risk for sexual recidivism has undergone substantial development in recent years. The foundation for advances in this area has been the use of actuarial measures to identify subgroups of offenders with different observed rates of sexual re-offending over time. An unresolved issue within this research area has been the moderating function of age in the assessment of risk. The current study examined sexual re-offending as a function of age and actuarial risk in a large sample of sexual offenders released from prison between 1990 and 2004. There was an overall decrease in the rate of sexual re-offending over the age of 50. However, a small group of offenders from the higher actuarial risk categories of the older age groups continued to re-offend at higher rates than their lower-risk peers.     

The development of an automatic recognition system for earmark and earprint comparisons

The value of earmarks as an efficient means of personal identification is still subject to debate. It has been argued that the field is lacking a firm systematic and structured data basis to help practitioners to form their conclusions. Typically, there is a paucity of research guiding as to the selectivity of the features used in the comparison process between an earmark and reference earprints taken from an individual. This study proposes a system for the automatic comparison of earprints and earmarks, operating without any manual extraction of key-points or manual annotations. For each donor, a model is created using multiple reference prints, hence capturing the donor within source variability. For each comparison between a mark and a model, images are automatically aligned and a proximity score, based on a normalized 2D correlation coefficient, is calculated. Appropriate use of this score allows deriving a likelihood ratio that can be explored under known state of affairs (both in cases where it is known that the mark has been left by the donor that gave the model and conversely in cases when it is established that the mark originates from a different source). To assess the system performance, a first dataset containing 1229 donors elaborated during the FearID research project was used. Based on these data, for mark-to-print comparisons, the system performed with an equal error rate (EER) of 2.3% and about 88% of marks are found in the first 3 positions of a hitlist. When performing print-to-print transactions, results show an equal error rate of 0.5%. The system was then tested using real-case data obtained from police forces.     

肋软骨分析检验技术在法医学中的应用

传统法医人类学对肋软骨的分析检验仅限于形态学检验.近年来,法医影像学以及分子遗传学的发展丰富了人类肋软骨的分析检验技术,并且已经能够运用于法医学实践中.本文从肋软骨的组织学特性入手,综述了近年来肋软骨在法医人类学性别判定、年龄推断等方面的研究进展,以期为同行提供借鉴和参考.     

Ontogeny of Size and Shape Sexual Dimorphism in the Pubis: A Multislice Computed Tomography Study by Geometric Morphometry

Few studies have been conducted to determine sex differences in the immature coxal bone and the results were often contradictory. The authors studied sexual dimorphic differences of the pubis using geometric morphometric analysis of five osteometric landmarks recorded by multislice computed tomography (MSCT), based on three‐dimensional reconstructions of 188 children (95 boys, 93 girls) living in the region of Toulouse, southwestern France, ranging in age from 1 to 18 years old. They used geometric morphometric methodology first to test sexual dimorphism in size (centroid size) and shape (Procrustes residuals) and second to examine patterns of shape change with age (development) and size change with age (growth). Based on statistical significance test results, the pubic shape became sexually dimorphic at 13 years old, although visible shape differences were observed as early as 9 years old. This work showed that the trajectories of pubis shape (development) and size (growth) differed throughout ontogeny and between sexes.     

On risking risk assessment of delinquent juveniles: some questions concerning the role of psychopathy

In recent years much research effort has been directed at assessing psychopathic personality disorder in juveniles and at devising structured assessment procedures for recidivism risk. Clinicians, however, are often reluctant to incorporate this recent research into their practice. While accepting the importance of a better understanding of the development of psychopathic personality disorder, we discuss three arguments against the uncritical application of current research findings concerning the disorder and its clinical value as a risk factor. We briefly review empirical evidence for the role of the disorder in risk assessment. A developmental psychopathology argument against current thinking about juvenile psychopathic personality disorder, and a criminological argument against risk assessment but in favor of a desistance approach to delinquency are discussed.     

司法透明度指数及其研究方法

近年来,法学实证研究逐渐成为法学研究的一种重要方法,法治量化研究是实证研究中最为重要的方法之一,不仅逐渐为法学界接受,也得到实务部门的认可。十八届三中全会决定提出,要“建立科学的法治建设指标体系和考核标准”,推动了法治量化研究的深人发展。     

利用额窦影像进行个体识别的研究进展

鉴于额窦不规则气腔形态的高度特异性、成熟后形态不变的稳定性以及放射学技术在临床的广泛应用,额窦影像已成为法医学个体识别的重要研究对象。利用额窦影像进行个体识别已具有法庭意义。当DNA和指纹等传统个体识别方法应用受限或无法有效进行,或缺乏相应的牙科记录等情况时,额窦影像对比是有效的个体识别替代方法。多种影像资料都可用于额窦的个体识别,以人工视觉观测分析为主要方式,受专业性要求高、效率低及应用范围小等限制,无法有效应用于大型灾难等情况。近年来,一些计算机图像识别技术被应用于额窦影像的识别中,能显著提高识别的效率,有望克服人工识别效率低等应用困难。本研究对额窦影像用于法医学个体识别的报道进行总结,以回顾额窦影像用于个体识别的研究进展,为额窦影像的进一步研究提供参考,为探索及建立一套更加快捷、高效及准确的个体识别方法提供思路。