人工智能技术驱动的法医病理时间类问题解决策略

doi:10.3969/j.issn.1671-2072.2024.03.006

摘要/Abstract

摘要： 在法医病理学领域，死亡时间、损伤时间、血痕遗留时间及血栓形成时间等时间类问题与案发时间及死因分析直接相关，在案件侦破、责任划分和定罪量刑等司法环节中起着关键作用。随着人工智能（artificial intelligence，AI）技术的发展，各行业对数据分析需求持续增加，以模拟人脑为代表的机器学习技术已经应用于医学研究的多个领域，为法医病理时间类问题的解决提供了新的方法和思路。通过对近年涌现出的一系列应用AI技术解决法医病理时间类问题的相关文献进行综述，以期为复杂鉴定问题研究提供帮助和激发新思考，为司法实践活动提供更为科学、客观的鉴定证据。

关键词: 法医病理学, 人工智能, 损伤时间, 死亡时间, 血痕遗留时间, 血栓形成时间

Abstract: In the field of forensic pathology，time related issues such as postmortem interval (PMI)，the age of wound，the age of bloodstain，and age of thrombosis are directly related with the cause of death and the time of incident. Issues above play a key role in forensic links such as case investigation，responsibilities allocation，and conviction and sentencing. With the development of artificial intelligence (AI) technology, the demand for data analysis in various industries continues to increase. Machine learning technology represented by simulated human brain has been applied in many fields of medical research，providing new methods and ideas for solving forensic pathological time problems. This article reviews a series of relevant papers on the application of AI technology in solving time related problems in recent years，hoping to provide assistance and stimulate new ideas for complex forensic problems，and provide more scientific and objective evidence for forensic practice.

Key words: forensic pathology, artificial intelligence (AI), wound age, postmortem interval（PMI）, the age of bloodstain, the age of thrombosis

中图分类号:

DF793.1
TP18

李娜, 张书芮, 孙俊红. 人工智能技术驱动的法医病理时间类问题解决策略[J]. 中国司法鉴定, 2024(3): 41-48.

LI Na, ZHANG Shurui, SUN Junhong. Strategies Driven by Artificial Intelligence Technology for Time Problems in Forensic Pathology[J]. Chinese Journal of Forensic Sciences, 2024(3): 41-48.

导出引用管理器 EndNote|Ris|BibTeX

链接本文: http://www.chsfjd.cn/CN/10.3969/j.issn.1671-2072.2024.03.006

http://www.chsfjd.cn/CN/Y2024/V0/I3/41

参考文献

[ 1 ] SAJID M，TAJ I A，BAJWA U I，et al. Facial asymmetry-based age group estimation：Role in recognizing age-separated face images[J]. Journal of Forensic Sciences，2018，63（6）：1727-1749.
[ 2 ] ZHANG K，YAN H，LIU R N，et al. Exploring metabolic alterations associated with death from asphyxia and the differentiation of asphyxia from sudden cardiac death by gc-hrms-based untargeted metabolomics[J]. Journal of Chromatography B，2021，1171：122638.
[ 3 ] ŠTEPANOVSKÝ M，IBROVÁ A，BUK Z，et al. Novel age estimation model based on development of permanent teeth compared with classical approach and other modern data mining methods[J]. Forensic Science International，2017，279：72-82.
[ 4 ] ZHANG J，ZHOU Y，VIEIRA D N，et al. An efficient method for building a database of diatom populations for drowning site inference using a deep learning algorithm[J]. International Journal of Legal Medicine，2021，135（3）：817-827.
[ 5 ] 黄平，张吉，邹冬华，等. 数字化与智能化技术在法医病理学鉴定中的研究现状与挑战[J]. 中国司法鉴定，2023（2）：35-47.
[ 6 ] TOURNOIS L，TROUSSET V，HATSCH D，et al. Artificial intelligence in the practice of forensic medicine：A scoping review[J]. International Journal of Legal Medicine，2024，138（3）：1023-1037.
[ 7 ] PIRAIANU A I，FULGA A，MUSAT C L，et al. Enhancing the evidence with algorithms：How artificial intelligence is transforming forensic medicine[J]. Diagnostics，2023，13（18）：2992.
[ 8 ] BREIMAN L. Random forests[J]. Machine Learning，2001，45（1）：5-32.
[ 9 ] ANGRA S，AHUJA S. Machine learning and its applications：A review[C]//Proceedings of the 2017 International Conference on Big Data Analytics and Computational Intelligence （ICBDAC）. Washington，D.C.，USA：IEEE Press，2017：23-25.
[10] LECUN Y，BENGIO Y，HINTON G. Deep learning[J]. Nature，2015，521（7553）：436-444.
[11] CASSE J M，MARTRILLE L，VIGNAUD J M，et al. Skin wounds vitality markers in forensic pathology：An updated review[J]. Medicine，Science，and the Law，2016，56（2）：128-137.
[12] LI N，DU Q X，BAI R F，et al. Vitality and wound-age estimation in forensic pathology：Review and future prospects[J]. Forensic Sciences Research，2018，5（1）：15-24.
[13] TIRADO J，MAURICIO D. Bruise dating using deep learning[J]. Journal of Forensic Sciences，2021，66（1）：336-346.
[14] DU Q X，WANG L，LI D，et al. Estimating the time of skeletal muscle contusion based on the spatial distribution of neutrophils：A practical approach to forensic problems[J]. International Journal of Legal Medicine，2022，136（1）：149-158.
[15] BARINGTON K，JENSEN H E，SKOVGAARD K. Forensic aspects of gene expression signatures for age determination in bruises as evaluated in an experimental porcine model[J]. Forensic Science，Medicine，and Pathology，2017，13（2）：151-160.
[16] DU Q X，LI N，DANG L H，et al. Temporal expression of wound healing-related genes inform wound age estimation in rats after a skeletal muscle contusion：A multivariate statistical model analysis[J]. International Journal of Legal Medicine，2020，134（1）：273-282.
[17] DANG L H，FENG N，AN G S，et al. Novel insights into wound age estimation：Combined with “up，no change，or down” system and cosine similarity in python environment[J]. International Journal of Legal Medicine，2020，134（6）：2177-2186.
[18] DANG L H，LI J，BAI X，et al. Novel prediction method applied to wound age estimation：Developing a stacking ensemble model to improve predictive performance based on multi-mRNA[J]. Diagnostics，2023，13（3）：395.
[19] REN K，WANG L L，WANG Y F，et al. Wound age estimation based on next-generation sequencing：Fitting the optimal index system using machine learning[J]. Forensic Science International，2022，59：102722.
[20] CAO J，AN G S，LI J，et al. Combined metabolomics and tandem machine-learning models for wound age estimation：A novel analytical strategy[J]. Forensic Sciences Research，2023，8（1）：50-61.
[21] 马星宇，程浩，张忠铎，等.代谢组学技术结合机器学习算法在损伤时间推断中的研究进展[J]. 法医学杂志，2023，39（6）：596-600.
[22] NAPOLI P E，NIOI M，D'ALOJA E，et al. Post-mortem corneal thickness measurements with a portable optical coherence tomography system：A reliability study[J]. Scientific Reports，2016，6：30428.
[23] CANTÜRK İ，ÖZYILMAZ L. A computational approach to estimate postmortem interval using opacity development of eye for human subjects[J]. Computers in Biology and Medicine，2018，98：93-99.
[24] ZHANG J，WEI X，HUANG J，et al. Attenuated total reflectance Fourier transform infrared （ATR-FTIR） spectral prediction of postmortem interval from vitreous humor samples[J]. Analytical and Bioanalytical Chemistry，2018，410（29）：7611-7620.
[25] METCALF J L，XU Z Z，WEISS S，et al. Microbial community assembly and metabolic function during mammalian corpse decomposition[J]. Science，2016，351（6269）：158-162.
[26] 赵广众，梁宇，董春楠. 应用法医微生物学推断死亡时间研究进展[J]. 刑事技术，2024，49（1）：80-84.
[27] METCALF J L，PARFREY L W，GONZALEZ A，et al. A microbial clock provides an accurate estimate of the postmortem interval in a mouse model system[J]. eLife，2013，2：1-19.
[28] LIU R N，GU Y X，SHEN M W，et al. Predicting postmortem interval based on microbial community sequences and machine learning algorithms[J]. Environmental Microbiology，2020，22（6）：2273-2291.
[29] JOHNSON H R，TRINIDAD D D，GUZMAN S，et al. A machine learning approach for using the postmortem skin microbiome to estimate the postmortem interval[J]. PLoS One，2016，11（12）：e0167370.
[30] LI N，LIANG X R，ZHOU S D，et al. Exploring postmortem succession of rat intestinal microbiome for PMI based on machine learning algorithms and potential use for humans[J]. Forensic Science International Genetics，2023，66：102904.
[31] DONALDSON A E，LAMONT I L. Metabolomics of post-mortem blood：Identifying potential markers of post-mortem interval[J]. Metabolomics，2015，11（1）：237-245.
[32] ZHANG F Y，WANG L L，DONG W W，et al. A preliminary study on early postmortem submersion interval （PMSI） estimation and cause-of-death discrimination based on nontargeted metabolomics and machine learning algorithms[J]. International Journal of Legal Medicine，2022，136（3）：941-954.
[33] LU X J，LI J，WEI X，et al. A novel method for determining postmortem interval based on the metabolomics of multiple organs combined with ensemble learning techniques[J]. International Journal of Legal Medicine，2023，137（1）：237-249.
[34] DU Q X，ZHANG S，LONG F H，et al. Combining with lab-on-chip technology and multi-organ fusion strategy to estimate post-mortem interval of rat[J]. Frontiers in Medicine，2022，9：1083474.
[35] 吴世豪，王继芬，白海涛，等. 基于昆虫证据推断死亡时间的研究进展[J]. 应用昆虫学报，2022，59（3）：469-488.
[36] 任立品，尚艳杰，郭亚东. 昆虫学证据在法庭科学中的应用及进展[J]. 法医学杂志，2021，37（3）：295-304.
[37] WANG Y，WANG Y H，WANG M，et al. Forensic entomology in China and its challenges[J]. Insects，2021，12（3）：230.
[38] 王禹，廖明庆，王颖慧，等. 应用嗜尸性昆虫推断死亡时间11例[J]. 法医学杂志，2021，37（3）：332-337.
[39] 沈肖，廖良柱，旦增晋美，等. 高原地区利用法医昆虫学推断死亡时间2例[J]. 刑事技术，2022，47（6）：652-656.
[40] BUTCHER J B，MOORE H E，DAY C R，et al. Artificial neural network analysis of hydrocarbon profiles for the ageing of Lucilia sericata for post mortem interval estimation[J]. Forensic Science International，2013，232（1/2/3）：25-31.
[41] MOORE H E，BUTCHER J B，DAY C R，et al. Adult fly age estimations using cuticular hydrocarbons and artificial neural networks in forensically important calliphoridae species[J]. Forensic Science International，2017，280：233-244.
[42] 李奕. 法医昆虫学PMI推断相关软件开发及应用[D]. 长沙：中南大学，2023.
[43] 夏鹏，彭谨，刘振江，等. 基于集成学习技术对死亡时间的研究[J]. 中国法医学杂志，2022，37（4）：323-326.
[44] BREMMER R H，DE BRUIN K G，VAN GEMERT M J C，et al. Forensic quest for age determination of bloodstains[J]. Forensic Science International，2012，216（1/2/3）：1-11.
[45] 杨志超，赵森，蔡竞，等. 基于拉曼光谱的血液遗留时间研究与模型预测[J]. 中国法医学杂志，2022，37（1）：61-64.
[46] TSUTSUMI A，YAMAMOTO Y，ISHIZU H. Determination of the age of bloodstains by enzyme activities in blood cells[J]. Nihon Hoigaku Zasshi，1983，37（6）：770-776.
[47] BAUER M，POLZIN S，PATZELT D. Quantification of RNA degradation by semi-quantitative duplex and competitive RT-PCR：A possible indicator of the age of bloodstains?[J]. Forensic Science International，2003，138（1/2/3）：94-103.
[48] FU J，ALLEN R W. A method to estimate the age of bloodstains using quantitative PCR[J]. Forensic Science International Genetics，2019，39：103-108.
[49] 孙婷怡，刘良，杨天潼，等. 家兔死后离体血液ATP含量变化与放置时间的关系[J]. 中国法医学杂志，2012，27（2）：93-96.
[50] 冯颖，蔡竞. 基于高光谱成像技术的不同介质血迹陈旧度研究[J]. 激光与光电子学进展，2020，57（5）：279-284.
[51] LEE S，MUN S，LEE Y R，et al. Validation of the metabolite ergothioneine as a forensic marker in bloodstains[J]. Molecules，2022，27（24）：8885.
[52] GIULIETTI N，DISCEPOLO S，CASTELLINI P，et al. Neural network based hyperspectral imaging for substrate independent bloodstain age estimation[J]. Forensic Science International，2023，349：111742.
[53] MARRONE A，LA RUSSA D，MONTESANTO A，et al. Short and long time bloodstains age determination by colorimetric analysis：A pilot study[J]. Molecules，2021，26（20）：6272.
[54] SEOK A E，LEE J，LEE Y R，et al. Estimation of age of bloodstains by mass-spectrometry：A metabolomic app-roach[J]. Analytical Chemistry，2018，90（21）：12431-12441.
[55] WORLEY B，HALOUSKA S，POWERS R. Utilities for quantifying separation in PCA/PLS-DA scores plots[J]. Analytical Biochemistry，2013，433（2）：102-104.
[56] ROHART F，GAUTIER B，SINGH A，et al. Mixomics：An R package for ’omics feature selection and multiple data integration[J]. PLoS Computational Biology，2017，13（11）：e1005752.
[57] RUIZ-PEREZ D，GUAN H，MADHIVANAN P，et al. So you think you can PLS-DA?[J]. BMC Bioinformatics，2020，21（S1）：2.
[58] LI H Y，SHEN C，WANG G J，et al. BloodNet：An attention-based deep network for accurate，efficient，and costless bloodstain time since deposition inference[J]. Briefings in Bioinformatics，2023，24（1）：557.
[59] BREMMER R H，DE BRUIN D M，DE JOODE M，et al. Biphasic oxidation of oxy-hemoglobin in bloodstains[J]. PLoS One，2011，6（7）：e21845.
[60] MOLLER P. Studien uber die embolische und autochtone thrombose in der arteria pulmonalis[J]. Beiträge Pathol Anat，1923，71：26.
[61] LEU A J，LEU H J. Special problems in the histologic age determination of thrombi and emboli[J]. Der Pathologe，1989，10（2）：87-92.
[62] IRNIGER W. Histologische altersbestimmung von thrombosen und embolien[J]. Virchows Archiv für Pathologische Anatomie und Physiologie und für klinische Medizin，1963，336（3）：220-237.
[63] 高卫民，林羽赫，曹志鹏，等. 26例肺动脉血栓栓塞的法医学分析[J]. 中国法医学杂志，2011，26（05）：409-410.
[64] DI FAZIO N，DELOGU G，CIALLELLA C，et al. State-of-art in the age determination of venous thromboembolism：A systematic review[J]. Diagnostics，2021，11（12）：2397.
[65] 杨琛腾，左敏，王松军，等. 血栓形成时间的推断[J]. 法医学杂志，2018，34（4）：352-358.
[66] FINESCHI V，TURILLAZZI E，NERI M，et al. Histological age determination of venous thrombosis：A neglected forensic task in fatal pulmonary thrombo-embolism[J]. Forensic Science International，2009，186（1/2/3）：22-28.
[67] NOSAKA M，ISHIDA Y，KIMURA A，et al. Time-dependent appearance of intrathrombus neutrophils and macrophages in a stasis-induced deep vein thrombosis model and its application to thrombus age determination[J]. International Journal of Legal Medicine，2009，123（3）：235-240.
[68] JIN Q Q，SUN J H，DU Q X，et al. Integrating microRNA and messenger RNA expression profiles in a rat model of deep vein thrombosis[J]. International Journal of Molecular Medicine，2017，40（4）：1019-1028.
[69] CAO J，JIN Q Q，WANG G M，et al. Comparison of the serum metabolic signatures based on 1H NMR between patients and a rat model of deep vein thrombosis[J]. Scientific Reports，2018，8（1）：7837.
[70] 任奎，孟泉润，闫守琨，等. 人工智能模型数据泄露的攻击与防御研究综述[J]. 网络与信息安全学报，2021，7（1）：1-10.
[71] 肖雄，唐卓，肖斌，等. 联邦学习的隐私保护与安全防御研究综述[J]. 计算机学报，2023，46（5）：1019-1044.