酶消化法结合人工智能技术在法医学溺死硅藻检验中的应用  

Enzym atic Digestion Method Coupled with Artificial Intelligence Techniques in Forensic Drowning Diatom Detection

作　　者：于慧潇 朱永正 赵天琦 程奇 李周儒 殷文江 陈敏 蔡红星 YU Hui-xiao;ZHU Yong-zheng;ZHAO Tian-qi;CHENG Qi;LI Zhou-ru;YIN Wen-jiang;CHEN Min;CAI Hong-xing(Department of Forensic Medicine,Xuzhou Medical University,Xuzhou 221000,China;Shanghai Key Laboratory of Forensic Medicine/Key Laboratory of Forensic Science,Ministry of Justice/Shanghai Forensic Service Platform/Acade-my of Forensic Science,Shanghai 200063,China;Criminal Investigation Brigade,Economic and Technological Devel-opment Zone Subbureau,Xi’an Public Security Bureau,Xi’an,710018,China;Suzhou Public Security Bureau,Su-zhou 21500,China)

机构地区：[1]徐州医科大学法医学教研室,江苏徐州221000 [2]司法鉴定科学研究院/上海市法医学重点实验室/司法部司法鉴定重点实验室/上海市司法鉴定专业技术服务平台,上海200063 [3]西安市公安局经济技术开发区分局刑事侦查大队,陕西西安710018 [4]苏州市公安局,江苏苏州215000

出　　处：《中山大学学报（医学科学版）》2023年第3期430-438,共9页Journal of Sun Yat-Sen University:Medical Sciences

基　　金：上海市法医学重点实验室,司法部司法鉴定重点实验室开放基金(KF202004);江苏省普通高校研究生科研、实践创新计划项目(KYCX22_2876)。

摘　　要：【目的】人工智能(AI)全涂片自动化硅藻检验技术能比人类专家更快速、高效进行法医病理学溺死硅藻检验。然而,该技术仅与硅藻提取率较低的硝酸消化法联用过,本研究拟采用更加高效的蛋白酶K组织消解法(以下简称酶消化法)作为硅藻提取方法,探究该技术在其他硅藻提取方法中的泛化能力及可行性。【方法】收集6例溺死尸体的肺组织进行蛋白酶K消解并制成涂片,利用数字化图像矩阵切割方法将涂片进行数字化处理并据此建立硅藻-背景数据库,将数据集按照3:1:1的比例分为训练集、验证集和测试集,在ImageNet预训练基础上对卷积神经网络(CNN)模型进行训练和内部验证及外部测试。【结果】结果显示最佳模型外部测试的准确率达97.65%,且模型特征提取区域即为硅藻所在区域。实际应用中最佳的CNN模型对溺水尸体的硅藻检测精准率高达80%以上。【结论】研究表明,基于CNN模型的AI自动化硅藻检验技术和酶消化法联用能高效识别硅藻,可以作为溺水鉴定中硅藻检测的辅助方法。【Objective】Artificial intelligence(AI)full smear automated diatom detection technology can perform forensic pathology drowning diatom detection more quickly and efficiently than human experts.However,this technique was only used in conjunction with the strong acid digestion method,which has a low extraction rate of diatoms.In this study,we propose to use the more efficient proteinase K tissue digestion method(hereinafter referred to as enzyme digestion method)as a diatom extraction method to investigate the generalization ability and feasibility of this technique in other diatom extraction methods.【Methods】Lung tissues from 6 drowned cadavers were collected for proteinase K ablation and made into smears,and the smears were digitized using the digital image matrix cutting method and a diatom and background data-base was established accordingly.The data set was divided into training set,validation set and test set in the ratio of 3:1:1,and the convolutional neural network(CNN)models were trained,internally validated,and externally tested on the basis of ImageNet pretraining.【Results】The results showed that the accuracy rate of the external test of the best model was 97.65%,and the area where the model features were extracted was the area where the diatoms were located.The best CNN model in practice had a precision of more than 80%for diatom detection of drowned corpses.【Conclusion】It is shown that the AI automated diatom detection technique based on CNN model and enzymatic digestion method in combination can efficiently identify diatoms and can be used as an auxiliary method for diatom detection in drowning identification.

关 键 词：法医病理学 硅藻 溺死 蛋白酶K 人工智能 卷积神经网络 

分 类 号：R89[医药卫生—法医学]