ABSTRACT
ObjectiveArtificial 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. MethodsLung 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 database 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 pre-training. ResultsThe 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. ConclusionIt 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.
ABSTRACT
OBJECTIVES@#To explore the research hotspots and development trends of the field of forensic drowning from 1991 to 2020 by bibliometrics methods.@*METHODS@#Based on Web of Science, CNKI database, Wanfang Data knowledge service platform, python 3.9.2, CiteSpace 5.8.R3, Gephi 0.9.2, etc. were used to analyze the publishing trends, countries/regions, institutions, authors and topics of the study on drowning.@*RESULTS@#A total of 631 English literature were obtained, including 59 articles from Chinese authors, and 386 Chinese literature were obtained. The Chinese and English journals with the largest number of related literatures were Chinese Journal of Forensic Science (80 articles) and Forensic Science International (106 articles), respectively. Japan published the most articles in English, and China ranked third. Osaka City Univ (Japan, 28 articles) published the most English articles, and Guangzhou Forens Sci Inst (China, 22 articles) ranked second. Among Chinese literature, Guangzhou Forens Sci Inst (32 articles) published the most. The topic analysis of Chinese and English literature showed that diatom examination, virtual autopsy, postmortem biochemical examination, the nature of death, and postmortem submersion interval were the hot spots of current research, but English literature had more studies on new technologies and methods, while Chinese literature was more inclined to practice, application and experience summary.@*CONCLUSIONS@#The number of literature in forensic medicine on drowning is relatively stable. The scope of international and domestic collaborations in this field is still limited. The automated examination of diatoms, the establishment of diatom DNA barcodes and virtual autopsy will be the most important research hotspots in the coming period and are expected to achieve breakthroughs in drowning diagnosis, drowning location inference, postmortem submersion interval estimation, etc.
Subject(s)
Humans , Bibliometrics , China/epidemiology , Drowning/diagnosis , Forensic Medicine , PublicationsABSTRACT
OBJECTIVES@#To select four algorithms with relatively balanced complexity and accuracy among deep learning image classification algorithms for automatic diatom recognition, and to explore the most suitable classification algorithm for diatom recognition to provide data reference for automatic diatom testing research in forensic medicine.@*METHODS@#The "diatom" and "background" small sample size data set (20 000 images) of digestive fluid smear of corpse lung tissue in water were built to train, validate and test four convolutional neural network (CNN) models, including VGG16, ResNet50, InceptionV3 and Inception-ResNet-V2. The receiver operating characteristic curve (ROC) of subjects and confusion matrixes were drawn, recall rate, precision rate, specificity, accuracy rate and F1 score were calculated, and the performance of each model was systematically evaluated.@*RESULTS@#The InceptionV3 model achieved much better results than the other three models with a balanced recall rate of 89.80%, a precision rate of 92.58%. The VGG16 and Inception-ResNet-V2 had similar diatom recognition performance. Although the performance of diatom recall and precision detection could not be balanced, the recognition ability was acceptable. ResNet50 had the lowest diatom recognition performance, with a recall rate of 55.35%. In terms of feature extraction, the four models all extracted the features of diatom and background and mainly focused on diatom region as the main identification basis.@*CONCLUSIONS@#Including the Inception-dependent model, which has stronger directivity and targeting in feature extraction of diatom. The InceptionV3 achieved the best performance on diatom identification and feature extraction compared to the other three models. The InceptionV3 is more suitable for daily forensic diatom examination.
Subject(s)
Humans , Algorithms , Deep Learning , Diatoms , Neural Networks, Computer , ROC CurveABSTRACT
Diatom test is the main laboratory test method in the diagnosis of drowning in forensic medicine. It plays an important role in differentiating the antemortem drowning from the postmortem drowning and inferring drowning site. Artificial intelligence (AI) automatic diatom test is a technological innovation in forensic drowning diagnosis which is based on morphological characteristics of diatom, the application of AI algorithm to automatic identification and classification of diatom in tissues and organs. This paper discusses the morphological diatom test methods and reviews the research progress of automatic diatom recognition and classification involving AI algorithms. AI deep learning algorithm can assist diatom testing to obtain objective, accurate, and efficient qualitative and quantitative analysis results, which is expected to become a new direction of diatom testing research in the drowning of forensic medicine in the future.