Use of Advanced Artificial Intelligence in Forensic Medicine, Forensic Anthropology and Clinical Anatomy

被引:56
作者
Thurzo, Andrej [1 ,2 ,3 ]
Kosnacova, Helena Svobodova [2 ,4 ]
Kurilova, Veronika [5 ]
Kosmel, Silvester [6 ]
Benus, Radoslav [3 ,7 ]
Moravansky, Norbert [3 ,8 ]
Kovac, Peter [3 ,9 ]
Kuracinova, Kristina Mikus [10 ]
Palkovic, Michal [10 ,11 ]
Varga, Ivan [12 ]
机构
[1] Comenius Univ, Fac Med, Dept Stomatol & Maxillofacial Surg, Bratislava 81250, Slovakia
[2] Comenius Univ, Fac Med, Dept Simulat & Virtual Med Educ, Sasinkova 4, Bratislava 81272, Slovakia
[3] Forens Sk Inst Forens Med Analyses Ltd, Bozeny Nemcovej 8, Bratislava 81104, Slovakia
[4] Slovak Acad Sci, Biomed Res Ctr, Canc Res Inst, Dept Genet, Dubravska Cesta 9, Bratislava 84505, Slovakia
[5] Slovak Univ Technol Bratislava, Fac Elect Engn & Informat Technol, Ilkovicova 3, Bratislava 81219, Slovakia
[6] Slovak Univ Technol Bratislava, Deep Learning Engn Dept Cognexa, Fac Informat & Informat Technol, Ilkovicova 2, Bratislava 84216, Slovakia
[7] Comenius Univ, Dept Anthropol, Fac Nat Sci, Mlynska Dolina Ilkovicova 6, Bratislava 84215, Slovakia
[8] Comenius Univ, Inst Forens Med, Fac Med, Sasinkova 4, Bratislava 81108, Slovakia
[9] Trnava Univ, Dept Criminal Law & Criminol, Fac Law, Kollarova 10, Trnava 91701, Slovakia
[10] Comenius Univ, Inst Pathol Anat, Fac Med, Sasinkova 4, Bratislava 81108, Slovakia
[11] Hlth Care Surveillance Author HCSA, Forens Med & Pathol Anat Dept, Sasinkova 4, Bratislava 81108, Slovakia
[12] Comenius Univ, Inst Histol & Embryol, Fac Med, Bratislava 81372, Slovakia
关键词
forensic medicine; forensic dentistry; forensic anthropology; 3D CNN; AI; deep learning; biological age determination; sex determination; 3D cephalometric; AI face estimation; growth prediction; DISCRIMINANT FUNCTION-ANALYSIS; CBCT IMAGE SEGMENTATION; AGE ESTIMATION METHODS; SEX DETERMINATION; NEURAL-NETWORK; OPEN APICES; LANDMARK ANNOTATION; CRANIOFACIAL GROWTH; DEVELOPING TEETH; SKELETAL AGE;
D O I
10.3390/healthcare9111545
中图分类号
R19 [保健组织与事业(卫生事业管理)];
学科分类号
摘要
Three-dimensional convolutional neural networks (3D CNN) of artificial intelligence (AI) are potent in image processing and recognition using deep learning to perform generative and descriptive tasks. Compared to its predecessor, the advantage of CNN is that it automatically detects the important features without any human supervision. 3D CNN is used to extract features in three dimensions where input is a 3D volume or a sequence of 2D pictures, e.g., slices in a cone-beam computer tomography scan (CBCT). The main aim was to bridge interdisciplinary cooperation between forensic medical experts and deep learning engineers, emphasizing activating clinical forensic experts in the field with possibly basic knowledge of advanced artificial intelligence techniques with interest in its implementation in their efforts to advance forensic research further. This paper introduces a novel workflow of 3D CNN analysis of full-head CBCT scans. Authors explore the current and design customized 3D CNN application methods for particular forensic research in five perspectives: (1) sex determination, (2) biological age estimation, (3) 3D cephalometric landmark annotation, (4) growth vectors prediction, (5) facial soft-tissue estimation from the skull and vice versa. In conclusion, 3D CNN application can be a watershed moment in forensic medicine, leading to unprecedented improvement of forensic analysis workflows based on 3D neural networks.
引用
收藏
页数:25
相关论文
共 166 条
[1]  
Abdulatif S., ARXIV107651437, DOI [10.1109/TMI.2021.3066857, DOI 10.1109/TMI.2021.3066857]
[2]  
Afrianty I., 2014, ADV COMPUTER SCI ITS, P723, DOI [DOI 10.1007/978-3-642-41674-3_103, 10.1007/978-3-642-41674-3103, DOI 10.1007/978-3-642-41674-3103]
[3]  
Al-Nakib LH., 2013, Dentistry, V25, P54, DOI DOI 10.12816/0014931
[4]   A review of the literature on the aging adult skull and face: Implications for forensic science research and applications [J].
Albert, A. Midori ;
Ricanek, Karl, Jr. ;
Patterson, Eric .
FORENSIC SCIENCE INTERNATIONAL, 2007, 172 (01) :1-9
[5]  
[Anonymous], 2009, Journal of Visual Languages and Computing
[6]  
[Anonymous], 2005, Semin Orthod, DOI [10.1053/J.SODO.2005.04.005, 10.1053/j.sodo.2005.04.005, DOI 10.1053/J.SODO.2005.04.005]
[7]  
Arcari S.R, 2015, J PLASTIC DERMATOLOG, V11, P1
[8]   Fully automated quantitative cephalometry using convolutional neural networks [J].
Arik S.Ö. ;
Ibragimov B. ;
Xing L. .
Journal of Medical Imaging, 2017, 4 (01)
[9]  
Armanious K, 2021, EUR SIGNAL PR CONF, P1225, DOI 10.23919/Eusipco47968.2020.9287398
[10]   Accuracy of an automated method of 3D soft tissue landmark detection [J].
Baksi, Sanjana ;
Freezer, Simon ;
Matsumoto, Takeshi ;
Dreyer, Craig .
EUROPEAN JOURNAL OF ORTHODONTICS, 2021, 43 (06) :622-630