Matsunobu Yusuke, Morishita Junji, Usumoto Yosuke, Okumura Miki, Ikeda Noriaki
Department of Health Sciences, Graduate School of Medical Sciences, Kyushu University, Fukuoka 812-8582, Japan.
Department of Health Sciences, Faculty of Medical Sciences, Kyushu University, Fukuoka 812-8582, Japan.
Leg Med (Tokyo). 2017 Nov;29:1-5. doi: 10.1016/j.legalmed.2017.08.002. Epub 2017 Aug 31.
The aim of this study is to examine the usefulness of bone structure extracted data from chest computed tomography (CT) images for personal identification. Eighteen autopsied cases (12 male and 6 female) that had ante- and post-mortem (AM and PM) CT images were used in this study. The two-dimensional (2D) and three-dimensional (3D) bone images were extracted from the chest CT images via thresholding technique. The similarity between two thoracic bone images (consisting of vertebrae, ribs, and sternum) acquired from AMCT and PMCT images was calculated in terms of the normalized cross-correlation value (NCCV) in both 2D and 3D matchings. An AM case with the highest NCCV corresponding to a given PM case among all of the AM cases studied was regarded as same person. The accuracy of identification of the same person using our method was 100% (18/18) in both 2D and 3D matchings. The NCCVs for the same person tended to be significantly higher than the average of NCCVs for different people in both 2D and 3D matchings. The computation times of image similarity between the two images were less than one second and approximately 10min in 2D and 3D matching, respectively. Therefore, 2D matching especially for thoracic bones seems more advantageous than 3D matching with regard to computation time. We conclude that our proposed personal identification method using bone structure would be useful in forensic cases.
本研究的目的是检验从胸部计算机断层扫描（CT）图像中提取的骨骼结构数据用于个人识别的有效性。本研究使用了18例有生前和死后（AM和PM）CT图像的尸检病例（12例男性和6例女性）。通过阈值技术从胸部CT图像中提取二维（2D）和三维（3D）骨骼图像。根据2D和3D匹配中的归一化互相关值（NCCV）计算从AMCT和PMCT图像获取的两幅胸部骨骼图像（由椎骨、肋骨和胸骨组成）之间的相似度。在所有研究的AM病例中，与给定PM病例对应的NCCV最高的AM病例被视为同一人。使用我们的方法在2D和3D匹配中识别同一人的准确率均为100%（18/18）。在2D和3D匹配中，同一人的NCCV往往显著高于不同人的NCCV平均值。两幅图像之间的图像相似度计算时间在2D匹配中小于1秒，在3D匹配中约为10分钟。因此，就计算时间而言，特别是对于胸部骨骼的2D匹配似乎比3D匹配更具优势。我们得出结论，我们提出的使用骨骼结构的个人识别方法在法医案件中将会有用。
