Andalusian Research Institute DaSCI, University of Granada, Granada, Spain.
Department of Computer Science and Artificial Intelligence, University of Granada, Granada, Spain.
Int J Legal Med. 2024 Jan;138(1):307-327. doi: 10.1007/s00414-023-03080-4. Epub 2023 Oct 6.
Comparative radiography is a forensic identification and shortlisting technique based on the comparison of skeletal structures in ante-mortem and post-mortem images. The images (e.g., 2D radiographs or 3D computed tomographies) are manually superimposed and visually compared by a forensic practitioner. It requires a significant amount of time per comparison, limiting its utility in large comparison scenarios.
We propose and validate a novel framework for automating the shortlisting of candidates using artificial intelligence. It is composed of (1) a segmentation method to delimit skeletal structures' silhouettes in radiographs, (2) a superposition method to generate the best simulated "radiographs" from 3D images according to the segmented radiographs, and (3) a decision-making method for shortlisting all candidates ranked according to a similarity metric.
The dataset is composed of 180 computed tomographies and 180 radiographs where the frontal sinuses are visible. Frontal sinuses are the skeletal structure analyzed due to their high individualization capability.
Firstly, we validate two deep learning-based techniques for segmenting the frontal sinuses in radiographs, obtaining high-quality results. Secondly, we study the framework's shortlisting capability using both automatic segmentations and superimpositions. The obtained superimpositions, based only on the superimposition metric, allowed us to filter out 40% of the possible candidates in a completely automatic manner. Thirdly, we perform a reliability study by comparing 180 radiographs against 180 computed tomographies using manual segmentations. The results allowed us to filter out 73% of the possible candidates. Furthermore, the results are robust to inter- and intra-expert-related errors.
比较影像学是一种基于对生前和死后影像学中骨骼结构进行比较的法医鉴定和筛选技术。图像（例如 2D 射线照片或 3D 计算机断层扫描）由法医从业者手动叠加并进行视觉比较。每次比较都需要大量时间，限制了其在大规模比较情况下的实用性。
我们提出并验证了一种使用人工智能自动筛选候选人的新框架。它由以下三个部分组成：（1）一种分割方法，用于限定射线照片中骨骼结构的轮廓；（2）一种叠加方法，用于根据分割的射线照片生成最佳模拟的“射线照片”；（3）一种决策方法，用于根据相似性度量对所有候选人进行排序和筛选。
该数据集由 180 张 CT 扫描和 180 张可见额窦的射线照片组成。由于额窦具有高度个体化的能力，因此我们分析了额窦作为骨骼结构。
首先，我们验证了两种基于深度学习的技术，用于分割射线照片中的额窦，获得了高质量的结果。其次，我们研究了框架使用自动分割和叠加的筛选能力。仅基于叠加度量的获得的叠加结果允许我们以完全自动的方式过滤掉 40%的可能候选人。第三，我们使用手动分割对 180 张射线照片和 180 张 CT 扫描进行可靠性研究。结果允许我们过滤掉 73%的可能候选人。此外，结果对专家间和专家内相关误差具有稳健性。
