1
|
Gómez Ó, Mesejo P, Ibáñez Ó, Valsecchi A, Bermejo E, Cerezo A, Pérez J, Alemán I, Kahana T, Damas S, Cordón Ó. Evaluating artificial intelligence for comparative radiography. Int J Legal Med 2024; 138:307-327. [PMID: 37801115 DOI: 10.1007/s00414-023-03080-4] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/22/2022] [Accepted: 08/23/2023] [Indexed: 10/07/2023]
Abstract
INTRODUCTION 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. METHODS 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. MATERIAL 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. RESULTS 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.
Collapse
Affiliation(s)
- Óscar Gómez
- Andalusian Research Institute DaSCI, University of Granada, Granada, Spain.
| | - Pablo Mesejo
- Andalusian Research Institute DaSCI, University of Granada, Granada, Spain
- Department of Computer Science and Artificial Intelligence, University of Granada, Granada, Spain
- Panacea Cooperative Research S. Coop., Ponferrada, Spain
| | - Óscar Ibáñez
- Andalusian Research Institute DaSCI, University of Granada, Granada, Spain
- Panacea Cooperative Research S. Coop., Ponferrada, Spain
- Faculty of Computer Science, CITIC, University of A Coruña, A Coruña, Spain
| | - Andrea Valsecchi
- Andalusian Research Institute DaSCI, University of Granada, Granada, Spain
- Panacea Cooperative Research S. Coop., Ponferrada, Spain
| | - Enrique Bermejo
- Andalusian Research Institute DaSCI, University of Granada, Granada, Spain
- Department of Computer Science and Artificial Intelligence, University of Granada, Granada, Spain
- Panacea Cooperative Research S. Coop., Ponferrada, Spain
| | - Andrea Cerezo
- Department of Legal Medicine, Toxicology and Physical Anthropology, University of Granada, Granada, Spain
| | - José Pérez
- Department of Legal Medicine, Toxicology and Physical Anthropology, University of Granada, Granada, Spain
| | - Inmaculada Alemán
- Department of Legal Medicine, Toxicology and Physical Anthropology, University of Granada, Granada, Spain
| | - Tzipi Kahana
- Faculty of Criminology, The Hebrew University of Jerusalem, Jerusalem, Israel
| | - Sergio Damas
- Andalusian Research Institute DaSCI, University of Granada, Granada, Spain
- Department of Software Engineering, University of Granada, Granada, Spain
| | - Óscar Cordón
- Andalusian Research Institute DaSCI, University of Granada, Granada, Spain
- Department of Computer Science and Artificial Intelligence, University of Granada, Granada, Spain
| |
Collapse
|