The Computer-Assisted Decedent Identification Method of Computer-Assisted Radiographic Identification

Derrick, Sharon M.; Hipp, John A.; Goel, Priya

doi:10.1016/b978-0-12-805429-1.00023-5

Cited by 2 publications

(2 citation statements)

References 58 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The segmentation of the skeletal structures in AM and PM radiographs is required in all these methods. Related to that, there are a few computational approaches that automate the manual segmentations using ad-hoc rule-based segmentation methods, as the automated dental identification system (ADIS) [136,137] for teeth comparison [138], or [139] for frontal sinuses segmentation, or via the direct comparison of the intensities as the computer-assisted decedent identification (CADI) [138] for vertebrae comparison. However, the latter approach suffers from the elapsed time between the AM and PM radiographs, and the consequent change in the intensities of the skeletal structures.…”

Section: D-2d Approaches For Comparative Radiographymentioning

confidence: 99%

A Survey on Artificial Intelligence Techniques for Biomedical Image Analysis in Skeleton-Based Forensic Human Identification

et al. 2020

View full text Add to dashboard Cite

This paper represents the first survey on the application of AI techniques for the analysis of biomedical images with forensic human identification purposes. Human identification is of great relevance in today’s society and, in particular, in medico-legal contexts. As consequence, all technological advances that are introduced in this field can contribute to the increasing necessity for accurate and robust tools that allow for establishing and verifying human identity. We first describe the importance and applicability of forensic anthropology in many identification scenarios. Later, we present the main trends related to the application of computer vision, machine learning and soft computing techniques to the estimation of the biological profile, the identification through comparative radiography and craniofacial superimposition, traumatism and pathology analysis, as well as facial reconstruction. The potentialities and limitations of the employed approaches are described, and we conclude with a discussion about methodological issues and future research.

show abstract

Section: D-2d Approaches For Comparative Radiographymentioning

confidence: 99%

A Survey on Artificial Intelligence Techniques for Biomedical Image Analysis in Skeleton-Based Forensic Human Identification

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Like frontal sinus comparisons, infracranial radiographic comparisons involve visual assessment of skeletal morphology between antemortem (AM) and postmortem (PM) radiographs to determine if they originated from the same individual [41]. However, unlike frontal sinus comparisons where the shape of the internal sinus space is the primary basis of assessment, infracranial comparisons depend on a much broader array of skeletal features, including whole bone shape, surface topography, cortical thicknesses, and bone density, as manifested by differential opacities of the element on the radiograph [13, 26, 27, 42].…”

Section: Introductionmentioning

confidence: 99%

Infracranial radiographic comparison for human identification: A study of image quality and tissue shielding effects

Hona

Byrd²,

Stephan

2021

Journal of Forensic Sciences

View full text Add to dashboard Cite

In this study, we explore how image resolution and tissue shielding can impact correct classification rates (CCRs) of infracranial radiographic comparisons undertaken using small field‐of‐view radiographs. Thirty‐six identification arrays (using clavicles and seventh cervical vertebra) were constructed with each array comprised of five radiographs: one X‐ray of a single dry bone (postmortem [PM] skeletal image) and four simulated antemortem [AM] radiographs (radiographs taken pre‐skeletization). One AM radiograph in each array represented the ground truth match to the PM radiograph (=25% rate of randomly selecting the correct match). Radiographs were digitally manipulated, so that four varieties of decreasing blur (Gaussian blur = 12–0 pr across 24 arrays), and, for PM clavicles, four varieties of decreasing hard tissue shielding (opacity of 40–0% across 12 arrays) existed. Arrays were evaluated, for their correct PM/AM pair, by 8 anthropologists trained in chest radiograph comparison (CXR; either currently or formerly competency certified by the Defense POW/MIA Accounting Agency CXR training program), 28 current American Board of Forensic Anthropology (ABFA) diplomates and 30 novices. Analysts’ CCRs substantially improved when Gaussian blur was <10 pr (55% CCR at >10 pr vs. 89% for <10 pr). Tissue shielding effects increased CCRs on average by +10% for each −10% opacity step (between 40–0% opacity). The CXR anthropologists were the most tolerant of the more challenging identification contexts (highest blur and opacity), reconfirming that analyst training and expertise is an important factor, especially when poorer quality radiographic images are the subject of analysis.

show abstract

The Computer-Assisted Decedent Identification Method of Computer-Assisted Radiographic Identification

Cited by 2 publications

References 58 publications

A Survey on Artificial Intelligence Techniques for Biomedical Image Analysis in Skeleton-Based Forensic Human Identification

A Survey on Artificial Intelligence Techniques for Biomedical Image Analysis in Skeleton-Based Forensic Human Identification

Infracranial radiographic comparison for human identification: A study of image quality and tissue shielding effects

Contact Info

Product

Resources

About