Back to Search
Start Over
Sex estimation of the pelvis by deep learning of two-dimensional depth images generated from homologous models of three-dimensional computed tomography images
- Source :
- Forensic Science International: Reports, Vol 2, Iss, Pp 100129-(2020)
- Publication Year :
- 2020
- Publisher :
- Elsevier, 2020.
-
Abstract
- The utility of convolutional neural networks (CNNs) for sex estimation of the pelvis was evaluated using depth images generated from reconstructed three-dimensional (3D) computed tomography images. The 3D volume data were normalized by a homologous modeling technique to create polygon data with identical topology, then captured images for learning and testing. The neural networks were trained via transfer learning. As a result, a correct assignment rate >90% was obtained in most trials. The frontal view of the pelvis with 60-degree inclination achieved the best results. Selecting samples close to the average images of the sex was effective for training.
- Subjects :
- Artificial neural network
business.industry
Computer science
Deep learning
Forensic anthropology
Pattern recognition
Convolutional neural network
Sex estimation
Pathology and Forensic Medicine
Pelvis
medicine.anatomical_structure
Polygon
Machine learning
medicine
lcsh:Criminal law and procedure
Artificial intelligence
Homologous modeling
lcsh:K5000-5582
Transfer of learning
business
Volume (compression)
Subjects
Details
- Language :
- English
- ISSN :
- 26659107
- Volume :
- 2
- Database :
- OpenAIRE
- Journal :
- Forensic Science International: Reports
- Accession number :
- edsair.doi.dedup.....73d09b296a51ba01f5aeb0aa28687342