DRDarkNet: a hybrid deep feature engineering model for accurate autopsy image classification.

Yildirim, K; Barua, PD; Turkoglu, A; Vicdanli, NH; Dogan, S; Tuncer, T; Somunkiran, I; Chakraborty, S; Taşcı, B; Baig, AH

DRDarkNet: a hybrid deep feature engineering model for accurate autopsy image classification.

Yildirim, K Barua, PD Turkoglu, A Vicdanli, NH Dogan, S Tuncer, T Somunkiran, I Chakraborty, S Taşcı, B Baig, AH

Permalink

Publisher:: Springer Nature
Publication Type:: Journal Article
Citation:: Int J Legal Med, 2026, 140, (4), pp. 2153-2167
Issue Date:: 2026-07

Open Access

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is open access.

Adobe PDF

Download Published versionAdobe PDF (2.88 MB)

View on publisher's site

View statistics

Full metadata record

Field	Value	Language
dc.contributor.author	Yildirim, K
dc.contributor.author	Barua, PD
dc.contributor.author	Turkoglu, A
dc.contributor.author	Vicdanli, NH
dc.contributor.author	Dogan, S
dc.contributor.author	Tuncer, T
dc.contributor.author	Somunkiran, I
dc.contributor.author	Chakraborty, S
dc.contributor.author	Taşcı, B
dc.contributor.author	Baig, AH
dc.date.accessioned	2026-10-09T07:38:15Z
dc.date.available	2026-03-07
dc.date.available	2026-10-09T07:38:15Z
dc.date.issued	2026-07
dc.identifier.citation	Int J Legal Med, 2026, 140, (4), pp. 2153-2167
dc.identifier.issn	0937-9827
dc.identifier.issn	1437-1596
dc.identifier.uri	http://hdl.handle.net/10453/197123
dc.description.abstract	In deaths due to injury, photographs of changes on deceased bodies are routinely taken during the forensic examination; the task of differentiating the types of fatal injury can be posed as an image classification problem. We aimed to develop a machine learning model for automated classification of the cause of injury-induced deaths based on postmortem images of external body regions. We collected a dataset comprising 4254 autopsy images of various body parts divided into six classes according to the cause of death: (i) crush (1808), (ii) choking (327), (iii) stabbing (977), (iv) gunshot (765), (v) burns (254), and (vi) drowning (127). Our model, DRDarkNet, comprised four phases: feature extraction; feature selection; classification; and information fusion. DenseNet201, ResNet50, and DarkNet53 pre-trained on the ImageNet-1 K dataset were deployed to generate six feature vectors of different lengths using the fully connected and global average pooling layers of the individual networks. Neighborhood component analysis (NCA), Chi2, and ReliefF functions were used to create 18 (= 6 × 3) selected feature vectors of identical length (512) with reduced dimensionality that contained the most discriminative features. These selected feature vectors were then fed to a support vector machine classifier to generate 18 classifier-wise outputs. Novel pruning-based iterative majority voting (PIMV) was used to aggregate the classifier-wise outputs, from which voted outputs were generated. From both classifier-wise and voted outputs, the most accurate output was automatically chosen, rendering the model self-organized. DRDarkNet outputs both classifier-wise results and voted results, attaining an excellent 96.47% overall multiclass classification accuracy.
dc.format	Print-Electronic
dc.language	eng
dc.publisher	Springer Nature
dc.relation.ispartof	Int J Legal Med
dc.relation.isbasedon	10.1007/s00414-026-03763-8
dc.rights	info:eu-repo/semantics/openAccess
dc.subject	0399 Other Chemical Sciences, 0699 Other Biological Sciences, 1103 Clinical Sciences
dc.subject.classification	Legal & Forensic Medicine
dc.subject.classification	3199 Other biological sciences
dc.subject.classification	3202 Clinical sciences
dc.subject.classification	3499 Other chemical sciences
dc.subject.mesh	Humans
dc.subject.mesh	Classification Algorithms
dc.subject.mesh	Autopsy
dc.subject.mesh	Postmortem Imaging
dc.subject.mesh	Machine Learning
dc.subject.mesh	Convolutional Neural Networks
dc.subject.mesh	Image Processing, Computer-Assisted
dc.subject.mesh	Neural Networks, Computer
dc.subject.mesh	Humans
dc.subject.mesh	Autopsy
dc.subject.mesh	Image Processing, Computer-Assisted
dc.subject.mesh	Machine Learning
dc.subject.mesh	Neural Networks, Computer
dc.subject.mesh	Postmortem Imaging
dc.subject.mesh	Convolutional Neural Networks
dc.subject.mesh	Classification Algorithms
dc.subject.mesh	Humans
dc.subject.mesh	Classification Algorithms
dc.subject.mesh	Autopsy
dc.subject.mesh	Postmortem Imaging
dc.subject.mesh	Machine Learning
dc.subject.mesh	Convolutional Neural Networks
dc.subject.mesh	Image Processing, Computer-Assisted
dc.subject.mesh	Neural Networks, Computer
dc.title	DRDarkNet: a hybrid deep feature engineering model for accurate autopsy image classification.
dc.type	Journal Article
utslib.citation.volume	140
utslib.location.activity	Germany
utslib.for	0399 Other Chemical Sciences
utslib.for	0699 Other Biological Sciences
utslib.for	1103 Clinical Sciences
pubs.organisational-group	University of Technology Sydney
pubs.organisational-group	University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	University of Technology Sydney/Faculty of Engineering and Information Technology/School of Electrical, Mechanical and Biomedical Engineering
utslib.copyright.status	open_access	*
dc.rights.license	This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/.
dc.date.updated	2026-10-09T07:38:13Z
pubs.issue	4
pubs.publication-status	Published
pubs.volume	140
utslib.citation.issue	4

Abstract:

In deaths due to injury, photographs of changes on deceased bodies are routinely taken during the forensic examination; the task of differentiating the types of fatal injury can be posed as an image classification problem. We aimed to develop a machine learning model for automated classification of the cause of injury-induced deaths based on postmortem images of external body regions. We collected a dataset comprising 4254 autopsy images of various body parts divided into six classes according to the cause of death: (i) crush (1808), (ii) choking (327), (iii) stabbing (977), (iv) gunshot (765), (v) burns (254), and (vi) drowning (127). Our model, DRDarkNet, comprised four phases: feature extraction; feature selection; classification; and information fusion. DenseNet201, ResNet50, and DarkNet53 pre-trained on the ImageNet-1 K dataset were deployed to generate six feature vectors of different lengths using the fully connected and global average pooling layers of the individual networks. Neighborhood component analysis (NCA), Chi2, and ReliefF functions were used to create 18 (= 6 × 3) selected feature vectors of identical length (512) with reduced dimensionality that contained the most discriminative features. These selected feature vectors were then fed to a support vector machine classifier to generate 18 classifier-wise outputs. Novel pruning-based iterative majority voting (PIMV) was used to aggregate the classifier-wise outputs, from which voted outputs were generated. From both classifier-wise and voted outputs, the most accurate output was automatically chosen, rendering the model self-organized. DRDarkNet outputs both classifier-wise results and voted results, attaining an excellent 96.47% overall multiclass classification accuracy.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/197123