pith. sign in

arxiv: 2606.22515 · v1 · pith:2JXK5O3Xnew · submitted 2026-06-21 · 💻 cs.CV

Biological Sex Determination in Cadavers Using Deep Learning Algorithms from Computed Tomography Images of Pelvis and Skull

Giovanna Herculano Tormena , Davi Nascimento Ara\'ujo , Germano Coimbra Soares de Carvalho , Gustavo Bruno Centenaro , Rafael Janowski Pozzer , Rodrigo Akira Azevedo Kurosawa , Danilo Aires Alves , Filipe Thiago Xavier de Campos
show 5 more authors
Pedro Henrique Macedo dos Santos Pedro Augusto Prado Mota Ricardo V. Godoy Jo\~ao Manoel Herrera Pinheiro Marcelo Becker
This is my paper

Pith reviewed 2026-06-26 10:37 UTC · model grok-4.3

classification 💻 cs.CV
keywords deep learningsex determinationcomputed tomographyforensic anthropologycadaverspelvisskullYOLO
0
0 comments X

The pith

Deep learning models determine biological sex from CT scans of pelvis and skull in cadavers at 95.65 percent patient-level accuracy.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper tests whether current deep learning algorithms can automatically classify biological sex from computed tomography images of the pelvis and skull in deceased bodies where traditional visual methods face difficulties due to decomposition. Researchers converted 3D CT reconstructions from 141 cadavers into standardized 2D profile views, then applied transfer learning to several models including YOLO variants, ConvNeXt-Tiny, and ResNet50. The strongest results came from pelvis images, with overall metrics reaching 95.65 percent accuracy, 92.86 percent recall, 94.36 percent F1-score, and 97.22 percent precision, and the approach held up on cases with trauma artifacts. A sympathetic reader would care because this offers a faster, more objective alternative to expert anthropological inspection for forensic identification.

Core claim

State-of-the-art deep learning models with transfer learning can classify biological sex from standardized 2D profile projections derived from 3D CT reconstructions of the pelvis and skull, achieving 95.65 percent patient-level accuracy, 92.86 percent recall, 94.36 percent F1-score, and 97.22 percent precision while remaining consistent across age ranges, preservation states, and trauma-damaged cases.

What carries the argument

Transfer learning on deep networks (YOLO26, YOLO11, ConvNeXt-Tiny, EfficientNetV2, ViT-B16, VGG16, ResNet50) applied to 2D projections from 3D CT scans of pelvis and skull, with data augmentation to address limited samples.

If this is right

  • Pelvis projections yield stronger and more consistent results than skull projections.
  • Performance holds steady on cases that include trauma-related artifacts.
  • Both binary sex classification and quaternary classification by sex plus anatomical region prove feasible.
  • The method supplies an objective, high-speed alternative to manual skeletal analysis for forensic work.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • The same projection-and-classification pipeline could be tested on other skeletal regions such as long bones for combined sex and age estimation.
  • Integration into forensic imaging workstations might shorten turnaround time in mass-casualty or decomposed-remains scenarios.
  • Retraining or domain adaptation would likely be needed before deployment on living patients or across diverse populations and scanner types.

Load-bearing premise

Data from a single forensic institute and one CT scanner captures enough variation to let the models work on scans from other centers and scanners.

What would settle it

Applying the trained models to CT scans collected at a second institution on a different scanner and obtaining patient-level accuracy below 80 percent.

Figures

Figures reproduced from arXiv: 2606.22515 by Danilo Aires Alves, Davi Nascimento Ara\'ujo, Filipe Thiago Xavier de Campos, Germano Coimbra Soares de Carvalho, Giovanna Herculano Tormena, Gustavo Bruno Centenaro, Jo\~ao Manoel Herrera Pinheiro, Marcelo Becker, Pedro Augusto Prado Mota, Pedro Henrique Macedo dos Santos, Rafael Janowski Pozzer, Ricardo V. Godoy, Rodrigo Akira Azevedo Kurosawa.

Figure 1
Figure 1. Figure 1: FIGURE 1 [PITH_FULL_IMAGE:figures/full_fig_p003_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: FIGURE 2 [PITH_FULL_IMAGE:figures/full_fig_p003_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: To ensure an objective evaluation and prevent data [PITH_FULL_IMAGE:figures/full_fig_p004_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: FIGURE 4 [PITH_FULL_IMAGE:figures/full_fig_p007_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: FIGURE 5 [PITH_FULL_IMAGE:figures/full_fig_p010_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: FIGURE 6 [PITH_FULL_IMAGE:figures/full_fig_p010_6.png] view at source ↗
Figure 7
Figure 7. Figure 7: FIGURE 7 [PITH_FULL_IMAGE:figures/full_fig_p011_7.png] view at source ↗
Figure 10
Figure 10. Figure 10: FIGURE 10 [PITH_FULL_IMAGE:figures/full_fig_p011_10.png] view at source ↗
Figure 9
Figure 9. Figure 9: FIGURE 9 [PITH_FULL_IMAGE:figures/full_fig_p011_9.png] view at source ↗
Figure 11
Figure 11. Figure 11: FIGURE 11 [PITH_FULL_IMAGE:figures/full_fig_p011_11.png] view at source ↗
read the original abstract

Sexual identification of decomposed cadavers challenges traditional methods dependent on visual anthropological analysis. This study evaluates state-of-the-art deep learning (including YOLO26, YOLO11, ConvNeXt-Tiny, EfficientNetV2, ViT-B16, VGG16, and ResNet50) with transfer learning to automatically determine biological sex from forensic computed tomography (CT) scans. We analyzed 141 autopsied cadavers from the Forensic Medical Institute of Goi\^ania-GO, including a broad age range and varying conditions of preservation. The three-dimensional reconstructions of the pelvis and skull were converted into standardized two-dimensional profile projections, contributing to the study of this new technical approach. Data augmentation techniques compensated for sample limitations. Two scenarios were validated: binary and quaternary classification (one class per sex vs. one class per anatomical region of each sex). The best-performing model achieved highly consistent results on the pelvis region and still satisfactory performance on the skull region, reaching an overall patient-level accuracy of 95.65%, recall of 92.86%, F1- score of 94.36%, and precision of 97.22%, maintaining consistent performance across the evaluated cases, including those with trauma-related artifacts. Results indicate the technical feasibility of the methodology, demonstrating that deep learning models can provide objective, high-speed skeletal analysis. Since the study was conducted using data from a single institution and a single computed tomography scanner, further validation across multiple centers and scanners is required to assess the generalizability of the proposed approach

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

2 major / 1 minor

Summary. The manuscript evaluates multiple deep learning architectures (YOLO26, YOLO11, ConvNeXt-Tiny, EfficientNetV2, ViT-B16, VGG16, ResNet50) with transfer learning on standardized 2D profile projections derived from 3D CT reconstructions of the pelvis and skull. Using a dataset of 141 autopsied cadavers from a single forensic institute, it compares binary and quaternary (sex × region) classification tasks, reports patient-level metrics up to 95.65% accuracy / 92.86% recall / 94.36% F1 / 97.22% precision (strongest on pelvis), and claims technical feasibility for objective, high-speed sex determination even in trauma cases, while noting the single-center/single-scanner limitation requires further multi-center validation.

Significance. If the reported performance generalizes, the work could supply a practical automated tool for forensic sex estimation in decomposed or fragmented remains where traditional visual methods are unreliable. The use of multiple modern architectures, data augmentation on a modest N, and explicit testing on trauma-affected cases are positive elements that support potential utility in high-throughput forensic settings.

major comments (2)
  1. [Abstract] Abstract: the headline performance figures (95.65% patient-level accuracy etc.) are presented without any description of train/test split strategy, cross-validation procedure, class-balance handling, or statistical significance testing. On a 141-case single-center corpus these omissions make it impossible to judge whether the metrics reflect genuine biological signal or overfitting to scanner-specific or demographic artifacts.
  2. [Abstract] Abstract: the claim that the method demonstrates 'technical feasibility' for objective skeletal analysis that 'works on trauma cases' rests on internal validation from one institution and one CT scanner. While the authors correctly flag the need for multi-center validation, this assumption is load-bearing for the generalization implied by the reported metrics and the quaternary classification / patient-level aggregation scheme; no quantitative evidence is supplied that learned features are driven by sex rather than acquisition parameters.
minor comments (1)
  1. [Abstract] Abstract: 'F1- score' contains an extraneous space before the hyphen.

Simulated Author's Rebuttal

2 responses · 1 unresolved

We thank the referee for the constructive comments on our manuscript. We address each major comment point-by-point below, proposing revisions to the abstract where feasible while being transparent about limitations inherent to the single-center dataset.

read point-by-point responses

  1. Referee: [Abstract] Abstract: the headline performance figures (95.65% patient-level accuracy etc.) are presented without any description of train/test split strategy, cross-validation procedure, class-balance handling, or statistical significance testing. On a 141-case single-center corpus these omissions make it impossible to judge whether the metrics reflect genuine biological signal or overfitting to scanner-specific or demographic artifacts.

    Authors: The Methods section of the full manuscript describes the train/test split (held-out test set with patient-level aggregation), data augmentation to address class balance and sample size, and the use of transfer learning across the evaluated architectures. We agree that the abstract should briefly summarize these elements to allow independent assessment of the metrics. We will revise the abstract to include a concise statement on the validation strategy and augmentation. No formal statistical significance testing (e.g., p-values) was applied beyond standard performance metrics; this can be noted explicitly if required. revision: yes

  2. Referee: [Abstract] Abstract: the claim that the method demonstrates 'technical feasibility' for objective skeletal analysis that 'works on trauma cases' rests on internal validation from one institution and one CT scanner. While the authors correctly flag the need for multi-center validation, this assumption is load-bearing for the generalization implied by the reported metrics and the quaternary classification / patient-level aggregation scheme; no quantitative evidence is supplied that learned features are driven by sex rather than acquisition parameters.

    Authors: The manuscript already states the single-institution, single-scanner limitation and calls for multi-center validation. The standardized 2D projections and explicit inclusion of trauma-affected cases support feasibility claims within this cohort. However, we cannot supply quantitative evidence (e.g., via domain adaptation or multi-scanner ablation) that features are purely sex-driven versus acquisition artifacts, as no such external data exist in the study. We will revise the abstract to temper the feasibility language and reinforce the limitation. revision: partial

standing simulated objections not resolved
  • Quantitative evidence that learned features are driven by biological sex rather than scanner-specific acquisition parameters, which would require multi-scanner datasets unavailable in the current single-center study.

Circularity Check

0 steps flagged

No circularity: purely empirical ML evaluation on held-out cadaver CT data

full rationale

The paper trains standard deep-learning classifiers (YOLO variants, ConvNeXt, EfficientNetV2, ViT, VGG16, ResNet50) with transfer learning on 141 single-center CT scans, converts 3-D reconstructions to 2-D projections, applies data augmentation, and reports patient-level accuracy/recall/F1/precision on internal test cases. No equations, first-principles derivations, fitted parameters renamed as predictions, or load-bearing self-citations appear in the derivation chain. Performance numbers are computed directly from model outputs versus ground-truth labels on the same dataset split; the single-institution limitation is explicitly flagged by the authors as requiring external validation rather than being smuggled in as a result. The evaluation is therefore self-contained against external benchmarks and contains no circular reduction.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 0 invented entities

The performance numbers rest on the empirical behavior of off-the-shelf convolutional and transformer networks trained with transfer learning on a modest single-site dataset; no new physical constants, particles, or mathematical axioms are introduced.

axioms (1)
  • domain assumption Standard deep learning architectures with transfer learning can extract sex-discriminative features from 2D projections of CT bone images
    Invoked implicitly by the choice to fine-tune YOLO, EfficientNet, ViT, etc., without first-principles justification of feature sufficiency.

pith-pipeline@v0.9.1-grok · 5887 in / 1435 out tokens · 26345 ms · 2026-06-26T10:37:11.162209+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

57 extracted references · 14 canonical work pages · 1 internal anchor

  1. [1]

    Zhang, ‘‘The application of forensic imaging to sex estimation: Focus on skull and pelvic structures,’’Perspectives in Legal and F orensic Sci- ences, vol

    M. Zhang, ‘‘The application of forensic imaging to sex estimation: Focus on skull and pelvic structures,’’Perspectives in Legal and F orensic Sci- ences, vol. 1, 2024

    2024

  2. [2]

    Krishan, P

    K. Krishan, P . M. Chatterjee, T. Kanchan, S. Kaur, N. Baryah, and R. K. Singh, ‘‘A review of sex estimation techniques during examination of skeletal remains in forensic anthropology casework,’’F orensic Science International, vol. 261, pp. 165.e1–165.e8, apr 2016. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S0379073816300202

    2016

  3. [3]

    Seifert, L

    Z. Seifert, L. Friedl, K. Chaumoitre, and J. Brůžek, ‘‘Applicability and lim- itations of sex assessment based on foramen magnum,’’F orensic Science International, vol. 271, pp. 126.e1–126.e9, feb 2017. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S0379073816305308

    2017

  4. [4]

    R. Lye, H. Min, J. Dowling, Z. Obertová, M. Estai, N. A. Bachtiar, and D. Franklin, ‘‘Deep learning versus human assessors: forensic sex estimation from three-dimensional computed tomography scans.’’ Scientific Reports, vol. 14, 2024. [Online]. Available: https://www.nature. com/articles/s41598-024-81718-y

    2024

  5. [5]

    Tournois, V

    L. Tournois, V . Trousset, D. Hatsch, T. Delabarde, B. Ludes, and T. Lefèvre, ‘‘Artificial intelligence in the practice of forensic medicine: a scoping review,’’International Journal of Legal Medicine, vol. 138, 12 2023

    2023

  6. [6]

    Galante, R

    N. Galante, R. Cotroneo, D. Furci, G. Lodetti, and M. B. Casali, ‘‘Ap- plications of artificial intelligence in forensic sciences: Current potential benefits, limitations and perspectives,’’International Journal of Legal Medicine, vol. 137, pp. 445–458, 2023

    2023

  7. [7]

    Y . Cao, Y . Ma, X. Y ang, J. Xiong, Y . Wang, J. Zhang, Z. Qin, Y . Chen, D. N. Vieira, F. Chen, J. Zhang, and P . Huang, ‘‘Use of deep learning in forensic sex estimation of virtual pelvic models from the han population,’’ F orensic Sciences Research, vol. 7, no. 3, pp. 540–549, 07 2022. [Online]. Available: https://doi.org/10.1080/20961790.2021.2024369

    work page doi:10.1080/20961790.2021.2024369 2022

  8. [8]

    Kourounis, A

    G. Kourounis, A. A. Elmahmudi, B. Thomson, J. Hunter, H. Ugail, and C. Wilson, ‘‘Computer image analysis with artificial intelligence: a practi- cal introduction to convolutional neural networks for medical profession- als,’’Postgraduate Medical Journal, vol. 99, no. 1178, 2023

    2023

  9. [9]

    De-Giorgio, G

    F. De-Giorgio, G. Ciasca, G. Fecondo, A. Mazzini, R. Di Santo, M. De Spir- ito, and V . L. Pascali, ‘‘Post mortem computed tomography meets ra- diomics: a case series on fractal analysis of post mortem changes in the brain,’’International Journal of Legal Medicine, vol. 136, pp. 719–727, 2022

    2022

  10. [10]

    Ortiz Rosa, E

    E. Ortiz Rosa, E. M. Crosato, C. C. Castro, R. E. Oliveira, and M. G. H. Biazevic, ‘‘Comparative study of sex estimates in adult skulls using direct measurement and tomographic image reconstruction,’’ Brazilian Oral Research, vol. 37, 2023. [Online]. Available: https: //doi.org/10.1590/1807-3107bor-2023.vol37.0064

    work page doi:10.1590/1807-3107bor-2023.vol37.0064 2023

  11. [11]

    Guareschi, S

    E. Guareschi, S. Poggesi, M. Palmesino, and P . Magni, ‘‘The presence of the human auditory ossicles—detected postmortem by ct scan—as a taphonomic indicator,’’F orensic Sciences, vol. 3, pp. 560–570, 11 2023

    2023

  12. [12]

    C. Lin, A. P . Y oon, C.-W. Wang, T. Chao, K. C. Chung, and C.-F. Kuo, ‘‘Effects of image degradation on deep neural network classification of scaphoid fracture radiographs: Comparison study of different noise types,’’ JMIR Med Inform, vol. 14, p. e65596, Jan 2026

    2026

  13. [13]

    Morán-Torres, K

    R. Morán-Torres, K. Feld, J. Hesser, Y . M. Taalab, and K. Y en, ‘‘Artificial intelligence and computer vision in forensic sciences,’’ Rechtsmedizin, vol. 35, no. 4, pp. 219–225, 08 2025. [Online]. Available: https://doi.org/10.1007/s00194-025-00775-3

    work page doi:10.1007/s00194-025-00775-3 2025

  14. [14]

    PL, ‘‘Sexing skulls using discriminant function analysis of visually assessed traits,’’American Journal of Physical Anthropology, vol

    W. PL, ‘‘Sexing skulls using discriminant function analysis of visually assessed traits,’’American Journal of Physical Anthropology, vol. 136, no. 1, pp. 39–50, 05 2008. [Online]. Available: https://doi.org/10.1002/ ajpa.20776

    2008

  15. [15]

    T. W. Phenice, ‘‘A newly developed visual method of sexing the os pubis,’’ American Journal of Physical Anthropology, vol. 30, no. 2, pp. 297–301, 1969

    1969

  16. [16]

    X. Wang, G. Liu, Q. Wu, Y . Zheng, F. Song, and Y . Li, ‘‘Sex estimation techniques based on skulls in forensic anthropology: A scoping review,’’ PLoS ONE, vol. 19, no. 12, 12 2024. VOLUME 11, 2023 13 G. H. Tormenaet al.: Biological sex determination in cadavers using deep learning algorithms

    2024

  17. [17]

    A. R. Klales, S. D. Ousley, and J. M. V ollner, ‘‘A revised method of sexing the human innominate using phenice’s nonmetric traits and statistical methods,’’American Journal of Physical Anthropology, vol. 149, no. 1, pp. 104–114, 2012

    2012

  18. [18]

    P . Shah, Y . Kumar, and T. Bhowmik, ‘‘Deep learning techniques for the diagnosis and detection of orthopedic conditions: A systematic review of recent advances and challenges,’’Archives of Computational Methods in Engineering, vol. 33, 09 2025

    2025

  19. [19]

    L. Chen, J. Chen, H. Hajimirsadeghi, and G. Mori, ‘‘Adapting grad-cam for embedding networks,’’ in2020 IEEE Winter Conference on Applications of Computer Vision (WACV), 2020, pp. 2783–2792

    2020

  20. [20]

    Anees, R

    W. Anees, R. Silva, A. Khan, J. Murray, L. Scavassini, M. Burle, N. Angelakopoulos, M. H. Napimoga, L. Porto, A. Abade, and A. Franco, ‘‘Maxillary sinus classification for sex and age using 23 artificial intelligence architectures,’’Scientific Reports, vol. 16, no. 1, p. 5716, 01

  21. [21]

    Available: https://doi.org/10.1038/s41598-026-36112-1

    [Online]. Available: https://doi.org/10.1038/s41598-026-36112-1

    work page doi:10.1038/s41598-026-36112-1

  22. [22]

    Bulut, M

    A. Bulut, M. B. Aşkın, and G. Çınarer, ‘‘Comparative analysis of third molar segmentation performance between sexes using deep learning models,’’Diagnostics, vol. 16, no. 7, p. 977, 03 2026. [Online]. Available: https://doi.org/10.3390/diagnostics16070977

    work page doi:10.3390/diagnostics16070977 2026

  23. [23]

    S. N. Batool, J. Y ang, G. Gilanie, A. Latif, S. Y asin, A. Ikram, and L. Y . Por, ‘‘Forensic radiology: A robust approach to biological profile estimation from bone image analysis using deep learning,’’Biomedical Signal Processing and Control, vol. 105, p. 107661, 2025. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S1746809425001727

    2025

  24. [24]

    Weiss, T

    K. Weiss, T. M. Khoshgoftaar, and D. Wang, ‘‘A survey of transfer learning,’’Journal of Big Data, vol. 3, no. 1, p. 9, 2016. [Online]. Available: https://doi.org/10.1186/s40537-016-0043-6

    work page doi:10.1186/s40537-016-0043-6 2016

  25. [25]

    , title =

    A. Krizhevsky, I. Sutskever, and G. E. Hinton, ‘‘Imagenet classification with deep convolutional neural networks,’’Commun. ACM, vol. 60, no. 6, p. 84–90, May 2017. [Online]. Available: https://doi.org/10.1145/3065386

    work page doi:10.1145/3065386 2017

  26. [26]

    T. Seo, Y . Y oon, Y . Kim, Y . Usumoto, N. Eto, Y . Sadamatsu, R. Tadakuma, and J. Morishita, ‘‘Sex estimation using skull silhouette images from postmortem computed tomography by deep learning,’’Scientific Reports, vol. 14, p. 22689, 09 2024

    2024

  27. [27]

    Provost, M.-E

    C. Provost, M.-E. Richard, T. Delabarde, G. Hmeydia, A. Berre, W. Hassen, O. Naggara, L. Hamza, B. Ludes, C. Oppenheim, and J. Benzakoun, ‘‘Age and sex estimation using post-mortem ct scout view,’’International Journal of Legal Medicine, pp. 1–14, 03 2026

    2026

  28. [28]

    Z. Xue, P . Pi, Z. Liu, Z. Zeng, and Z. Sun, ‘‘Mednext for accurate medical image classification and segmentation: A lightweight transformer-style convolutional neural network,’’PLOS One, vol. 21, 01 2026

    2026

  29. [29]

    Sapkota, R

    R. Sapkota, R. H. Cheppally, A. Sharda, and M. Karkee, ‘‘Y olo26: Key architectural enhancements and performance benchmarking for real-time object detection,’’ 2026

    2026

  30. [30]

    Mustra, K

    M. Mustra, K. Delac, and M. Grgic, ‘‘Overview of the dicom standard,’’ in 2008 50th International Symposium ELMAR, vol. 1, 2008, pp. 39–44

    2008

  31. [31]

    Levoy, ‘‘ Display of Surfaces from V olume Data ,’’IEEE Computer Graphics and Applications, vol

    M. Levoy, ‘‘ Display of Surfaces from V olume Data ,’’IEEE Computer Graphics and Applications, vol. 8, no. 03, pp. 29–37, 1988. [Online]. Available: https://doi.ieeecomputersociety.org/10.1109/38.511

    work page doi:10.1109/38.511 1988

  32. [32]

    Mason, ‘‘pydicom/pydicom: pydicom 3.0.1,’’ 2024

    D. Mason, ‘‘pydicom/pydicom: pydicom 3.0.1,’’ 2024. [Online]. Available: https://doi.org/10.5281/zenodo.13824606

    work page doi:10.5281/zenodo.13824606 2024

  33. [33]

    Tan and Q

    M. Tan and Q. Le, ‘‘Efficientnetv2: Smaller models and faster training,’’ in International Conference on Machine Learning (ICML). PMLR, 2021, pp. 10 096–10 106

    2021

  34. [34]

    Z. Liu, H. Mao, C.-Y . Wu, C. Feichtenhofer, T. Darrell, and S. Xie, ‘‘A convnet for the 2020s,’’ pp. 11 976–11 986, 2022

    2022

  35. [35]

    Dosovitskiy, L

    A. Dosovitskiy, L. Beyer, A. Kolesnikov, D. Weissenborn, X. Zhai, T. Un- terthiner, M. Dehghani, M. Minderer, G. Heigold, S. Gellyet al., ‘‘An image is worth 16x16 words: Transformers for image recognition at scale,’’ arXiv preprint arXiv:2010.11929, 2021

    Pith/arXiv arXiv 2010

  36. [36]

    Simonyan and A

    K. Simonyan and A. Zisserman, ‘‘V ery deep convolutional networks for large-scale image recognition,’’arXiv preprint arXiv:1409.1556, 2014

    Pith/arXiv arXiv 2014

  37. [37]

    K. He, X. Zhang, S. Ren, and J. Sun, ‘‘Deep residual learning for image recognition,’’ inProceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016, pp. 770–778

    2016

  38. [38]

    Jocher, J

    G. Jocher, J. Qiu, and M. Najibi, ‘‘Ultralytics yolo11,’’ 2024. [Online]. Available: https://github.com/ultralytics/ultralytics

    2024

  39. [39]

    Jocher, A

    G. Jocher, A. Chaurasia, and J. Qiu, ‘‘Ultralytics yolov26,’’ 2026. [Online]. Available: https://github.com/ultralytics/ultralytics

    2026

  40. [40]

    A. Wong, M. Famuori, M. J. Shafiee, F. Li, B. Chwyl, and J. Chung, ‘‘Y olo nano: a highly compact you only look once convolutional neural network for object detection,’’ 2019. [Online]. Available: https: //arxiv.org/abs/1910.01271

    arXiv 2019

  41. [41]

    , author Iglovikov, V.I

    A. Buslaev, V . I. Iglovikov, E. Khvedchenya, A. Parinov, M. Druzhinin, and A. A. Kalinin, ‘‘Albumentations: Fast and flexible image augmentations,’’ Information, vol. 11, no. 2, p. 125, 2020. [Online]. Available: https: //doi.org/10.3390/info11020125

    work page doi:10.3390/info11020125 2020

  42. [42]

    O’Gara and K

    S. O’Gara and K. McGuinness, ‘‘Comparing data augmentation strategies for deep image classification,’’ inIMVIP 2019: Irish Machine Vision & Image Processing, Technological University Dublin, Dublin, Ireland, August 2019

    2019

  43. [43]

    You Only Look Once: Unified, Real -Time Object Detection[J].IEEE, 2016.DOI:10.1109/CVPR.2016.91

    J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, ‘‘Y ou only look once: Unified, real-time object detection,’’ inProceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 779–788. [Online]. Available: https://doi.org/10.1109/CVPR.2016.91

    work page doi:10.1109/cvpr.2016.91 2016

  44. [44]

    YOLOv4: Optimal Speed and Accuracy of Object Detection

    A. Bochkovskiy, C. Y . Wang, and H. Y . M. Liao, ‘‘Y olov4: Optimal speed and accuracy of object detection,’’arXiv preprint arXiv:2004.10934, 2020. [Online]. Available: https://doi.org/10.48550/arXiv.2004.10934

    work page internal anchor Pith review Pith/arXiv arXiv doi:10.48550/arxiv.2004.10934 2004

  45. [45]

    Wong and P .-Y

    T.-T. Wong and P .-Y . Y eh, ‘‘Reliable accuracy estimates from k-fold cross validation,’’IEEE Transactions on Knowledge and Data Engineering, vol. 32, no. 8, pp. 1586–1594, 2020

    2020

  46. [46]

    Sokolova and G

    M. Sokolova and G. Lapalme, ‘‘A systematic analysis of performance measures for classification tasks,’’Information Processing & Management, vol. 45, no. 4, pp. 427–437, 2009

    2009

  47. [47]

    R. R. Selvaraju, M. Cogswell, A. Das, R. V edantam, D. Parikh, and D. Batra, ‘‘Grad-cam: Visual explanations from deep networks via gradient-based localization,’’International Journal of Computer Vision, vol. 128, no. 2, p. 336–359, Oct. 2019. [Online]. Available: http://dx.doi.org/10.1007/s11263-019-01228-7

    work page doi:10.1007/s11263-019-01228-7 2019

  48. [48]

    K. Wang, S. Yin, Y . Wang, and S. Li, ‘‘Explainable deep learning for medical image segmentation with learnable class activation mapping,’’ in2023 2nd Asia Conference on Algorithms, Computing and Machine Learning (CACML 2023). ACM, 2023, pp. 210–215

    2023

  49. [49]

    V enema, D

    J. V enema, D. Peula, J. Irurita, and P . Mesejo, ‘‘Employing deep learning for sex estimation of adult individuals using 2d images of the humerus,’’ Neural Computing and Applications, vol. 35, no. 8, pp. 5987–5998, 2023

    2023

  50. [50]

    Lambora, K

    A. Lambora, K. Gupta, and K. Chopra, ‘‘Genetic algorithm- a literature review,’’ in2019 International Conference on Machine Learning, Big Data, Cloud and Parallel Computing (COMITCon), 2019, pp. 380–384

    2019

  51. [51]

    J. M. Johnson and T. M. Khoshgoftaar, ‘‘Survey on deep learning with class imbalance,’’Journal of Big Data, vol. 6, no. 1, p. 27, 03 2019. [Online]. Available: https://doi.org/10.1186/s40537-019-0192-5

    work page doi:10.1186/s40537-019-0192-5 2019

  52. [52]

    Çelikbilek & Fatih Tüysüz, ‘‘An in-depth review of theory of the topsis method: An experimental analysis,’’Journal of Management Analytics, 2020

    Y . Çelikbilek & Fatih Tüysüz, ‘‘An in-depth review of theory of the topsis method: An experimental analysis,’’Journal of Management Analytics, 2020

    2020

  53. [53]

    Mardani, E

    A. Mardani, E. K. Zavadskas, K. Govindan, A. Amat Senin, and A. Jusoh, ‘‘Vikor technique: A systematic review of the state of the art literature on methodologies and applications,’’Sustainability, vol. 8, no. 1, 2016. [Online]. Available: https://www.mdpi.com/2071-1050/8/1/37

    2016

  54. [54]

    Saraiva, ‘‘On shannon entropy and its applications,’’Kuwait Journal of Science, vol

    P . Saraiva, ‘‘On shannon entropy and its applications,’’Kuwait Journal of Science, vol. 50, no. 3, p. 194–199, 2023

    2023

  55. [55]

    S. S. Moosa, M. H. R. Shaikh, M. Khwaja, S. A. H. Shaikh, F. B. Siddiqui, S. R. H. Daimi, S. D. Hiware, E. E. Ismail, and Y . Begum, ‘‘Sexual di- morphic parameters of femur: A clinical guide in orthopedics and forensic studies,’’Journal of Medicine and Life, vol. 14, no. 6, pp. 762–768, 2021

    2021

  56. [56]

    S. M. Mani, Y . S. Ahamed, P . Ambiga, V . Ramalingam, G. Sivaraman, and N. Balan, ‘‘Evaluation of orbital morphometry using 3d computed to- mographic images in biological sex determination: a retrospective study,’’ Journal of Indian Academy of Oral Medicine and Radiology, vol. 32, no. 4, p. 390, 2020

    2020

  57. [57]

    E. D. Kalkan, A. Baransel, M. Akşamoğlu, M. Akbaba, and H. Kalkan, ‘‘Sex determination using craniometric parameters: A computed tomography- based assessment,’’Adli Tıp Dergisi, vol. 39, no. 2, p. 125–135, 2025. 14 VOLUME 11, 2023 G. H. Tormenaet al.: Biological sex determination in cadavers using deep learning algorithms GIOVANNA HERCULANO TORMENAis cur-...

    2025