International Journal of Computational and Electronic Aspects in Engineering
Volume 7 · Issue 2 · June 2026 · pp. 227-236
Research Article · Peer Reviewed
Received: March 25, 2026 · Accepted: May 30, 2026 · Published: June 20, 2026
DOI: 10.26706/ijceae.7.2.20260311
Open Access · CC BY 4.0

Beyond Chronological Age: Explainable Multi-Task Swin Transformers for Biological Age and Gender Estimation from Dorsal Hand Images

Shamil Kh. Ramadhan1,*, Nora Rashid Najem2, Abdulmajeed Sulaiman3, Hussam Ahmed Rammo4, Fahad Ahmed Shaban3
1 Department of Medical Devices Techniques, Polytechnic College – Mosul, Northern Technical University, Mosul, Iraq.
2 Department of Computer Science, Alnoor University, Nineveh, Iraq.
3 Department of Computer Networks and Internet, College of Information Technology, Ninevah University, Mosul, Iraq.
4 Department of Techniques Engineering College for Computer and AI, Northern Technical University, Nineveh, Iraq.

*Corresponding author: shamil.ramadhan@ntu.edu.iq
Download PDF Cite this article Certificate Volume 7 Issue 2

Abstract

Predicting biological age and determining gender from physical characteristics play a vital role in forensics, biometric identification, and medical diagnosis. Although most deep learning models focus on facial traits, the dorsal hand is a highly accurate but little-used non-invasive trait. In this work, we develop a new Multi-Task Learning (MTL) approach using the Swin Transformer model to predict biological age and gender from hand images. Using a dataset of 5,680 selected dorsal hand images, we incorporated Contrast Limited Adaptive Histogram Equalization (CLAHE) to highlight micro-textures such as wrinkles, veins, and knuckle deformations. The proposed model achieved outstanding performance with 99.9% gender classification accuracy (F1-Score: 0.999), while biological age estimation attained a Mean Absolute Error (MAE) of 0.3 years and a Root Mean Square Error (RMSE) of 0.38 years. Explainable AI (XAI) using occlusion sensitivity verified that the model relied on anatomical features rather than background artifacts, demonstrating its reliability as an accurate, efficient, and interpretable "Hand Ageing Clock."

Keywords

Biological Age Estimation Gender Classification Multi-Task Learning Swin Transformer Explainable AI (XAI) Hand Biometrics

References

References

  1. J. Wang et al., "Accurate estimation of biological age and its application in disease prediction using a multimodal image Transformer system," Proceedings of the National Academy of Sciences of the United States of America, vol. 121, no. 3, p. e2308812120, Jan. 2024, doi: 10.1073/PNAS.2308812120.
  2. S. N. G, P. R. B, S. C. R, V. T, and V. V, "Detection of Gender and Age," in 2026 International Conference on Intelligent Innovation Technology in Computing, Electrical and Electronics (IITCEE), Jan. 2026, pp. 1–6, doi: 10.1109/IITCEE67948.2026.11394555.
  3. W. Tanveer, L. Fernández-Robles, E. Fidalgo, V. González-Castro, and E. Alegre, "Overcoming occlusions in the wild: A multi-task age head approach to age estimation," Pattern Recognition, Elsevier, 2025, doi: 10.1016/j.patcog.2025.1015808.
  4. S. E. Moon et al., "Biological Age Estimation From the Age Gap Using Deep Learning Integrating Morbidity and Mortality: Model Development and Validation Study," Journal of Medical Internet Research, vol. 27, no. 1, p. e71592, Sep. 2025, doi: 10.2196/71592.
  5. N. L. Baisa, "Joint Person Identity, Gender and Age Estimation from Hand Images Using Deep Multi-Task Representation Learning," in 2024 12th International Workshop on Biometrics and Forensics (IWBF), 2024, doi: 10.1109/IWBF62628.2024.10593838.
  6. S. K. Ramadhan, F. A. Yousif, and F. S. Hamid, "Enhancing user experience with hand gesture volume control: overcoming challenges of camera distance," Cybernetics and Physics, vol. 14, no. 4, pp. 375–382, Dec. 2025, doi: 10.35470/2226-4116-2025-14-4-375-382.
  7. A. Villamarín-Olmos and D. Renza, "Improving Skin Lesion Detection with Transformer-Based Architectures," Information, vol. 17, no. 2, p. 130, Feb. 2026, doi: 10.3390/info17020130.
  8. R. Albano, L. Giusti, E. Maiorana, and P. Campisi, "Explainable Vision Transformers for Vein Biometric Recognition," IEEE Access, vol. 12, pp. 60436–60446, 2024, doi: 10.1109/ACCESS.2024.3393558.
  9. R. G. Alsultan, F. S. Hamid, A. S. M. Khidhir, M. Karaaslan, and S. K. Ramadhan, "Parametric Optimization and Performance Analysis of a Compact Dual-Band Split Square Loop FSS for X-Band and Ku-Band," Journal Européen des Systèmes Automatisés, vol. 59, no. 2, pp. 413–419, Feb. 2026, doi: 10.18280/jesa.590211.
  10. R. Azad et al., "Advances in medical image analysis with vision transformers: a comprehensive review," Medical Image Analysis, Elsevier, 2024, doi: 10.1016/j.media.2023.102608.
  11. N. L. Baisa, "Joint Person Identity, Gender and Age Estimation from Hand Images Using Deep Multi-Task Representation Learning," in 2024 12th International Workshop on Biometrics and Forensics (IWBF), pp. 1–6, 2024, doi: 10.1109/IWBF62628.2024.10593838.
  12. X. Mao et al., "Automated Skeletal Bone Age Assessment with Two-Stage Convolutional Transformer Network Based on X-ray Images," Diagnostics, vol. 13, no. 11, p. 1837, May 2023, doi: 10.3390/diagnostics13111837.
  13. A. Badawi, A. Saber, B. Mohamed, M. Shahin, and A. Abdelrahman, "Gender classification using dorsal NIR hand veins imaging," Neural Computing and Applications, vol. 37, no. 22, pp. 18275–18301, Jun. 2025, doi: 10.1007/S00521-025-11363-7.
  14. N. Pishhadam, R. Esmaeilyfard, and M. Paknahad, "Explainable deep learning for age and gender estimation in dental CBCT scans using attention mechanisms and multi task learning," Scientific Reports, vol. 15, no. 1, pp. 1–10, 2025, doi: 10.1038/s41598-025-03305-z.
  15. X. Qiao, C. Hu, and B. Qin, "Semantic Attention Guided Hierarchical Decision Network for Age Estimation," Applied Sciences, vol. 15, no. 14, pp. 1–19, 2025, doi: 10.3390/app15147707.
  16. A. Georgievskaya et al., "LB1652 Images of the hand are comparable to those of the face for predicting chronological age via AI," Journal of Investigative Dermatology, vol. 143, no. 9, p. B5, Sep. 2023, doi: 10.1016/j.jid.2023.06.189.
  17. A. Georgievskaya et al., "Predicting human chronological age via AI analysis of dorsal hand versus facial images: A study in a cohort of Indian females," Experimental Dermatology, vol. 33, no. 3, pp. 1–13, 2024, doi: 10.1111/exd.15045.
  18. L. Qin et al., "SwinFace: A Multi-Task Transformer for Face Recognition, Expression Recognition, Age Estimation and Attribute Estimation," IEEE Transactions on Circuits and Systems for Video Technology, vol. 34, no. 4, pp. 2223–2234, Apr. 2024, doi: 10.1109/TCSVT.2023.3304724.
  19. A. T, S. Abhishek, and S. Remya, "A novel framework for rosacea detection using Swin Transformers and explainable artificial intelligence," Alexandria Engineering Journal, vol. 118, pp. 36–58, Apr. 2025, doi: 10.1016/J.AEJ.2024.12.080.
  20. C. Shi, S. Zhao, K. Zhang, Y. Wang, and L. Liang, "Face-based age estimation using improved Swin Transformer with attention-based convolution," Frontiers in Neuroscience, vol. 17, p. 1136934, Apr. 2023, doi: 10.3389/FNINS.2023.1136934.
  21. N. Mirabet-Herranz, C. Galdi, and J. L. Dugelay, "One Embedding to Predict Them All: Visible and Thermal Universal Face Representations for Soft Biometric Estimation via Vision Transformers," in IEEE/CVF Computer Society Conference on Computer Vision and Pattern Recognition Workshops (CVPR Workshops), pp. 1500–1509, 2024, doi: 10.1109/CVPRW63382.2024.00157.
  22. S. J. Park et al., "Automatic and robust estimation of sex and chronological age from panoramic radiographs using a multi-task deep learning network: a study on a South Korean population," International Journal of Legal Medicine, vol. 138, no. 4, pp. 1741–1757, Mar. 2024, doi: 10.1007/S00414-024-03204-4.
  23. N. Sributsayakarn, T. Intharah, N. Hirunchavarod, S. Pornprasertsuk-Damrongsri, and V. Jirarattanasopha, "Automated Age and Sex Estimation From Dental Panoramic Radiographs," International Dental Journal, vol. 75, no. 6, p. 103967, Dec. 2025, doi: 10.1016/J.IDENTJ.2025.103967.
  24. D. Štern, C. Payer, and M. Urschler, "Automated age estimation from MRI volumes of the hand," Medical Image Analysis, vol. 58, p. 101538, Dec. 2019, doi: 10.1016/J.MEDIA.2019.101538.
  25. Z. Shu, Z. Xie, and X. Zou, "Dual-Stream Enhanced Deep Network for Transmission Near-Infrared Dorsal Hand Vein Age Estimation with Attention Mechanisms," Photonics, vol. 11, no. 12, p. 1113, Nov. 2024, doi: 10.3390/photonics11121113.
  26. M. H. G. Abdkhaleq, "Hybrid Deep Learning and Neuro-Fuzzy Approach for COVID-19 Diagnosis Using CT Scan Imaging: Integration of CNN, ANFIS, and PCA," International Journal of Computational and Electronic Aspects in Engineering, vol. 6, no. 2, pp. 81–88, Jun. 2025, doi: 10.26706/ijceae.6.2.20250404.
  27. N. K. Younis, M. H. Qahtan, and M. R. Ahmed, "A Review of Artificial Intelligence Techniques for Medical Image Enhancement," International Journal of Computational and Electronic Aspects in Engineering, vol. 6, no. 2, pp. 98–107, Jun. 2025, doi: 10.26706/ijceae.6.2.20250406.
  28. N. Waisi, "Deep Feature Fusion Method for Images Classification," International Journal of Computational and Electronic Aspects in Engineering, vol. 5, no. 4, pp. 148–153, Dec. 2024, doi: 10.26706/ijceae.5.4.20241103.
  29. W. Razzaq, "Categorization of Carcinogenic Abnormalities in Digital Mastography Using Deep Learning Algorithms," International Journal of Computational and Electronic Aspects in Engineering, vol. 4, no. 4, pp. 119–126, Oct. 2023, doi: 10.26706/ijceae.4.4.20231004.
  30. I. S. Seger, "Evaluating and Selecting Optimal CNN Architectures for Accurate Pneumonia Detection in Chest X-Rays," International Journal of Computational and Electronic Aspects in Engineering, vol. 5, no. 4, pp. 183–193, Dec. 2024, doi: 10.26706/ijceae.5.4.20241106.
  31. E. Aydemir and R. T. E. Alalawi, "Classification of Hand Images by Person, Age and Gender with The Median Robust Extended Local Binary Model," Balkan Journal of Electrical and Computer Engineering, vol. 11, no. 1, pp. 78–87, Jan. 2023, doi: 10.17694/bajece.1171905.
  32. H. E. Ulubaba, I. Atik, R. Çiftçi, O. Eken, and M. I. Aldhahi, "Deep learning for gender estimation using hand radiographs: a comparative evaluation of CNN models," BMC Medical Imaging, vol. 25, no. 1, p. 260, Jul. 2025, doi: 10.1186/s12880-025-01809-8.