Application of Innovative Artificial Intelligence Methods to Detect Flat Feet in Children
Source abstract
Abstract
This study examined the potential of artificial intelligence tools for detecting pediatric flatfoot pathology. We would like to emphasize that there is very little research in this area and we would like to point out that this is a relevant and very important topic in medicine. First, the base flow was used: a pre-trained “backbone” on the ImageNet platform. In this study, this term is used to describe the feature extraction part of a convolutional network. A standardized pre-processing with pruning and augmentation was performed, and a three-stage training schedule (stages 1, 2 and 3), average and maximum aggregation at the subject level and the addition of light test time were proposed. Eight different model architectures were used. From stage 2 onwards, all models were trained on feet. Three-dimensional photographs with real flatfoot shapes, from flatfoot stages I to III, were used. The most validated model was displayed in accurate AUROC plots with estimated average and maximum aggregation values with standard deviation. The research and calculations conducted demonstrate the possibility of applying artificial intelligence in the field of orthopedics.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Lower Extremity Biomechanics and Pathologies · Foot and Ankle Surgery · Diabetic Foot Ulcer Assessment and Management
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
St. Ignatius of Loyola College, Vilniaus Str. 29, LT-44286 Kaunas, Lithuania
Department of Informatics, Kaunas University of Technology, Stuentu Str. 50, LT-51368 Kaunas, Lithuania
References (40)
Show source-provided references
1. Babu, D., and Bordoni, B. (2022). Anatomy, Bony Pelvis and Lower Limb, Medial Longitudinal Arch of the Foot, StatPearls Publishing.
2. Baumfeld, D., Baumfeld, T., da Rocha, R.L., Macedo, B., Raduan, F., Zambelli, R., Alves Silva, T.A., and Nery, C. (2017). Reliability of Baropodometry on the Evaluation of Plantar Load Distribution: A Transversal Study. BioMed Res. Int., 2017.10.1155/2017/5925137 ↗
3. Bresnahan, P.J., and Juanto, M.A. (2020). Pediatric Flatfeet—A Disease Entity That Demands Greater Attention and Treatment. Front. Pediatr., 8.10.3389/fped.2020.00019 ↗
4. Cen, X., Gao, L., Yang, M., Liang, M., Bíró, I., and Gu, Y. (2021). Arch-Support Induced Changes in Foot-Ankle Coordination in Young Males with Flatfoot during Unplanned Gait Termination. J. Clin. Med., 10.10.3390/jcm10235539 ↗
5. One small step: A review of Plio- Pleistocene hominin foot evolution10.1002/ajpa.23750 ↗
6. Adult Acquired Flatfoot Deformity: Anatomy, Biomechanics, Staging, and Imaging Findings10.1148/rg.2019190046 ↗
7. Understanding the foot’s functional anatomy in physiological and pathological conditions: The calcaneopedal unit concept10.1302/1863-2548.13.180022 ↗
8. Adult-Acquired Flatfoot Deformity10.1177/2473011418820847 ↗
9. First steps: Parent health behaviours related to children’s foot health10.1177/1367493519864752 ↗
10. Holowka, N.B., Wallace, I.J., and Lieberman, D.E. (2018). Foot strength and stiffness are related to footwear use in a comparison of minimally- vs. conventionally-shod populations. Sci. Rep., 8.10.1038/s41598-018-21916-7 ↗
11. Kostkevičius, G., and Astromskas, R.A. (2010). Visos Bėdos Dėl Pėdos, Verslo Respublika.
12. The biomechanical effects and perceived comfort of textile-fabricated insoles during straight line walking10.1177/0309364617696084 ↗
13. Martinelli, N., Bianchi, A., Prandoni, L., Maiorano, E., and Sansone, V. (2021). Quality of Life in Young Adults after Flatfoot Surgery: A Case-Control Study. J. Clin. Med., 10.10.3390/jcm10030451 ↗
14. Evaluation of Foot Arch in Adult Women: Comparison between Five Different Footprint Parameters10.17576/jsm-2017-4610-22 ↗
15. Nagano, H., and Begg, R. (2018). Shoe-Insole Technology for Injury Prevention in Walking. Sensors, 18.10.3390/s18051468 ↗
16. Modern Theory of the Development of Adult Acquired Flat Foot and an Updated Spring Ligament Classification System10.4172/2329-910X.1000247 ↗
17. Shi, Q.Q., Li, P.L., Yick, K.-L., Li, N.-W., and Jiao, J. (2022). Effects of contoured insoles with different materials on plantar pressure offloading in diabetic elderly during gait. Sci. Rep., 12.10.1038/s41598-022-19814-0 ↗
18. The Effect of Arch Height and Material Hardness of Personalized Insole on Correction and Tissues of Flatfoot10.1155/2017/8614341 ↗
19. Utilization of artificial intelligence in the diagnosis of pes planus and pes cavus with a smartphone camera10.5312/wjo.v15.i12.1146 ↗
20. Subramaniam, S., Majumder, S., Faisal, A.I., and Deen, M.J. (2022). Insole-Based Systems for Health Monitoring: Current Solutions and Research Challenges. Sensors, 22.10.3390/s22020438 ↗
21. Differences in rearfoot, midfoot, and forefoot kinematics of normal foot and flatfoot during running10.1002/jor.24877 ↗
22. Anatomy of foot and ankle perforator veins
23. Finite element analysis of biomechanical effects of total ankle arthroplasty on the foot
24. Low-cost 3D motion capture system using passive optical markers and monocular vision10.1016/j.ijleo.2016.11.174 ↗
25. Foot trajectories and loading rates in a transfemoral amputee for six different commercial prosthetic knees: An indication of adaptability10.1016/j.medengphy.2019.03.014 ↗
26. Povilaitytė, J. (2025, June 17). Comparison of Preschool Children Flatfoot Evaluation Methods Before and After Kinesitherapy. Available online: https://vb.lsu.lt/object/elaba:2139234/index.html.
27. He, K., Zhang, X., Ren, S., and Sun, J. (2016). Deep Residual Learning for Image Recognition. arXiv.10.1109/CVPR.2016.90 ↗
28. Huang, G., Liu, Z., Van Der Maaten, L., and Weinberger, K.Q. (2017, January 21–26). Densely Connected Convolutional Networks. Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.10.1109/CVPR.2017.243 ↗
29. Tan, M., and Le, Q. (2019). EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks. arXiv.
30. Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., and Chen, L.-C. (2018, January 18–23). MobileNetV2: Inverted Residuals and Linear Bottlenecks. Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition CVPR, Salt Lake City, UT, USA.10.1109/CVPR.2018.00474 ↗
31. Howard, A., Sandler, M., Chen, B., Wang, W., Chen, L.-C., Tan, M., Chu, G., Vasudevan, V., Zhu, Y., and Pang, R. (November, January 27). Searching for MobileNetV3. Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision (ICCV), Seoul, Republic of Korea.10.1109/ICCV.2019.00140 ↗
32. Liu, Z., Mao, H., Wu, C.-Y., Feichtenhofer, C., Darrell, T., and Xie, S. (2022). A ConvNet for the 2020s (ConvNeXt). arXiv.10.1109/CVPR52688.2022.01167 ↗
33. Ma, N., Zhang, X., Zheng, H.-T., and Sun, J. (2018). ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design. arXiv.10.1007/978-3-030-01264-9_8 ↗
34. Iandola, F.N., Han, S., Moskewicz, M.W., Ashraf, K., Dally, W.J., and Keutzer, K. (2016). SqueezeNet: AlexNet-level accuracy with 50× fewer parameters and <0.5 MB model size. arXiv.
35. Index for rating diagnostic tests10.1002/1097-0142(1950)3:1<32::AID-CNCR2820030106>3.0.CO;2-3 ↗
36. Goodfellow, I., Bengio, Y., and Courville, A. (2016). Deep Learning, MIT Press. Available online: https://www.deeplearningbook.org/.
37. Wysocka-Mincewicz, M., Szczerbik, E., Mazur, M., Grabik, M., Kalinowska, M., and Syczewska, M. (2023). Foot Plantar Pressure Abnormalities in Near Adulthood Patients with Type 1 Diabetes. Biomedicines, 11.10.3390/biomedicines11112901 ↗
38. Ramírez-Rios, L.Y., Olguín-Tiznado, J.E., Ramos-Acosta, E.R., Inzunza-Gonzalez, E., Cano-Gutiérrez, J.C., García-Guerrero, E.E., and Camargo-Wilson, C. (2025). Toward Smarter Orthopedic Care: Classifying Plantar Footprints from RGB Images Using Vision Transformers and CNNs. J. Imaging, 11.10.3390/jimaging11110414 ↗
39. Evaluation of calcaneal inclusion angle in the diagnosis of pes planus with pretrained deep learning networks: An observational study10.1097/MD.0000000000043639 ↗
40. Joseph, S., and Balakannan, S.P. (2024). Early Detection and Classification of Flat Foot Deformity-It’s Significance and use of Deep Learning Techniques. Grenze International Journal of Engineering and Technology, Grenze Scientific Society.