EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Development and internal validation of a multimodal deep learning model for screening-level lower-limb alignment using plantar 3D foot scans

Simin Ni iD, Yaxi Chen iD, Chenyan Wang, Ding Zhou, Jiaqi Liu, Mo Zhou, Julian Leong, Yipeng Hu, Jie Huang, Jinwu Wang, Chaozong Liu iD

PLOS Digital Health · 11.11.2026 · 5 (11) · e0001802

DOI: 10.1371/journal.pdig.0001802 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS Digital Health, online erschienen am 11.11.2026. Verfasst von Simin Ni und 10 weiteren Autor:innen. Beteiligte Einrichtung: Division of Surgery and Interventional Science, University College London, London, United Kingdom. Die Arbeit nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: School of Medicine, Shanghai Jiao Tong University, HORIZON EUROPE Marie Sklodowska-Curie Actions.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Lower-limb alignment is a key determinant of musculoskeletal loading and is associated with biomechanical risk pathways for conditions such as knee osteoarthritis and plantar fasciitis. However, routine alignment assessment still relies on radiography or specialist clinical examination, limiting scalability for early screening. Here, we investigated whether plantar foot morphology captured by weight-bearing 3D scanning can serve as a computational screening feature for proximal lower-limb alignment, and we developed a multimodal deep learning framework to support scalable alignment screening. We established a cross-sectional dataset of 167 participants (adults and children aged 6–60 years) with standardised plantar 3D foot scans and clinical labels for arch type, hindfoot alignment, and frontal-plane knee alignment. The proposed model jointly learns from plantar scan images and 16 geometric morphological features, integrated using feature-wise attention to prioritise alignment-relevant cues across modalities. Performance was evaluated using accuracy, precision, recall, F1 score, and AUC on a held-out test set, and interpretability was assessed with class activation mapping (CAM). Ablation studies compared alternative image encoders and fusion variants, including image-only, morphology-only, and fusion without attention. The attention-based multimodal model showed competitive but task-dependent performance, achieving accuracies of 89% for arch type, 81% for hindfoot alignment, and 76% for knee alignment. The image-only ViT achieved the highest accuracy for arch classification, while the ViT without-attention configuration achieved slightly higher accuracy and macro-F1 for knee alignment. These findings indicate that the benefit of multimodal attention fusion varied across alignment tasks. Activation maps consistently highlighted clinically relevant plantar regions associated with alignment patterns, suggesting morphological correlations consistent with a distal-proximal kinetic chain hypothesis. Together, these findings demonstrate the potential of plantar 3D scanning combined with multimodal, explainable deep learning as a non-invasive approach for screening alignment-related biomechanical risk factors, warranting further external validation before clinical translation.

Autor:innen und Institutionen

  • Division of Surgery and Interventional Science, University College London, London, United Kingdom.
  • Mechanical Engineering Department, University College London, London, United Kingdom.
  • UCL Hawkes Institute, University College London, London, United Kingdom.
  • College of Integrated Circuits and Micro-Nano Electronics, Fudan University, Shanghai, China.
  • Department of Orthopedic Surgery, Shanghai Ninth People's Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China.
  • Department of Medical Physics and Biomedical Engineering, University College London, London, United Kingdom.

ORCID-Profile: Simin Ni, Yaxi Chen, Chaozong Liu

Förderung

  • School of Medicine, Shanghai Jiao Tong University
  • HORIZON EUROPE Marie Sklodowska-Curie Actions

Zitieren

APA

Ni, S., Chen, Y., Wang, C., Zhou, D., Liu, J., Zhou, M., Leong, J., Hu, Y., Huang, J., Wang, J., & Liu, C. (2026). Development and internal validation of a multimodal deep learning model for screening-level lower-limb alignment using plantar 3D foot scans. PLOS Digital Health, 5(11), e0001802. https://doi.org/10.1371/journal.pdig.0001802

Vancouver

Ni S, Chen Y, Wang C, Zhou D, Liu J, Zhou M, et al. Development and internal validation of a multimodal deep learning model for screening-level lower-limb alignment using plantar 3D foot scans. PLOS Digital Health. 2026;5(11):e0001802. doi:10.1371/journal.pdig.0001802

BibTeX
@article{Ni2026,
  author = {Ni, Simin and Chen, Yaxi and Wang, Chenyan and Zhou, Ding and Liu, Jiaqi and Zhou, Mo and Leong, Julian and Hu, Yipeng and Huang, Jie and Wang, Jinwu and Liu, Chaozong},
  title = {Development and internal validation of a multimodal deep learning model for screening-level lower-limb alignment using plantar 3D foot scans},
  journal = {PLOS Digital Health},
  year = {2026},
  volume = {5},
  number = {11},
  pages = {e0001802},
  doi = {10.1371/journal.pdig.0001802}
}
Kostenlos starten →