跳到正文
原文
Nature 健康护理主题·· 8 小时前AI 评分55

Tele-Cranio:一种无需CT的AI远程诊断和规划解决方案

Tele-Cranio: a CT-free AI solution for remote diagnosis and planning of craniomaxillofacial deformities

AI 导读

该研究开发了一种基于AI的远程诊断和规划解决方案,无需CT即可重建面部形态,适用于多种口腔颌面畸形。该框架使用移动获取的2D面部照片重建3D面部形态,支持术后面部模拟。该技术适用于远程评估、无辐射随访和医生-患者沟通,补充而非替代基于CT的诊断和手术规划。

正文

npj Digital Medicine (2026) Cite this article

We’re sharing this article early to provide faster access to peer-reviewed, accepted research. It is citable and carries a permanent DOI. This version is subject to further edits and will be replaced automatically by the final Version of Record. All legal disclaimers apply.

Abstract

Computed tomography (CT) is central to craniomaxillofacial (CMF) deformity care, yet dependence on in-hospital imaging constrains remote preoperative assessment and outcome visualization, and repeated imaging can increase radiation and access burdens, particularly for children. We developed Tele-Cranio, a telemedicine-oriented artificial intelligence framework that uses mobile-acquired 2D facial photographs to reconstruct 3D facial morphology, estimate corresponding skeletal morphology and support postoperative facial simulation conditioned on surgeon-defined skeletal plans. Tele-Cranio was developed using 539 paired multimodal samples comprising 2D facial photographs, 3D facial scans and CT-derived skeletal models from individuals aged 3–60 years, including 334 patients with CMF deformities across malocclusion, cleft lip with/without palate, hemifacial microsomia and rare anomalies. Its core model, the Bidirectional Craniomaxillofacial Model-Deformity, learns a shared anatomical representation linking facial soft tissue and skeletal structures across normal and pathological morphology. For remote assessment, Tele-Cranio converts facial photographs into 3D facial surfaces and then infers 3D patient-specific skeletal geometry. For simulation, it generates individualized 3D postoperative facial previews after clinicians complete skeletal planning using standard clinical tools. Validated across heterogeneous CMF subgroups, Tele-Cranio provides an interpretable CT-free layer for remote triage, pre-CT consultation, radiation-free follow-up and surgeon–patient communication, while complementing rather than replacing CT-based definitive diagnosis and operative planning.

Acknowledgements

This work was supported by the Beijing Natural Science Foundation (L242092), the Strategic Priority Research Program of the Chinese Academy of Sciences (XDA0480103), the InnoHK Program and the CAMS Innovation Fund for Medical Sciences (CIFMS) (2024-I2M-C&T-B-078).

Funding

This work was supported by the Beijing Natural Science Foundation (L242092), the Strategic Priority Research Program of the Chinese Academy of Sciences (XDA0480103), the InnoHK Program and the CAMS Innovation Fund for Medical Sciences (CIFMS) (2024-I2M-C&T-B-078).

Author information

Author notes

  1. These authors contributed equally: Meng Xu, Zidu Wang.

Authors and Affiliations

  1. Cleft Lip & Palate Center, Plastic Surgery Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China

    Meng Xu & Tao Song

  2. State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China

    Zidu Wang, Zhen Lei & Xiangyu Zhu

  3. School of Artificial Intelligence, University of Chinese Academy of Sciences (UCAS), Beijing, China

    Zidu Wang, Zhen Lei & Xiangyu Zhu

  4. Department of Oral and Maxillofacial Surgery, the Affiliated Stomatological Hospital, China Medical University, Shenyang, China

    Lei Zhang

  5. Department of Orthognathic and Cleft Lip & Palate Surgery, School and Hospital of Stomatology, Wuhan University, Wuhan, China

    Chuanqi Qin & Xiaole Wang

  6. Digital Technology Center, Plastic Surgery Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China

    Jiayu Zhou & Hengyuan Ma

  7. Centre for Artificial Intelligence and Robotics (CAIR), Hong Kong Institute of Science & Innovation (HKISI), Chinese Academy of Sciences, Hong Kong SAR, China

    Zhen Lei

Authors

  1. Meng Xu
  2. Zidu Wang
  3. Lei Zhang
  4. Chuanqi Qin
  5. Xiaole Wang
  6. Jiayu Zhou
  7. Zhen Lei
  8. Hengyuan Ma
  9. Tao Song
  10. Xiangyu Zhu

Corresponding authors

Correspondence to Hengyuan Ma, Tao Song or Xiangyu Zhu.

Ethics declarations

Competing interests

The authors declare no competing interests.

Additional information

Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, 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 you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. 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-nc-nd/4.0/.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Xu, M., Wang, Z., Zhang, L. et al. Tele-Cranio: a CT-free AI solution for remote diagnosis and planning of craniomaxillofacial deformities. npj Digit. Med. (2026). https://doi.org/10.1038/s41746-026-03454-z

Download citation

  • Received: 06 July 2026

  • Accepted: 18 October 2026

  • Published: 20 November 2026

  • DOI: https://doi.org/10.1038/s41746-026-03454-z

来源:Nature 健康护理主题 · nature.com