EUVIMEDEUVIMED entdecken
Open Access

Three-dimensional face reconstruction for emotional dynamics: a novel approach to distinguishing bipolar disorder from major depressive disorder

Tao DU, Jinchao Ge, Hong Lyu, Yutong Zhang, Xin Xu, Shaohua Hu, Jingkai Chen

Journal of Zhejiang University-SCIENCE B · 2026

DOI: 10.1631/jzus.b2500705 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Zhejiang University-SCIENCE B, 2026. Verfasst von Tao DU und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Psychiatry, The First Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou 310003, China. Hauptthemen laut MEDLINE: Major Depressive Disorder, Bipolar Disorder, Imaging, Three-Dimensional, Emotions. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 45 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: the National Key Research and Development Program of China, the National Natural Science Foundation of China, the Key R&D Program of Zhejiang Province.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Major depressive disorder (MDD) and bipolar disorder (BD) are frequently misdiagnosed in clinical practice due to their overlapping symptoms, resulting in delayed treatment and an increased burden on patients. Reliable biomarkers for early differential diagnosis are currently lacking. To address this, we developed a clinical facial video dataset of patients with BD and MDD and introduced an adaptive-shape vision-to-language model (AsmV2L), a vision-language-guided fine-grained three-dimensional (3D) face reconstruction framework that better preserves affect-related facial cues from monocular videos. Using valence-arousal (VA) representations estimated from these reconstructed 3D faces, we identified distinct affective patterns that differentiated the two disorders. In the subject-level downstream evaluation, the emotional dynamic features extracted by our framework achieved 88.9% accuracy in distinguishing BD from MDD. Additionally, experiments on public benchmark datasets demonstrated that AsmV2L maintained competitive 3D reconstruction accuracy while preserving emotion-related semantic information more effectively. 重度抑郁障碍(major depressive disorder,MDD)与双相情感障碍(bipolar disorder,BD)由于临床症状存在重叠,在临床实践中容易发生误诊,从而导致治疗延误并增加患者负担。目前,针对这两种疾病进行早期鉴别诊断的可靠生物标志物仍较为缺乏。为解决这一问题,本研究构建了由BD和MDD患者组成的临床面部视频数据集,并提出视觉-语言自适应形状模型(adaptive-shape vision-to-language model,AsmV2L)。该模型是一种视觉-语言引导的细粒度三维(three-dimensional,3D)人脸重建框架,能够更好地保留单目视频中与情感相关的面部线索。基于重建三维人脸所估计的效价-唤醒度(valence-arousal,VA)表征,本研究识别出了可用于区分两种疾病的特异性情感模式。在受试者水平的下游评估中,本框架提取的情绪动态特征在区分BD与MDD时取得了88.9%的准确率。此外,在公共基准数据集上的实验结果表明,AsmV2L在保持具有竞争力的三维人脸重建精度的同时,能够更加有效地保留与情绪相关的语义信息。.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Major Depressive DisorderBipolar DisorderImaging, Three-DimensionalEmotionsFaceHumansDiagnosis, DifferentialFacial ExpressionFemaleMale

Stichwörter der Autor:innen

3D facial reconstructionBipolar disorderEmotion dynamicsMajor depressive disorderValence and arousal

Autor:innen und Institutionen

  • Department of Psychiatry, The First Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou 310003, China.
  • School of Automation and Electrical Engineering, Shenyang Ligong University, Shenyang 110159, China.
  • School of Computing and Information Technology, University of Wollongong, Northfields Avenue, Wollongong NSW 2522, Australia.
  • Department of Computer Science, Loughborough University, Loughborough, LE11 3TU, UK.
  • School of Public Health, The Second Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou 310058, China. wzcjk922@163.com, xuxinsummer@zju.edu.cn.
  • Nanhu Brain-Computer Interface Institute, Hangzhou 311100, China. wzcjk922@163.com, xuxinsummer@zju.edu.cn.

Förderung

  • the National Key Research and Development Program of China
  • the National Natural Science Foundation of China
  • the Key R&D Program of Zhejiang Province

Zitieren

APA

DU, T., Ge, J., Lyu, H., Zhang, Y., Xu, X., Hu, S., & Chen, J. (2026). Three-dimensional face reconstruction for emotional dynamics: a novel approach to distinguishing bipolar disorder from major depressive disorder. Journal of Zhejiang University-SCIENCE B. https://doi.org/10.1631/jzus.b2500705

Vancouver

DU T, Ge J, Lyu H, Zhang Y, Xu X, Hu S, et al. Three-dimensional face reconstruction for emotional dynamics: a novel approach to distinguishing bipolar disorder from major depressive disorder. Journal of Zhejiang University-SCIENCE B. 2026. doi:10.1631/jzus.b2500705

BibTeX
@article{DU2026,
  author = {DU, Tao and Ge, Jinchao and Lyu, Hong and Zhang, Yutong and Xu, Xin and Hu, Shaohua and Chen, Jingkai},
  title = {Three-dimensional face reconstruction for emotional dynamics: a novel approach to distinguishing bipolar disorder from major depressive disorder},
  journal = {Journal of Zhejiang University-SCIENCE B},
  year = {2026},
  doi = {10.1631/jzus.b2500705}
}
Kostenlos starten →