Journal of Zhejiang University

Journal of Zhejiang University SCIENCE B 1998 Vol.-1 No.-1 P.

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

Author(s): Tao DU^1,³, Jinchao GE², Hong LYU^1,³, Yutong ZHANG^1,⁴, Xin XU^5,^6,⁷, Shaohua HU^1,^6,^7,⁹, Jingkai CHEN^1,⁸
Affiliation(s): 1. ¹Department of Psychiatry, The First Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou 310003, China ²School of Computing and Information Technology, University of Wollongong, Northfields Avenue, Wollongong NSW 2522, Australia ³School of Automation and Electrical Engineering, Shenyang Ligong University, Shenyang 110159, China ⁴Department of?Computer Science, Loughborough University, Loughborough?LE11?3TU, UK ⁵School of Public Health, The Second Affiliated Hospital of School of Medicine, Zhejiang University, Hangzhou 310058, China ⁶Nanhu Brain-computer Interface institute, Hangzhou 311100, China ⁷The State Key Lab of Brain-Machine Intelligence, MOE Frontier Science Center for Brain Science and Brain-Machine Integration, Zhejiang University School of Medicine, Hangzhou 310003, China ⁸The Zhejiang Key Laboratory of Precision Psychiatry, Hangzhou 310003, China ⁹Liangzhu Laboratory, Zhejiang University School of Medicine, Hangzhou 310000, China
Corresponding email(s): Jingkai CHEN, wzcjk922@163.com Shaohua HU, dorhushaohua@zju.edu.cn Xin XU, xuxinsummer@zju.edu.cn
Key Words: Major depressive disorder, Bipolar disorder, 3D facial reconstruction, Emotion dynamics, Valence and arousal

Share this article to： More <<< Previous Article \|Next Article >>>

Tao DU^1,³, Jinchao GE², Hong LYU^1,³, Yutong ZHANG^1,⁴, Xin XU^5,^6,⁷ , Shaohua HU^1,^6,^7,⁹, Jingkai CHEN^1,⁸. Three-dimensional face reconstruction for emotional dynamics: a novel approach to distinguishing bipolar disorder from major depressive disorders[J]. Journal of Zhejiang University Science B, 1998, -1(-1): .

@article{title="Three-dimensional face reconstruction for emotional dynamics: a novel approach to distinguishing bipolar disorder from major depressive disorders",
author="Tao DU^1,³, Jinchao GE², Hong LYU^1,³, Yutong ZHANG^1,⁴, Xin XU^5,^6,⁷ , Shaohua HU^1,^6,^7,⁹, Jingkai CHEN^1,⁸",
journal="Journal of Zhejiang University Science B",
volume="-1",
number="-1",
pages="",
year="1998",
publisher="Zhejiang University Press & Springer",
doi="10.1631/jzus.B2500705"
}

%0 Journal Article
%T Three-dimensional face reconstruction for emotional dynamics: a novel approach to distinguishing bipolar disorder from major depressive disorders
%A Tao DU^1
%A³
%A Jinchao GE²
%A Hong LYU^1
%A³
%A Yutong ZHANG^1
%A⁴
%A Xin XU^5
%A^6
%A⁷
%A Shaohua HU^1
%A^6
%A^7
%A⁹
%A Jingkai CHEN^1
%A⁸
%J Journal of Zhejiang University SCIENCE B
%V -1
%N -1
%P
%@ 1673-1581
%D 1998
%I Zhejiang University Press & Springer
%DOI 10.1631/jzus.B2500705

TY - JOUR
T1 - Three-dimensional face reconstruction for emotional dynamics: a novel approach to distinguishing bipolar disorder from major depressive disorders
A1 - Tao DU^{1
A1 -}³
A1 - Jinchao GE²
A1 - Hong LYU^{1
A1 -}³
A1 - Yutong ZHANG^{1
A1 -}⁴
A1 - Xin XU^{5
A1 -}^{6
A1 -}⁷
A1 - Shaohua HU^{1
A1 -}^{6
A1 -}^{7
A1 -}⁹
A1 - Jingkai CHEN^{1
A1 -}⁸
J0 - Journal of Zhejiang University Science B
VL - -1
IS - -1
SP -
EP - 0
%@ 1673-1581
Y1 - 1998
PB - Zhejiang University Press & Springer
ER -
DOI - 10.1631/jzus.B2500705

Abstract
Chinese Summary
Academic Network
Reviewer Comment

Abstract: 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 Adaptive Shape Model with Vision-to-Language (AsmV2L), a vision-language-guided fine-grained 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 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 maintains competitive 3D reconstruction accuracy while preserving emotion-related semantic information more effectively.

Darkslateblue:Affiliate; Royal Blue:Author; Turquoise:Article

Open peer comments: Debate/Discuss/Question/Opinion

<1>

Full Text: <5>

CLC number:

On-line Access: 2026-05-25

Received: 2025-11-09

Revision Accepted: 2026-04-19

Crosschecked: 0000-00-00

Cited: 0

Clicked: 11

Citations: Bibtex RefMan EndNote GB/T7714

Darkslateblue:Affiliate; Royal Blue:Author; Turquoise:Article

Similar articles

- Go to