STAR-Net: Physics Inspired Spectral Topology Aware Reconstruction Network for Single-View Fluorescence Molecular Tomography

Li, Xiangzheng; Zhang, Jian; Chu, Mengxiang; Luo, Xiaoli; Guo, Hongbo; He, Xiaowei

doi:10.24963/ijcai.2026/754

STAR-Net: Physics Inspired Spectral Topology Aware Reconstruction Network for Single-View Fluorescence Molecular Tomography

Xiangzheng Li, Jian Zhang, Mengxiang Chu, Xiaoli Luo, Hongbo Guo, Xiaowei He

Download BibTeX Cite

Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence. AI and Health. Pages 6779-6787.

https://doi.org/10.24963/ijcai.2026/754

Keywords

Explainable AI: Explainable AI
Medical imaging: Medical imaging

Abstract

Fluorescence molecular tomography (FMT) serves as a pivotal modality for preclinical tumor screening. While single-view FMT offers distinct advantages in data acquisition efficiency and cost-effectiveness, the scarcity of projection views severely exacerbates photon scattering-induced depth ambiguity, rendering 3D volumetric recovery a highly ill-posed inverse problem. To address these challenges, we propose a physics-inspired spectral topology aware reconstruction network (STAR-Net). Specifically, STAR-Net establishes a synergistic framework: initially, a frequency domain decoupling strategy is introduced to simulate the physical characteristics of diffuse light fields; building on this, a differentiable inverse spectral gating (DISG) mechanism is utilized to explicitly impose low-pass spectral regularization for precise depth recovery; and further, a dual-domain synergistic module is integrated to dynamically fuse spatial and frequency features, achieving high-fidelity detail preservation. Extensive experiments on the Digimouse benchmark demonstrate that the proposed STAR-Net achieves the highest dice coefficient under single-view conditions, validating that explicit spectral topology modeling is a powerful paradigm for mitigating depth ambiguity.

Xiangzheng Li, Jian Zhang, Mengxiang Chu, Xiaoli Luo, Hongbo Guo, and Xiaowei He. 2026. STAR-Net: Physics Inspired Spectral Topology Aware Reconstruction Network for Single-View Fluorescence Molecular Tomography. In Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-26. IJCAI, 6779–6787. https://doi.org/10.24963/ijcai.2026/754

@inproceedings{ijcai2026p754,
  title     = {STAR-Net: Physics Inspired Spectral Topology Aware Reconstruction Network for Single-View Fluorescence Molecular Tomography},
  author    = {Li, Xiangzheng and Zhang, Jian and Chu, Mengxiang and Luo, Xiaoli and Guo, Hongbo and He, Xiaowei},
  booktitle = {Proceedings of the Thirty-Fifth International Joint Conference on
               Artificial Intelligence, {IJCAI-26}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {Diego Calvanese},
  pages     = {6779--6787},
  year      = {2026},
  month     = {8},
  note      = {AI and Health},
  doi       = {10.24963/ijcai.2026/754},
  url       = {https://doi.org/10.24963/ijcai.2026/754},
}

TY  - CPAPER
TI  - STAR-Net: Physics Inspired Spectral Topology Aware Reconstruction Network for Single-View Fluorescence Molecular Tomography
AU  - Li, Xiangzheng
AU  - Zhang, Jian
AU  - Chu, Mengxiang
AU  - Luo, Xiaoli
AU  - Guo, Hongbo
AU  - He, Xiaowei
T2  - Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-26
PB  - International Joint Conferences on Artificial Intelligence Organization
PY  - 2026
SP  - 6779
EP  - 6787
DO  - 10.24963/ijcai.2026/754
UR  - https://doi.org/10.24963/ijcai.2026/754
ER  -