---
title: "STAR-Net: Physics Inspired Spectral Topology Aware Reconstruction Network for Single-View Fluorescence Molecular Tomography"
authors:
  - "Xiangzheng Li"
  - "Jian Zhang"
  - "Mengxiang Chu"
  - "Xiaoli Luo"
  - "Hongbo Guo"
  - "Xiaowei He"
doi: "10.24963/ijcai.2026/754"
url: "https://ijcai.org/proceedings/2026/754"
pdf: "https://ijcai.org/proceedings/2026/0754.pdf"
venue: "Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence"
year: 2026
pages: "6779-6787"
track: "AI and Health"
keywords:
  - "Explainable AI: Explainable AI"
  - "Medical imaging: Medical imaging"
---

# 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

*Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence*, pages 6779-6787. DOI: [10.24963/ijcai.2026/754](https://doi.org/10.24963/ijcai.2026/754)

## 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.