Selfrec-Net: self-supervised deep learning approach for the reconstruction of Cherenkov-excited luminescence scanned tomography

Wenqian Zhang; Ting Hu; Zhe Li; Zhonghua Sun; Kebin Jia; Huijing Dou; Jinchao Feng; Brian W Pogue

doi:10.1364/BOE.480429

Selfrec-Net: self-supervised deep learning approach for the reconstruction of Cherenkov-excited luminescence scanned tomography

Biomed Opt Express. 2023 Jan 17;14(2):783-798. doi: 10.1364/BOE.480429. eCollection 2023 Feb 1.

Authors

Wenqian Zhang^{1

2}, Ting Hu^{1

2}, Zhe Li^{1

2}, Zhonghua Sun^{1

2}, Kebin Jia^{1

2}, Huijing Dou¹, Jinchao Feng^{1

2}, Brian W Pogue^{3

4}

Affiliations

¹ Beijing Key Laboratory of Computational Intelligence and Intelligent System, Faculty of Information Technology, Beijing University of Technology, Beijing 100124, China.
² Beijing Laboratory of Advanced Information Networks, Beijing 100124, China.
³ Department of Medical Physics, University of Wisconsin-Madison, Madison, WI 53705, USA.
⁴ bpogue@wisc.edu.

Abstract

As an emerging imaging technique, Cherenkov-excited luminescence scanned tomography (CELST) can recover a high-resolution 3D distribution of quantum emission fields within tissue using X-ray excitation for deep penetrance. However, its reconstruction is an ill-posed and under-conditioned inverse problem because of the diffuse optical emission signal. Deep learning based image reconstruction has shown very good potential for solving these types of problems, however they suffer from a lack of ground-truth image data to confirm when used with experimental data. To overcome this, a self-supervised network cascaded by a 3D reconstruction network and the forward model, termed Selfrec-Net, was proposed to perform CELST reconstruction. Under this framework, the boundary measurements are input to the network to reconstruct the distribution of the quantum field and the predicted measurements are subsequently obtained by feeding the reconstructed result to the forward model. The network was trained by minimizing the loss between the input measurements and the predicted measurements rather than the reconstructed distributions and the corresponding ground truths. Comparative experiments were carried out on both numerical simulations and physical phantoms. For singular luminescent targets, the results demonstrate the effectiveness and robustness of the proposed network, and comparable performance can be attained to a state-of-the-art deep supervised learning algorithm, where the accuracy of the emission yield and localization of the objects was far superior to iterative reconstruction methods. Reconstruction of multiple objects is still reasonable with high localization accuracy, although with limits to the emission yield accuracy as the distribution becomes more complex. Overall though the reconstruction of Selfrec-Net provides a self-supervised way to recover the location and emission yield of molecular distributions in murine model tissues.