Zhang, Peng, Ma, Chenbin, Song, Fan, Zhang, Tianyi, Sun, Yangyang, Feng, Youdan, He, Yufang, Liu, Fei, Wang, Daifa, and Zhang, Guanglei
• We propose an effective adversarial learning strategy in the image domain to enhance the reconstruction robustness. • We propose a novel transfer learning strategy in the perceptual domain to improve the reconstruction accuracy. • The adversarial learning strategy is combined with the transfer learning strategy to form the dual-domain joint reconstruction strategy to jointly improve the FMT reconstruction performance. • Prior knowledge of reconstructed fluorescent sources could be transferred to the FMT reconstruction to optimize the structural edge details. • The perceptual loss works together with the adversarial loss to mitigate the severely ill-posed nature of the FMT inverse problem. Fluorescence molecular tomography (FMT) is a promising molecular imaging modality for quantifying the three-dimensional (3D) distribution of fluorescent probes in small animals. Over the past few years, learning-based FMT reconstruction methods have achieved promising results. However, these methods typically attempt to minimize the mean-squared error (MSE) between the reconstructed image and the ground truth. Although signal-to-noise ratios (SNRs) are improved, they are susceptible to non-uniform artifacts and loss of structural detail, making it extremely challenging to obtain accurate and robust FMT reconstructions under noisy measurements. We propose a novel dual-domain joint strategy based on the image domain and perception domain for accurate and robust FMT reconstruction. First, we formulate an explicit adversarial learning strategy in the image domain, which greatly facilitates training and optimization through two enhanced networks to improve anti-noise ability. Besides, we introduce a novel transfer learning strategy in the perceptual domain to optimize edge details by providing perceptual priors for fluorescent targets. Collectively, the proposed dual-domain joint reconstruction strategy can significantly eliminate the non-uniform artifacts and effectively preserve the structural edge details. Both numerical simulations and in vivo mouse experiments demonstrate that the proposed method markedly outperforms traditional and cutting-edge methods in terms of positioning accuracy, image contrast, robustness, and target morphological recovery. The proposed method achieves the best reconstruction performance and has great potential to facilitate precise localization and 3D visualization of tumors in in vivo animal experiments. [ABSTRACT FROM AUTHOR]