Adaptive monotone fast iterative shrinkage thresholding algorithm for fluorescence molecular tomography

Fang, Erxi; Wang, Jiajun; Hu, Dongming; Zhang, Jingya; Zou, Wei; Zhou, Yue

doi:10.1049/iet-smt.2014.0030

Cited by 6 publications

(4 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To tackle the ill-posedness of inverse problem, A priori sparsity is introduced [15]. L1-norm regularization is used and the over-relaxation algorithm is improved [16]. To achieve higher image clarity, a shape-based method based on the cosinoidal level set is conceived [17].…”

Section: Introductionmentioning

confidence: 99%

A method of fluorescence molecular tomographic reconstruction via the second-order sensitivity matrix

Zou,

Wang

2024

J. Eur. Opt. Society-Rapid Publ.

Self Cite

View full text Add to dashboard Cite

Fluorescence molecular tomographic (FMT) reconstruction is commonly solved based on the Jacobian matrix, which is a first-order sensitivity matrix. Basically, using the second-order derivatives for iterative reconstruction can help improve the performance of convergence. In this paper, a reconstruction method of FMT based on the reduction of the second-order sensitivity matrix is proposed. In addition, the strategy of detectors rotation is combined into the inverse reconstruction to further improve the reconstruction quality. The reconstructed results demonstrate that the proposed method accelerates the reconstruction with high precision of inverse solutions.

show abstract

Section: Introductionmentioning

confidence: 99%

A method of fluorescence molecular tomographic reconstruction via the second-order sensitivity matrix

Zou,

Wang

2024

J. Eur. Opt. Society-Rapid Publ.

Self Cite

View full text Add to dashboard Cite

show abstract

Section: Introductionmentioning

confidence: 99%

“…Although FMT holds great research potential in various practical applications related to tumor detection, it still faces huge challenges in biological tissue imaging, mainly limited detection accuracy and imaging quality (Ntziachristos 2010, Liu et al 2012b, Darne et al 2014, Fang et al 2015. First, due to the strong scattering effect of photons, linear changes in the optical parameters of fluorescent markers inside biological tissues cause nonlinear changes in fluorescence signals detected on the surface, and the simplified linear photon propagation model makes it challenging to improve the detection accuracy (Ntziachristos 2010, Liu et al 2012b, Fang et al 2015. Secondly, since FMT reconstruction is a process of recovering 3D data from 2D data, coupled with the nonlinear relationship caused by scattering, the reconstruction process is regarded as an ill-posed problem, leading to the deterioration of FMT image quality including spatial resolution, positioning accuracy and morphological restoration (Ntziachristos 2010, Darne et al 2014.…”

Section: Introductionmentioning

confidence: 99%

A review of advances in imaging methodology in fluorescence molecular tomography

Zhang

Song

et al. 2022

Phys. Med. Biol.

View full text Add to dashboard Cite

Objective. Fluorescence molecular tomography (FMT), as an encouraging and non-invasive optical molecular imaging technology with strong specificity and sensitivity, has great potential for preclinical and clinical studies in tumor diagnosis, drug development, and therapeutic evaluation. However, the strong scattering of photons and the insufficient surface measurements make it very challenging to improve the quality of FMT reconstruction and practical application for early tumor detection. Therefore, continuous efforts have been made to explore more effective approaches or solutions in the pursuit of obtaining high-quality FMT reconstructions. Approach. This review takes a comprehensive overview of imaging methodology advances of FMT, mainly focusing on two critical issues in FMT reconstructions: improving the accuracy of solving the forward physical model and mitigating the ill-posed nature of the inverse problem from a methodological point of view. More importantly, numerous impressive and practical strategies and methods for improving the FMT reconstruction quality are summarized. Notably, the deep learning methods have been elaborately discussed to illustrate the advantages in promoting the imaging performance of FMT owing to the practicality of large datasets, the emergence of optimized algorithms, and the applications of innovative networks. Main results. The results demonstrate that the imaging quality of FMT can be effectively promoted by improving the accuracy of optical parameter modeling, combining with prior knowledge, and reducing dimensionality. In addition, the traditional regularization-based methods and the deep neural network-based methods, especially the end-to-end deep network, can enormously alleviate the ill-posedness of the inverse problem and improve the quality of FMT image reconstruction. Significance. This review aims at illustrating a variety of effective and practical methods for FMT image reconstruction, from which future research may benefit. Furthermore, it may provide some valuable research ideas and directions for FMT in the future, and could promote the development of FMT and other optical tomography.

show abstract

“…The strong scattering effect of photons causes nonlinear changes in the fluorescent signals detected on the surface of the tissue, causing the reconstruction of FMT to be seriously ill-posed. The simplified linear photon transport model will affect the space resolution, positioning accuracy and morphological recovery quality of the reconstruction image [4][5] . In addition, the number of fluorescent unknowns that need to be rebuilt in most FMT systems is much greater than the number of measurements, making the inverse problem of FMT is underdetermined, which affects the robustness of the solution process [3,[6][7] .…”

Section: Introductionmentioning

confidence: 99%

A model-driven deep unfolding network for fluorescence molecular tomography reconstruction

Yang

Zhou²

2022

Optics in Health Care and Biomedical Optics XII

View full text Add to dashboard Cite

As a high-sensitivity and high-specificity imaging method, fluorescence molecular tomography (FMT) can quantitatively reconstruct the distribution of fluorescence sources inside the organism, and has great application prospects in tumor diagnosis, medicine development, and treatment evaluation. However, the reconstruction accuracy of traditional FMT is limited by the oversimplified forward model and the severe ill-posedness of the inverse problem. A physical model-driven iteratively unfolding network named ISTA-UNet is proposed in this paper. By combining the model-driven Iterative Shrinkage/Thresholding (IST) process and the UNet network model, the ISTA-Unet framework can take advantage of the denoising and detail recovery capabilities of deep neural networks on the basis of guaranteeing interpretability. In order to verify the effectiveness of the network, this paper analyzes the reconstruction of fluorescent targets with different positions, edge-to-edge distances, and fluorescence yield ratios. The results demonstrates that the FMT reconstruction based on ISTA-UNet has a significant improvement in spatial resolution and quantification compared with traditional methods, and has great potential in improving the quality of image reconstruction.

show abstract

Adaptive monotone fast iterative shrinkage thresholding algorithm for fluorescence molecular tomography

Cited by 6 publications

References 24 publications

A method of fluorescence molecular tomographic reconstruction via the second-order sensitivity matrix

A method of fluorescence molecular tomographic reconstruction via the second-order sensitivity matrix

A review of advances in imaging methodology in fluorescence molecular tomography

A model-driven deep unfolding network for fluorescence molecular tomography reconstruction

Contact Info

Product

Resources

About