1
|
Yi H, Yang R, Wang Y, Wang Y, Guo H, Cao X, Zhu S, He X. Enhanced model iteration algorithm with graph neural network for diffuse optical tomography. BIOMEDICAL OPTICS EXPRESS 2024; 15:1910-1925. [PMID: 38495688 PMCID: PMC10942675 DOI: 10.1364/boe.509775] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 10/19/2023] [Revised: 02/01/2024] [Accepted: 02/12/2024] [Indexed: 03/19/2024]
Abstract
Diffuse optical tomography (DOT) employs near-infrared light to reveal the optical parameters of biological tissues. Due to the strong scattering of photons in tissues and the limited surface measurements, DOT reconstruction is severely ill-posed. The Levenberg-Marquardt (LM) is a popular iteration method for DOT, however, it is computationally expensive and its reconstruction accuracy needs improvement. In this study, we propose a neural model based iteration algorithm which combines the graph neural network with Levenberg-Marquardt (GNNLM), which utilizes a graph data structure to represent the finite element mesh. In order to verify the performance of the graph neural network, two GNN variants, namely graph convolutional neural network (GCN) and graph attention neural network (GAT) were employed in the experiments. The results showed that GCNLM performs best in the simulation experiments within the training data distribution. However, GATLM exhibits superior performance in the simulation experiments outside the training data distribution and real experiments with breast-like phantoms. It demonstrated that the GATLM trained with simulation data can generalize well to situations outside the training data distribution without transfer training. This offers the possibility to provide more accurate absorption coefficient distributions in clinical practice.
Collapse
Affiliation(s)
- Huangjian Yi
- School of Information Sciences and Technology, Northwest University, Xi’an, Shaanxi 710069, China
- The Xi’an Key Laboratory of Radiomics and Intelligent Perception, No. 1 Xuefu Avenue, 710127 Xi’an, Shaanxi, China
| | - Ruigang Yang
- School of Information Sciences and Technology, Northwest University, Xi’an, Shaanxi 710069, China
- The Xi’an Key Laboratory of Radiomics and Intelligent Perception, No. 1 Xuefu Avenue, 710127 Xi’an, Shaanxi, China
| | - Yishuo Wang
- School of Information Sciences and Technology, Northwest University, Xi’an, Shaanxi 710069, China
- The Xi’an Key Laboratory of Radiomics and Intelligent Perception, No. 1 Xuefu Avenue, 710127 Xi’an, Shaanxi, China
| | - Yihan Wang
- School of Life Science and Technology, Xidian University, Xi’an, Shaanxi 710026, China
| | - Hongbo Guo
- School of Information Sciences and Technology, Northwest University, Xi’an, Shaanxi 710069, China
- The Xi’an Key Laboratory of Radiomics and Intelligent Perception, No. 1 Xuefu Avenue, 710127 Xi’an, Shaanxi, China
| | - Xu Cao
- School of Life Science and Technology, Xidian University, Xi’an, Shaanxi 710026, China
| | - Shouping Zhu
- School of Life Science and Technology, Xidian University, Xi’an, Shaanxi 710026, China
| | - Xiaowei He
- School of Information Sciences and Technology, Northwest University, Xi’an, Shaanxi 710069, China
- The Xi’an Key Laboratory of Radiomics and Intelligent Perception, No. 1 Xuefu Avenue, 710127 Xi’an, Shaanxi, China
| |
Collapse
|
2
|
Poplack SP, Park EY, Ferrara KW. Optical Breast Imaging: A Review of Physical Principles, Technologies, and Clinical Applications. JOURNAL OF BREAST IMAGING 2023; 5:520-537. [PMID: 37981994 PMCID: PMC10655724 DOI: 10.1093/jbi/wbad057] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/21/2023]
Abstract
Optical imaging involves the propagation of light through tissue. Current optical breast imaging technologies, including diffuse optical spectroscopy, diffuse optical tomography, and photoacoustic imaging, capitalize on the selective absorption of light in the near-infrared spectrum by deoxygenated and oxygenated hemoglobin. They provide information on the morphological and functional characteristics of different tissues based on their varied interactions with light, including physiologic information on lesion vascular content and anatomic information on tissue vascularity. Fluorescent contrast agents, such as indocyanine green, are used to visualize specific tissues, molecules, or proteins depending on how and where the agent accumulates. In this review, we describe the physical principles, spectrum of technologies, and clinical applications of the most common optical systems currently being used or developed for breast imaging. Most notably, US co-registered photoacoustic imaging and US-guided diffuse optical tomography have demonstrated efficacy in differentiating benign from malignant breast masses, thereby improving the specificity of diagnostic imaging. Diffuse optical tomography and diffuse optical spectroscopy have shown promise in assessing treatment response to preoperative systemic therapy, and photoacoustic imaging and diffuse optical tomography may help predict tumor phenotype. Lastly, fluorescent imaging using indocyanine green dye performs comparably to radioisotope mapping of sentinel lymph nodes and appears to improve the outcomes of autologous tissue flap breast reconstruction.
Collapse
Affiliation(s)
- Steven P. Poplack
- Stanford University School of Medicine, Department of Radiology, Palo Alto, CA, USA
| | - Eun-Yeong Park
- Stanford University School of Medicine, Department of Radiology, Palo Alto, CA, USA
| | - Katherine W. Ferrara
- Stanford University School of Medicine, Department of Radiology, Palo Alto, CA, USA
| |
Collapse
|
3
|
Shi Y, Wang Y, Meng F, Zhou J, Wen B, Zhang X, Liu Y, Li L, Li J, Cao X, Kang F, Zhu S. 3D directional gradient L 0 norm minimization guided limited-view reconstruction in a dual-panel positron emission mammography. Comput Biol Med 2023; 161:107010. [PMID: 37235943 DOI: 10.1016/j.compbiomed.2023.107010] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/21/2022] [Revised: 04/13/2023] [Accepted: 05/03/2023] [Indexed: 05/28/2023]
Abstract
BACKGROUND Dual-panel PET is often used for local organ imaging, especially breast imaging, due to its simple structure, high sensitivity, good in-plane resolution, and straightforward fusion with other imaging modalities. Nevertheless, because of data loss caused by the dual-panel structure, using conventional image reconstruction methods results in limited-view artifacts and low image quality in dual-panel positron emission mammography (PEM), which may seriously affect the diagnosis. To mitigate the limited-view artifacts in the dual-panel PEM, we propose a 3D directional gradient L0 norm minimization (3D-DL0) guided reconstruction method. METHODS The detailed derivation and reasonable simplification of the 3D-DL0 algorithm are given first. Using this algorithm, we then obtain a prior image with edge recovery but contrast loss. To limit the solution space, the 3D-DL0 prior is introduced into the Maximum a Posteriori reconstruction. Meanwhile, a space-invariant point spread function is also implemented to restore image contrast and boundaries. Finally, the reconstructed images with limited-view artifact suppression are obtained. The proposed method was evaluated using the data acquired from physical phantoms and patients with breast tumors on a commercial dual-panel PET system. RESULTS The qualitative and quantitative studies for phantom data and the blind reader study for clinical data show that the proposed method is more effective in reaching a balance between artifact elimination and image contrast improvement compared with various limited-view reconstruction methods. In addition, the iteration process of the method is proved convergent numerically. CONCLUSIONS The image quality improvement confirms the potential value of the proposed reconstruction algorithm to address the limited-view problem, and thus improve diagnostic accuracy in dual-panel PEM imaging.
Collapse
Affiliation(s)
- Yu Shi
- School of Life Science and Technology, Xidian University & Engineering Research Center of Molecular and Neuro Imaging, Ministry of Education, Xi'an, Shaanxi, 710126, China; Xi'an Key Laboratory of Intelligent Sensing and Regulation of Trans-Scale Life Information & International Joint Research Center for Advanced Medical Imaging and Intelligent Diagnosis and Treatment, School of Life Science and Technology, Xidian University, Xi'an, Shaanxi, 710126, China; Innovation Center for Advanced Medical Imaging and Intelligent Medicine, Guangzhou Institute of Technology, Xidian University, Guangzhou, Guangdong, 51055, China
| | - Yirong Wang
- Department of Nuclear Medicine, Xijing Hospital, Fourth Military Medical University, Xi'an, Shaanxi, 710032, China
| | - Fanzhen Meng
- School of Life Science and Technology, Xidian University & Engineering Research Center of Molecular and Neuro Imaging, Ministry of Education, Xi'an, Shaanxi, 710126, China; School of Medical Imaging, Hebei Medical University, Shijiazhuang City, Hebei, 050017, China
| | - Jianwei Zhou
- School of Life Science and Technology, Xidian University & Engineering Research Center of Molecular and Neuro Imaging, Ministry of Education, Xi'an, Shaanxi, 710126, China; Xi'an Key Laboratory of Intelligent Sensing and Regulation of Trans-Scale Life Information & International Joint Research Center for Advanced Medical Imaging and Intelligent Diagnosis and Treatment, School of Life Science and Technology, Xidian University, Xi'an, Shaanxi, 710126, China; Innovation Center for Advanced Medical Imaging and Intelligent Medicine, Guangzhou Institute of Technology, Xidian University, Guangzhou, Guangdong, 51055, China
| | - Bo Wen
- School of Life Science and Technology, Xidian University & Engineering Research Center of Molecular and Neuro Imaging, Ministry of Education, Xi'an, Shaanxi, 710126, China; Xi'an Key Laboratory of Intelligent Sensing and Regulation of Trans-Scale Life Information & International Joint Research Center for Advanced Medical Imaging and Intelligent Diagnosis and Treatment, School of Life Science and Technology, Xidian University, Xi'an, Shaanxi, 710126, China; Innovation Center for Advanced Medical Imaging and Intelligent Medicine, Guangzhou Institute of Technology, Xidian University, Guangzhou, Guangdong, 51055, China
| | - Xuexue Zhang
- School of Life Science and Technology, Xidian University & Engineering Research Center of Molecular and Neuro Imaging, Ministry of Education, Xi'an, Shaanxi, 710126, China; Xi'an Key Laboratory of Intelligent Sensing and Regulation of Trans-Scale Life Information & International Joint Research Center for Advanced Medical Imaging and Intelligent Diagnosis and Treatment, School of Life Science and Technology, Xidian University, Xi'an, Shaanxi, 710126, China; Innovation Center for Advanced Medical Imaging and Intelligent Medicine, Guangzhou Institute of Technology, Xidian University, Guangzhou, Guangdong, 51055, China
| | - Yanyun Liu
- School of Life Science and Technology, Xidian University & Engineering Research Center of Molecular and Neuro Imaging, Ministry of Education, Xi'an, Shaanxi, 710126, China; Xi'an Key Laboratory of Intelligent Sensing and Regulation of Trans-Scale Life Information & International Joint Research Center for Advanced Medical Imaging and Intelligent Diagnosis and Treatment, School of Life Science and Technology, Xidian University, Xi'an, Shaanxi, 710126, China; Innovation Center for Advanced Medical Imaging and Intelligent Medicine, Guangzhou Institute of Technology, Xidian University, Guangzhou, Guangdong, 51055, China
| | - Lei Li
- School of Life Science and Technology, Xidian University & Engineering Research Center of Molecular and Neuro Imaging, Ministry of Education, Xi'an, Shaanxi, 710126, China; Xi'an Key Laboratory of Intelligent Sensing and Regulation of Trans-Scale Life Information & International Joint Research Center for Advanced Medical Imaging and Intelligent Diagnosis and Treatment, School of Life Science and Technology, Xidian University, Xi'an, Shaanxi, 710126, China; Innovation Center for Advanced Medical Imaging and Intelligent Medicine, Guangzhou Institute of Technology, Xidian University, Guangzhou, Guangdong, 51055, China
| | - Juntao Li
- School of Life Science and Technology, Xidian University & Engineering Research Center of Molecular and Neuro Imaging, Ministry of Education, Xi'an, Shaanxi, 710126, China; Xi'an Key Laboratory of Intelligent Sensing and Regulation of Trans-Scale Life Information & International Joint Research Center for Advanced Medical Imaging and Intelligent Diagnosis and Treatment, School of Life Science and Technology, Xidian University, Xi'an, Shaanxi, 710126, China; Innovation Center for Advanced Medical Imaging and Intelligent Medicine, Guangzhou Institute of Technology, Xidian University, Guangzhou, Guangdong, 51055, China
| | - Xu Cao
- School of Life Science and Technology, Xidian University & Engineering Research Center of Molecular and Neuro Imaging, Ministry of Education, Xi'an, Shaanxi, 710126, China; Xi'an Key Laboratory of Intelligent Sensing and Regulation of Trans-Scale Life Information & International Joint Research Center for Advanced Medical Imaging and Intelligent Diagnosis and Treatment, School of Life Science and Technology, Xidian University, Xi'an, Shaanxi, 710126, China; Innovation Center for Advanced Medical Imaging and Intelligent Medicine, Guangzhou Institute of Technology, Xidian University, Guangzhou, Guangdong, 51055, China.
| | - Fei Kang
- Department of Nuclear Medicine, Xijing Hospital, Fourth Military Medical University, Xi'an, Shaanxi, 710032, China.
| | - Shouping Zhu
- School of Life Science and Technology, Xidian University & Engineering Research Center of Molecular and Neuro Imaging, Ministry of Education, Xi'an, Shaanxi, 710126, China; Xi'an Key Laboratory of Intelligent Sensing and Regulation of Trans-Scale Life Information & International Joint Research Center for Advanced Medical Imaging and Intelligent Diagnosis and Treatment, School of Life Science and Technology, Xidian University, Xi'an, Shaanxi, 710126, China; Innovation Center for Advanced Medical Imaging and Intelligent Medicine, Guangzhou Institute of Technology, Xidian University, Guangzhou, Guangdong, 51055, China.
| |
Collapse
|
4
|
Vanegas M, Mireles M, Xu E, Yan S, Fang Q. Compact breast shape acquisition system for improving diffuse optical tomography image reconstructions. BIOMEDICAL OPTICS EXPRESS 2023; 14:1579-1593. [PMID: 37078036 PMCID: PMC10110328 DOI: 10.1364/boe.481092] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Received: 11/15/2022] [Revised: 12/23/2022] [Accepted: 01/04/2023] [Indexed: 05/03/2023]
Abstract
Diffuse optical tomography (DOT) has been investigated for diagnosing malignant breast lesions, but its accuracy relies on model-based image reconstructions, which in turn depends on the accuracy of breast shape acquisition. In this work, we have developed a dual-camera structured light imaging (SLI) breast shape acquisition system tailored for a mammography-like compression setting. Illumination pattern intensity is dynamically adjusted to account for skin tone differences, while thickness-informed pattern masking reduces artifacts due to specular reflections. This compact system is affixed to a rigid mount that can be installed into existing mammography or parallel-plate DOT systems without the need for camera-projector re-calibration. Our SLI system produces sub-millimeter resolution with a mean surface error of 0.26 mm. This breast shape acquisition system results in more accurate surface recovery, with an average 1.6-fold reduction in surface estimation errors over a reference method via contour extrusion. Such improvement translates to 25% to 50% reduction in mean squared error in the recovered absorption coefficient for a series of simulated tumors 1-2 cm below the skin.
Collapse
Affiliation(s)
- Morris Vanegas
- Department of Bioengineering, Northeastern University, Boston, MA 02115, USA
| | - Miguel Mireles
- Department of Bioengineering, Northeastern University, Boston, MA 02115, USA
| | - Edward Xu
- Department of Bioengineering, Northeastern University, Boston, MA 02115, USA
| | - Shijie Yan
- Department of Electrical and Computer Engineering, Northeastern University, Boston, MA 02115, USA
| | - Qianqian Fang
- Department of Bioengineering, Northeastern University, Boston, MA 02115, USA
- Department of Electrical and Computer Engineering, Northeastern University, Boston, MA 02115, USA
| |
Collapse
|