Traditional methods under sparse view for reconstruction of photoacoustic tomography (PAT) often result in significant artifacts. Here, a novel image to image transformation method based on unsupervised learning artifact disentanglement network (ADN), named PAT-ADN, was proposed to address the issue. This network is equipped with specialized encoders and decoders that are responsible for encoding and decoding the artifacts and content components of unpaired images, respectively. The performance of the proposed PAT-ADN was evaluated using circular phantom data and the animal experimental data. The results demonstrate that PAT-ADN exhibits excellent performance in effectively removing artifacts. In particular, under extremely sparse view (e.g., 16 projections), structural similarity index and peak signal-to-noise ratio are improved by ∼188 % and ∼85 % in experimental data using the proposed method compared to traditional reconstruction methods. PAT-ADN improves the imaging performance of PAT, opening up possibilities for its application in multiple domains.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC11101706 | PMC |
| http://dx.doi.org/10.1016/j.pacs.2024.100613 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Unrolled deep learning for breast cancer detection using limited-view photoacoustic tomography data.
Med Biol Eng Comput
January 2025
Department of Electrical and Communication Engineering, United Arab Emirates University, Asharej, Al Ain, 15551, Abu Dhabi, United Arab Emirates.
Photoacoustic tomography (PAT) has emerged as a promising imaging modality for breast cancer detection, offering unique advantages in visualizing tissue composition without ionizing radiation. However, limited-view scenarios in clinical settings present significant challenges for image reconstruction quality and computational efficiency. This paper introduces novel unrolled deep learning networks based on split Bregman total variation (SBTV) and relaxed basis pursuit alternating direction method of multipliers (rBP-ADMM) algorithms to address these challenges.
View Article and Find Full Text PDFDeep Learning-Based Multi-View Projection Synthesis Approach for Improving the Quality of Sparse-View CBCT in Image-Guided Radiotherapy.
J Imaging Inform Med
January 2025
School of Electronic and Information Engineering, Beijing Jiaotong University, Beijing, China.
While radiation hazards induced by cone-beam computed tomography (CBCT) in image-guided radiotherapy (IGRT) can be reduced by sparse-view sampling, the image quality is inevitably degraded. We propose a deep learning-based multi-view projection synthesis (DLMPS) approach to improve the quality of sparse-view low-dose CBCT images. In the proposed DLMPS approach, linear interpolation was first applied to sparse-view projections and the projections were rearranged into sinograms; these sinograms were processed with a sinogram restoration model and then rearranged back into projections.
View Article and Find Full Text PDFMorphological Characteristics of Inferior Pole Patellar Fractures and a Finite-Element Analysis Combined With a Retrospective Clinical Study of Anchor Suture and Titanium Cable Cerclage Treatment.
Orthop Surg
January 2025
Department of Orthopedics Surgery, The Second Affiliated Hospital of Soochow University, Suzhou, Jiangsu Province, China.
Objective: Inferior pole patellar fractures (IPPFs) pose a significant challenge due to their complex fracture patterns and high risk of complications associated with current treatment methods. This study aims to (1) characterize the fracture patterns of IPPFs using fracture mapping and (2) compare the biomechanical stability and clinical outcomes of treatment with anchor suture with patellar cerclage versus Kirschner-wire tension band combined with patellar cerclage.
Methods: (1) A retrospective analysis was conducted on 61 patients with IPPF.
Contrastive independent subspace analysis network for multi-view spatial information extraction.
Neural Netw
January 2025
College of Mechatronics and Control Engineering, Shenzhen University, Shenzhen, Guangdong, China.
Multi-view classification integrates features from different views to optimize classification performance. Most of the existing works typically utilize semantic information to achieve view fusion but neglect the spatial information of data itself, which accommodates data representation with correlation information and is proven to be an essential aspect. Thus robust independent subspace analysis network, optimized by sparse and soft orthogonal optimization, is first proposed to extract the latent spatial information of multi-view data with subspace bases.
View Article and Find Full Text PDFHow do neighborhood environments impact adolescent health: a comprehensive study from subjective and objective perspectives using machine learning method.
Front Public Health
January 2025
School of Architecture and Urban Planning, Kunming University of Science and Technology, Kunming, China.
Existing studies have established a linear relationship between urban environments and adolescent health, but the combined impacts of subjective and objective environments on multi-dimensional health status (including physical and mental health) have not been fully explored. Furthermore, while some studies have examined the non-linear relationship between urban environments and adult health, research specifically focusing on adolescents is sparse. Using Kunming, China, as a case study, we employ Random Forest model to examine the non-linear relationship between subjective/objective neighborhood environments and adolescent physical/mental health.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!