以注意力驱动的互补信息融合网络用于稀疏的光声图像重建
Yixin Lai1,2, Qiong Zhang1, Zhengnan Yin1,2
1Shantou University Medical College, Shantou 515041, China.
Photoacoustics
|February 2, 2026
概括
DUAFF-Net显著改善了有限视图光声学断层扫描 (PAT) 图像的重建. 这种新的深度学习方法在数据有限的条件下提高了图像质量,超过了现有的技术.
科学领域:
- 生物医学成像技术 生物医学成像技术
- 医学物理 医学物理
- 计算机视觉 计算机视觉
背景情况:
- 光声学断层扫描 (PAT) 提供高分辨率,深层组织成像,但在有限的视图数据下遭受图像退化.
- 像延迟和总和 (DAS) 这样的传统方法产生了文物,并在有限视野场景中失去细节.
- 现有的深度学习 (DL) 方法很难从严重低样本的有限视图PAT数据中完全恢复复杂的细节.
研究的目的:
- 开发一种新的深度学习架构,DUAFF-Net,用于在有限视图光声学断层扫描中进行高质量的图像重建.
- 解决传统和现有的DL方法在从不完整的数据中恢复精细解剖特征方面的局限性.
- 在具有挑战性的数据采集约束条件下,提高PAT成像的稳定性和性能.
主要方法:
- 提出DUAFF-Net,一个双流深度学习网络,处理传统的DAS重建和插入原始数据.
- 实施了两阶段的功能融合策略:多尺度信息聚合和功能改进模块 (MIAF模块) 和全球上下文和深度融合模块 (GCDF模块).
- 在模拟的视网膜血管,大脑结构和体内小鼠腹部数据集上验证了DUAFF-Net.
主要成果:
- DUAFF-Net从极不完整的有限视图PAT数据生成了高质量的图像.
- 与DAS相比取得了显著的改进:~18.38 dB PSNR和~0.69 SSIM.
- 在保存细节和抑制文物方面,超越了最先进的DL重建模型.
结论:
- DUAFF-Net在有限视图PAT重建方面表现出卓越的性能,即使数据严重不完整.
- 双流架构和功能融合战略有效地提高了图像质量和细节恢复.
- 在数据采集受到限制的情况下,DUAFF-Net提供了一个强大的解决方案来挑战PAT应用程序.
相关概念视频
Complementary DNA
31.6K
Overview
31.6K
Nuclear Fusion
33.9K
The process of converting very light nuclei into heavier nuclei is also accompanied by the conversion of mass into large amounts of energy, a process called fusion. The principal source of energy in the sun is a net fusion reaction in which four hydrogen nuclei fuse and ultimately produce one helium nucleus and two positrons.
A helium nucleus has a mass that is 0.7% less than that of four hydrogen nuclei; this lost mass is converted into energy during the fusion. This reaction produces about...
A helium nucleus has a mass that is 0.7% less than that of four hydrogen nuclei; this lost mass is converted into energy during the fusion. This reaction produces about...
33.9K
Protein Networks
4.5K
An organism can have thousands of different proteins, and these proteins must cooperate to ensure the health of an organism. Proteins bind to other proteins and form complexes to carry out their functions. Many proteins interact with multiple other proteins creating a complex network of protein interactions.
These interactions can be represented through maps depicting protein-protein interaction networks, represented as nodes and edges. Nodes are circles that are representative of a protein,...
These interactions can be represented through maps depicting protein-protein interaction networks, represented as nodes and edges. Nodes are circles that are representative of a protein,...
4.5K
Network Covalent Solids
16.2K
Network covalent solids contain a three-dimensional network of covalently bonded atoms as found in the crystal structures of nonmetals like diamond, graphite, silicon, and some covalent compounds, such as silicon dioxide (sand) and silicon carbide (carborundum, the abrasive on sandpaper). Many minerals have networks of covalent bonds.
To break or to melt a covalent network solid, covalent bonds must be broken. Because covalent bonds are relatively strong, covalent network solids are typically...
To break or to melt a covalent network solid, covalent bonds must be broken. Because covalent bonds are relatively strong, covalent network solids are typically...
16.2K
Attention-Deficit/Hyperactivity Disorder
986
Attention-deficit/hyperactivity disorder (ADHD) is a neurodevelopmental disorder characterized by persistent inattention, hyperactivity, and impulsivity. It affects approximately 5-8% of children globally, with around 60-70% of cases persisting into adulthood. ADHD has significant implications for educational attainment, social interactions, and occupational success.
Diagnostic Criteria and Symptoms
To diagnose ADHD, symptoms must manifest before age 12 and be evident across multiple settings....
Diagnostic Criteria and Symptoms
To diagnose ADHD, symptoms must manifest before age 12 and be evident across multiple settings....
986
Tagging and Fusion Proteins
8.5K
Proteins are involved in several cellular processes and biochemical reactions. Analyzing a specific protein of interest requires it to be isolated from the other proteins in the cell. This is achieved by overexpressing the specific gene in a suitable host to produce large quantities of the target protein. A tag or label is recombined with the gene to produce a fusion protein containing the target protein and the tag. The tags on these fusion proteins can then be used for easy detection and...
8.5K


