Related Experiment Video
Updated: Feb 16, 2026
14:23
Imaging Intermediate Filaments and Microtubules with 2-dimensional Direct Stochastic Optical Reconstruction Microscopy
Published on: March 6, 2018
11.4K
List-mode TOF-PET 3D image reconstruction using stochastic primal-dual network
Kun Tian1, Rui Hu1, Yiming Wan1
1State Key Laboratory of Modern Optical Instrumentation, College of Optical Science and Engineering, Zhejiang University, Hangzhou, People's Republic of China.
Medical Physics
|February 15, 2026
Summary
A new deep learning method, LM-SPD-Net, reconstructs positron emission tomography (PET) images directly from list-mode data. This approach enhances image quality and overcomes computational challenges in time-of-flight (TOF) PET reconstruction.
Area of Science:
- Nuclear Medicine Imaging
- Medical Image Reconstruction
- Deep Learning Applications
Background:
- Positron Emission Tomography (PET) offers high sensitivity for visualizing biological activity.
- Conventional PET imaging faces limitations in spatial resolution and signal-to-noise ratio (SNR).
- Time-of-flight (TOF) data integration improves PET image quality but increases computational demands.
Purpose of the Study:
- To introduce a novel deep learning framework for direct list-mode PET image reconstruction.
- To address computational and memory challenges associated with TOF-PET data.
- To enhance the quality of reconstructed PET images.
Main Methods:
- LM-SPD-Net, a list-mode TOF-PET reconstruction framework utilizing a stochastic primal-dual network architecture.
- A primal module (CNNs) for image domain processing and a dual module (FCNNs) for data domain features.
- Integration of a physics-informed projection model and subset partitioning for efficient 3D reconstruction.
Main Results:
- LM-SPD-Net demonstrated superior performance compared to LM-OSEM, LM-SPDHG, and Fast-PET.
- Achieved 5%-20% improvements in Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index (SSIM) metrics.
- Visibly enhanced image quality in both simulated and semi-real clinical data.
Conclusions:
- The proposed LM-SPD-Net method effectively reconstructs overall subject structures with high fidelity.
- Maintained excellent performance in clinically relevant regions like tumors and the thalamus.
- Showcased robust performance, particularly under low-count conditions.
Related Concept Videos
01:07What is a Mode?
26.8K
The mode is one of the commonly used measures of a central tendency. It is defined as the most frequent value in a data set.
There can be more than one mode in a data set if multiple values have the same highest frequency. For instance, suppose that the Statistics exam scores of 20 students are: 50; 53; 59; 59; 63; 63; 72; 72; 72; 72; 72; 76; 78; 81; 83; 84; 84; 84; 90; 93. Here, the mode is 72, as it occurs most frequently, five times.
A data set with two modes is called bimodal. For example,...
There can be more than one mode in a data set if multiple values have the same highest frequency. For instance, suppose that the Statistics exam scores of 20 students are: 50; 53; 59; 59; 63; 63; 72; 72; 72; 72; 72; 76; 78; 81; 83; 84; 84; 84; 90; 93. Here, the mode is 72, as it occurs most frequently, five times.
A data set with two modes is called bimodal. For example,...
26.8K
02:26Protein Networks
4.6K
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,...
4.6K
01:14Ventilatory Modes
1.7K
Mechanical ventilators are life-saving devices that support or replace spontaneous breathing. They deliver breaths to patients through varying methods known as ventilator modes. Understanding these modes is critical for healthcare providers managing patients with respiratory failure.
There are three ventilatory modes: full support, partial support, and spontaneous. These are described below.
Full Support Modes
Full support modes include controlled mechanical ventilation, continuous mandatory...
There are three ventilatory modes: full support, partial support, and spontaneous. These are described below.
Full Support Modes
Full support modes include controlled mechanical ventilation, continuous mandatory...
1.7K
02:18Network Covalent Solids
16.3K
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...
16.3K
01:19MALDI-TOF Mass Spectrometry
7.1K
Mass spectrometry is a powerful characterization technique that can identify and separate a wide variety of compounds ranging from chemical to biological entities, based on their mass-to-charge ratio (m/z). The instruments that allow this detection, known as mass spectrometers, have three components: an ion source, a mass analyzer, and a detector. These spectrometers differ based on the nature of their ion source and analyzers.Matrix-assisted laser desorption ionization (MALDI) is a commonly...
7.1K
01:03Modes of Standing Waves - I
4.1K
A close look at earthquakes provides evidence for the conditions appropriate for resonance, standing waves, and constructive and destructive interference. A building may vibrate for several seconds with a driving frequency matching the building's natural frequency of vibration; this produces a resonance that results in one building collapsing while the neighboring buildings do not. Often, buildings of a certain height are devastated, while other taller buildings remain intact. This...
4.1K