Implicit neural representations for end-to-end PET reconstruction
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866910897372397568 |
|---|---|
| author | Moussaoui, Younès Mateus, Diana Taheri, Nasrin Moussaoui, Saïd Carlier, Thomas Stute, Simon |
| author_facet | Moussaoui, Younès Mateus, Diana Taheri, Nasrin Moussaoui, Saïd Carlier, Thomas Stute, Simon |
| contents | Implicit neural representations (INRs) have demonstrated strong capabilities in various medical imaging tasks, such as denoising, registration, and segmentation, by representing images as continuous functions, allowing complex details to be captured. For image reconstruction problems, INRs can also reduce artifacts typically introduced by conventional reconstruction algorithms. However, to the best of our knowledge, INRs have not been studied in the context of PET reconstruction. In this paper, we propose an unsupervised PET image reconstruction method based on the implicit SIREN neural network architecture using sinusoidal activation functions. Our method incorporates a forward projection model and a loss function adapted to perform PET image reconstruction directly from sinograms, without the need for large training datasets. The performance of the proposed approach was compared with that of conventional penalized likelihood methods and deep image prior (DIP) based reconstruction using brain phantom data and realistically simulated sinograms. The results show that the INR-based approach can reconstruct high-quality images with a simpler, more efficient model, offering improvements in PET image reconstruction, particularly in terms of contrast, activity recovery, and relative bias. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_21825 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Implicit neural representations for end-to-end PET reconstruction Moussaoui, Younès Mateus, Diana Taheri, Nasrin Moussaoui, Saïd Carlier, Thomas Stute, Simon Image and Video Processing Computer Vision and Pattern Recognition Implicit neural representations (INRs) have demonstrated strong capabilities in various medical imaging tasks, such as denoising, registration, and segmentation, by representing images as continuous functions, allowing complex details to be captured. For image reconstruction problems, INRs can also reduce artifacts typically introduced by conventional reconstruction algorithms. However, to the best of our knowledge, INRs have not been studied in the context of PET reconstruction. In this paper, we propose an unsupervised PET image reconstruction method based on the implicit SIREN neural network architecture using sinusoidal activation functions. Our method incorporates a forward projection model and a loss function adapted to perform PET image reconstruction directly from sinograms, without the need for large training datasets. The performance of the proposed approach was compared with that of conventional penalized likelihood methods and deep image prior (DIP) based reconstruction using brain phantom data and realistically simulated sinograms. The results show that the INR-based approach can reconstruct high-quality images with a simpler, more efficient model, offering improvements in PET image reconstruction, particularly in terms of contrast, activity recovery, and relative bias. |
| title | Implicit neural representations for end-to-end PET reconstruction |
| topic | Image and Video Processing Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.21825 |