ReMAR-DS: Recalibrated Feature Learning for Metal Artifact Reduction and CT Domain Transformation
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916809626615808 |
|---|---|
| author | Rehman, Mubashara Martinel, Niki Avanzo, Michele Spizzo, Riccardo Micheloni, Christian |
| author_facet | Rehman, Mubashara Martinel, Niki Avanzo, Michele Spizzo, Riccardo Micheloni, Christian |
| contents | Artifacts in kilo-Voltage CT (kVCT) imaging degrade image quality, impacting clinical decisions. We propose a deep learning framework for metal artifact reduction (MAR) and domain transformation from kVCT to Mega-Voltage CT (MVCT). The proposed framework, ReMAR-DS, utilizes an encoder-decoder architecture with enhanced feature recalibration, effectively reducing artifacts while preserving anatomical structures. This ensures that only relevant information is utilized in the reconstruction process. By infusing recalibrated features from the encoder block, the model focuses on relevant spatial regions (e.g., areas with artifacts) and highlights key features across channels (e.g., anatomical structures), leading to improved reconstruction of artifact-corrupted regions. Unlike traditional MAR methods, our approach bridges the gap between high-resolution kVCT and artifact-resistant MVCT, enhancing radiotherapy planning. It produces high-quality MVCT-like reconstructions, validated through qualitative and quantitative evaluations. Clinically, this enables oncologists to rely on kVCT alone, reducing repeated high-dose MVCT scans and lowering radiation exposure for cancer patients. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_19531 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | ReMAR-DS: Recalibrated Feature Learning for Metal Artifact Reduction and CT Domain Transformation Rehman, Mubashara Martinel, Niki Avanzo, Michele Spizzo, Riccardo Micheloni, Christian Computer Vision and Pattern Recognition Artificial Intelligence Artifacts in kilo-Voltage CT (kVCT) imaging degrade image quality, impacting clinical decisions. We propose a deep learning framework for metal artifact reduction (MAR) and domain transformation from kVCT to Mega-Voltage CT (MVCT). The proposed framework, ReMAR-DS, utilizes an encoder-decoder architecture with enhanced feature recalibration, effectively reducing artifacts while preserving anatomical structures. This ensures that only relevant information is utilized in the reconstruction process. By infusing recalibrated features from the encoder block, the model focuses on relevant spatial regions (e.g., areas with artifacts) and highlights key features across channels (e.g., anatomical structures), leading to improved reconstruction of artifact-corrupted regions. Unlike traditional MAR methods, our approach bridges the gap between high-resolution kVCT and artifact-resistant MVCT, enhancing radiotherapy planning. It produces high-quality MVCT-like reconstructions, validated through qualitative and quantitative evaluations. Clinically, this enables oncologists to rely on kVCT alone, reducing repeated high-dose MVCT scans and lowering radiation exposure for cancer patients. |
| title | ReMAR-DS: Recalibrated Feature Learning for Metal Artifact Reduction and CT Domain Transformation |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2506.19531 |