Academic Journal
Deep learning-based segmentation of ultra-low-dose CT images using an optimized nnU-Net model
| Τίτλος: | Deep learning-based segmentation of ultra-low-dose CT images using an optimized nnU-Net model |
|---|---|
| Συγγραφείς: | Salimi, Yazdan, Mansouri, Zahra, Sun, Chang, Sanaat, Amirhossein, Yazdanpanah, Mohammadhossein, Shooli, Hossein, Nkoulou, René, Boudabbous, Sana, Zaidi, Habib |
| Πηγή: | Radiol Med |
| Στοιχεία εκδότη: | Springer Science and Business Media LLC, 2025. |
| Έτος έκδοσης: | 2025 |
| Θεματικοί όροι: | 616.0757, nnU-Net, Image Processing, Radiation dose, Radiographic Image Interpretation, Deep learning, NnU-Net, Radiation Dosage, X-Ray Computed/methods, Tomography, X-Ray Computed / methods, Deep Learning, Ultra-low-dose CT, Computed Tomography, Image Processing, Computer-Assisted / methods, Computer-Assisted/methods, Humans, Organ segmentation, Tomography, Algorithms, Radiographic Image Interpretation, Computer-Assisted / methods |
| Περιγραφή: | Purpose Low-dose CT protocols are widely used for emergency imaging, follow-ups, and attenuation correction in hybrid PET/CT and SPECT/CT imaging. However, low-dose CT images often suffer from reduced quality depending on acquisition and patient attenuation parameters. Deep learning (DL)-based organ segmentation models are typically trained on high-quality images, with limited dedicated models for noisy CT images. This study aimed to develop a DL pipeline for organ segmentation on ultra-low-dose CT images. Materials and methods 274 CT raw datasets were reconstructed using Siemens ReconCT software with ADMIRE iterative algorithm, generating full-dose (FD-CT) and simulated low-dose (LD-CT) images at 1%, 2%, 5%, and 10% of the original tube current. Existing FD-nnU-Net models segmented 22 organs on FD-CT images, serving as reference masks for training new LD-nnU-Net models using LD-CT images. Three models were trained for bony tissue (6 organs), soft-tissue (15 organs), and body contour segmentation. The segmented masks from LD-CT were compared to FD-CT as standard of reference. External datasets with actual LD-CT images were also segmented and compared. Results FD-nnU-Net performance declined with reduced radiation dose, especially below 10% (5 mAs). LD-nnU-Net achieved average Dice scores of 0.937 ± 0.049 (bony tissues), 0.905 ± 0.117 (soft-tissues), and 0.984 ± 0.023 (body contour). LD models outperformed FD models on external datasets. Conclusion Conventional FD-nnU-Net models performed poorly on LD-CT images. Dedicated LD-nnU-Net models demonstrated superior performance across cross-validation and external evaluations, enabling accurate segmentation of ultra-low-dose CT images. The trained models are available on our GitHub page. |
| Τύπος εγγράφου: | Article Other literature type |
| Περιγραφή αρχείου: | application/pdf |
| Γλώσσα: | English |
| ISSN: | 1826-6983 |
| DOI: | 10.1007/s11547-025-01989-x |
| Σύνδεσμος πρόσβασης: | https://pubmed.ncbi.nlm.nih.gov/40100539 |
| Rights: | CC BY |
| Αριθμός Καταχώρησης: | edsair.doi.dedup.....e321773c4de14318e3cc6a16f9a06e99 |
| Βάση Δεδομένων: | OpenAIRE |
| ISSN: | 18266983 |
|---|---|
| DOI: | 10.1007/s11547-025-01989-x |