Deep learning-based segmentation of ultra-low-dose CT images using an optimized nnU-Net model

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.