Feasibility of Simulated Low-Dose CT with Deep Learning Denoising for Lymphoma PET/CT Imaging: A Clinical Study on Lesion Detection, Staging, and Therapy Response.
Authors
Affiliations (6)
Affiliations (6)
- Department of Nuclear Medicine, Xiangtan Central Hospital (The Affiliated Hospital of Hunan University), 120 Heping Road, Xiangtan, 411100, Hunan Province, China.
- Yale Biomedical Imaging Institute and Department of Radiology and Biomedical Imaging, Yale University, 333 Cedar Street, New Haven, CT, 06510, USA.
- Department of Radiology, Xiangtan Central Hospital (The Affiliated Hospital of Hunan University), 120 Heping Road, Xiangtan, 411100, Hunan Province, China.
- Department of Biomedical Informatics and Data Science, Yale University, 333 Cedar Street, New Haven, CT, 06510, USA.
- Gastrointestinal Endoscopy Center, Xiangtan Central Hospital (The Affiliated Hospital of Hunan University), 120 Heping Road, Xiangtan, 411100, Hunan Province, China. [email protected].
- Department of Nuclear Medicine, Xiangtan Central Hospital (The Affiliated Hospital of Hunan University), 120 Heping Road, Xiangtan, 411100, Hunan Province, China. [email protected].
Abstract
<sup>[18F]</sup>FDG PET/CT is central to lymphoma staging and treatment-response assessment, but repeated examinations increase cumulative radiation exposure, largely from the CT component. This retrospective study included 152 patients with 211 whole-body PET/CT scans and evaluated whether deep learning-denoised simulated low-dose CT can preserve diagnostic performance. A single-scan cohort of 108 patients was used exclusively for model development, while an independent follow-up cohort of 44 patients (103 examinations) was reserved for quantitative evaluation and a fully crossed multi-reader, multi-case study. Simulated low-dose CT images ranging from 2/3 to 1/8 of the standard dose were reviewed, and the 1/4-dose level was selected as the lowest clinically acceptable level. A denoising model was trained using paired standard-dose CT (SDCT) and simulated low-dose CT at 1/4 of the standard dose (SLDCT) images. Six nuclear medicine physicians evaluated three imaging conditions: PET/CT with SDCT, PET/CT with SLDCT, and PET/CT with denoised SLDCT (D-SLDCT), for image quality, lesion detectability, staging, and treatment response. D-SLDCT significantly improved quantitative image quality compared with SLDCT (all p < 0.0001) and increased subjective image-quality scores (4.11 ± 0.46 vs 3.00 ± 0.00). Staging accuracy was lower under the SLDCT condition than under the SDCT condition (MAE, 1.50 ± 0.27 vs 1.40 ± 0.20; p = 0.0011), whereas the D-SLDCT condition did not differ significantly from the SDCT condition (MAE, 1.44 ± 0.22; p = 0.47). Differences were more pronounced in patients with BMI ≥ 24 kg/m<sup>2</sup> and among junior readers. Lesion detectability and treatment-response assessment did not differ significantly across conditions, while within-reader lesion-detection agreement with the SDCT condition improved after denoising (κ = 0.72 vs 0.67). The D-SLDCT condition preserved diagnostic performance, supporting radiation-conscious lymphoma PET/CT. This study was registered with the Chinese Clinical Trial Registry (ChiCTR) on February 14, 2026 (registration number: ChiCTR2600119037).