Lymphoma
Conditions
Interventions
Gold Standard:The reference standard in this study was independently determined by two senior physicians who were dual-certified in radiology and nuclear medicine and had extensive experience in inter
Index test:The index test in this study is a deep learning–based denoising low-dose CT image processing method, in which simulated quarter-dose CT images are denoised using a deep learning model and s
Sponsors
The Central Hospital of Xiangtan
Eligibility
Sex/Gender
All
Inclusion criteria
Inclusion criteria: 1. Patients with lymphoma who underwent whole-body [18F]FDG PET/CT examinations; 2. Imaging data that can be fully retrieved from the PACS system; 3. Availability of both baseline PET/CT and at least one follow-up PET/CT examination (applicable only to patients included in the clinical evaluation).
Exclusion criteria
Exclusion criteria: 1. Missing or incomplete PET or CT imaging data; 2. Images with severe artifacts or clearly insufficient quality that impair lesion detection, disease staging, or treatment response assessment; 3. Insufficient clinical or imaging information to establish reference standards for diagnosis, staging, or treatment response evaluation.
Design outcomes
Primary
| Measure | Time frame |
|---|---|
| Root Mean Square Error, Structural Similarity Index, and Peak Signal-to-Noise Ratio;Sensitivity for hypermetabolic lesions;Specificity for hypermetabolic lesions;ROC-AUC for hypermetabolic lesions; | — |
Countries
China
Contacts
Public ContactMantian Liao
The Central Hospital of Xiangtan
Outcome results
None listed