T-NK Cell Lymphoma
Conditions
Keywords
T-NK cell Lymphoma, PET/CT, Diferential Diagnosis, Efficacy Prediction, Prognosis Prediction
Brief summary
Based on the PET/CT imaging data of patients with T-NK cell lymphoma, machine learning and deep learning methods are used to extract imaging features, establish a T-NK cell lymphoma prediction model, and provide more scientific and accurate prognosis prediction for the clinic.
Detailed description
This study adopts a multicenter retrospective cohort study design，we provided PET/CT of 200 patients with T-NK cell lymphoma as an external validation set for model validation.
Interventions
None listed
Sponsors
West China Hospital
Ruijin Hospital
Study design
Observational model
OTHER
Time perspective
RETROSPECTIVE
Eligibility
Sex/Gender
ALL
Age
18 Years to 75 Years
Healthy volunteers
No
Inclusion criteria
1\. Pathological histology confirmed as T-NK Cell Lymphoma; 2.18F-FDG PET/CT examination before treatment; 3. Using modern best practice treatment options; 4. Complete clinicopathological and follow-up data were obtained.
Exclusion criteria
1. The patient had previously received antitumor therapy; 2. The patient had a history of other tumors; 3. Incomplete clinical information or imaging data; 4. Concomitant other malignant tumors.
Design outcomes
Primary
| Measure | Time frame | Description |
|---|---|---|
| Evaluation the value of Artificial Intelligence-based 18F-FDG PET/CT of T-NK Cell Lymphoma | Within 1 week of enrollment and after 3 months treatment | The Value of Artificial Intelligence-based 18F-FDG PET/CT in Diferential Diagnosis, Efficacy Prediction and Prognosis Prediction of T-NK Cell Lymphoma |
Secondary
| Measure | Time frame | Description |
|---|---|---|
| Progress free survival | 3 years | Progress free survival |
| Overall survival | 3 years | Overall survival |
Countries
China
Contacts
Primary ContactGuo rui Deputy director
Outcome results
None listed