Related Experiment Video
Updated: Aug 5, 2026
Gene Regulation and Targeted Therapy in Gastric Cancer Peritoneal Metastasis: Radiological Findings from Dual Energy CT and PET/CT
Published on: January 22, 2018
Automated Deauville Score computation from baseline [¹⁸F]FDG PET/CT predicts progression-free survival in multiple
Sara Peluso1,2, Stefano Polizzi3, Lisa Pagnini4,5
1Department of Medical and Surgical Sciences, University of Bologna, Bologna, 40138, Italy. sara.peluso5@unibo.it.
Purpose:
Deauville Score (DS) assessment from [18F]FDG PET/CT in multiple myeloma (MM) relies on visual interpretation, limiting reproducibility. This study aimed to develop an automated pipeline for standardised DS computation, evaluate the prognostic value of DS at five anatomical sites, and predict progression-free survival (PFS) by integrating DS with copy number alterations (CNA) and clinical variables.
Methods:
A retrospective cohort of 165 newly diagnosed MM patients with baseline FDG PET/CT, CNA profiling, and blood tests was analysed. An automated pipeline computed DS fully automatically for vertebral bone marrow (BM) and long bones (LB), and semi-automatically for focal (FL), paramedullary (PM), and extramedullary (EM) lesions. DS were subdivided into absent (1), low (2-3), and high (4-5) groups and compared via log-rank test. A penalised Cox model with 12 covariates (five DS, three CNAs, haemoglobin, platelet count, age, sex) was evaluated via nested cross-validation for PFS prediction. For inference on individual prognostic contributions, an unpenalised multivariable Cox model was fitted on the full cohort.
Results:
In univariate analyses, high LB, PM and EM DS were significantly associated with shorter PFS. The penalised Cox model achieved a C-index of 0.710 [95% CI: 0.689-0.732] in predicting the risk of progression. In the multivariable analysis, age, haemoglobin, BM DS, PM DS and amp(1q) were identified as independent prognostic factors.
Conclusion:
Automated DS computation from baseline FDG PET/CT is feasible and, combined with genomic and clinical data, enables a reproducible multimodal approach to prognostic stratification in MM. The pipeline for DS computation is publicly available as an open-source tool (autoDS-PET) at https://github.com/Sara-Peluso/autoDS-PET .
Insights
An automated pipeline for Deauville Score (DS) computation in multiple myeloma (MM) improves reproducibility. Integrating DS with genomic and clinical data enhances progression-free survival (PFS) prediction, identifying key prognostic factors.
Area of Science:
- Nuclear medicine imaging
- Genomics
- Hematologic oncology
Background:
- Deauville Score (DS) assessment in [18F]FDG PET/CT for multiple myeloma (MM) is subjective and lacks reproducibility.
- Developing standardized, automated methods for DS computation is crucial for reliable prognostic evaluation.
Purpose of the Study:
- To create an automated pipeline for standardized DS computation in MM.
- To assess the prognostic significance of DS across five anatomical sites.
- To predict progression-free survival (PFS) by integrating DS with copy number alterations (CNA) and clinical data.
Main Methods:
- Retrospective analysis of 165 newly diagnosed MM patients with baseline FDG PET/CT, CNA profiling, and blood tests.
- Developed an automated/semi-automated pipeline for DS computation at vertebral bone marrow, long bones, focal, paramedullary, and extramedullary lesions.
- Utilized a penalised Cox model integrating five DS measures, three CNAs, and clinical variables for PFS prediction.
Main Results:
- High DS in long bones, paramedullary, and extramedullary lesions were significantly associated with shorter PFS.
- The predictive model achieved a C-index of 0.710 for progression risk.
- Independent prognostic factors identified include age, haemoglobin, bone marrow DS, paramedullary DS, and amp(1q).
Conclusions:
- Automated DS computation via FDG PET/CT is feasible and enhances reproducibility in MM.
- A multimodal approach combining automated DS, genomic, and clinical data offers reproducible prognostic stratification.
- The autoDS-PET pipeline is available as an open-source tool.
