TY - JOUR
T1 - Radiomics with Clinical Data and [18F]FDG-PET for Differentiating Between Infected and Non-Infected Intracavitary Vascular (Endo)Grafts
T2 - A Proof-of-Concept Study
AU - van Praagh, Gijs D.
AU - Vos, Francine
AU - Legtenberg, Stijn
AU - Wouthuyzen-Bakker, Marjan
AU - Kouijzer, Ilse J. E.
AU - Aarntzen, Erik H. J. G.
AU - de Vries, Jean-Paul P. M.
AU - Slart, Riemer H. J. A.
AU - Alic, Lejla
AU - Sinha, Bhanu
AU - Saleem, Ben R.
N1 - Publisher Copyright:
© 2025 by the authors.
PY - 2025/8/2
Y1 - 2025/8/2
N2 - Objective: We evaluated the feasibility of a machine-learning (ML) model based on clinical features and radiomics from [18F]FDG PET/CT images to differentiate between infected and non-infected intracavitary vascular grafts and endografts (iVGEI). Methods: Three ML models were developed: one based on pre-treatment criteria to diagnose a vascular graft infection (“MAGIC-light features”), another using radiomics features from diagnostic [18F]FDG-PET scans, and a third combining both datasets. The training set included 92 patients (72 iVGEI-positive, 20 iVGEI-negative), and the external test set included 20 iVGEI-positive and 12 iVGEI-negative patients. The abdominal aorta and iliac arteries in the PET/CT scans were automatically segmented using SEQUOIA and TotalSegmentator and manually adjusted, extracting 96 radiomics features. The best-performing models for the MAGIC-light features and PET-radiomics features were selected from 343 unique models. Most relevant features were combined to test three final models using ROC analysis, accuracy, sensitivity, and specificity. Results: The combined model achieved the highest AUC in the test set (mean ± SD: 0.91 ± 0.02) compared with the MAGIC-light-only model (0.85 ± 0.06) and the PET-radiomics model (0.73 ± 0.03). The combined model also achieved a higher accuracy (0.91 vs. 0.82) than the diagnosis based on all the MAGIC criteria and a comparable sensitivity and specificity (0.70 and 1.00 vs. 0.76 and 0.92, respectively) while providing diagnostic information at the initial presentation. The AUC for the combined model was significantly higher than the PET-radiomics model (p = 0.02 in the bootstrap test), while other comparisons were not statistically significant. Conclusions: This study demonstrated the potential of ML models in supporting diagnostic decision making for iVGEI. A combined model using pre-treatment clinical features and PET-radiomics features showed high diagnostic performance and specificity, potentially reducing overtreatment and enhancing patient outcomes.
AB - Objective: We evaluated the feasibility of a machine-learning (ML) model based on clinical features and radiomics from [18F]FDG PET/CT images to differentiate between infected and non-infected intracavitary vascular grafts and endografts (iVGEI). Methods: Three ML models were developed: one based on pre-treatment criteria to diagnose a vascular graft infection (“MAGIC-light features”), another using radiomics features from diagnostic [18F]FDG-PET scans, and a third combining both datasets. The training set included 92 patients (72 iVGEI-positive, 20 iVGEI-negative), and the external test set included 20 iVGEI-positive and 12 iVGEI-negative patients. The abdominal aorta and iliac arteries in the PET/CT scans were automatically segmented using SEQUOIA and TotalSegmentator and manually adjusted, extracting 96 radiomics features. The best-performing models for the MAGIC-light features and PET-radiomics features were selected from 343 unique models. Most relevant features were combined to test three final models using ROC analysis, accuracy, sensitivity, and specificity. Results: The combined model achieved the highest AUC in the test set (mean ± SD: 0.91 ± 0.02) compared with the MAGIC-light-only model (0.85 ± 0.06) and the PET-radiomics model (0.73 ± 0.03). The combined model also achieved a higher accuracy (0.91 vs. 0.82) than the diagnosis based on all the MAGIC criteria and a comparable sensitivity and specificity (0.70 and 1.00 vs. 0.76 and 0.92, respectively) while providing diagnostic information at the initial presentation. The AUC for the combined model was significantly higher than the PET-radiomics model (p = 0.02 in the bootstrap test), while other comparisons were not statistically significant. Conclusions: This study demonstrated the potential of ML models in supporting diagnostic decision making for iVGEI. A combined model using pre-treatment clinical features and PET-radiomics features showed high diagnostic performance and specificity, potentially reducing overtreatment and enhancing patient outcomes.
U2 - 10.3390/diagnostics15151944
DO - 10.3390/diagnostics15151944
M3 - Article
SN - 2075-4418
VL - 15
JO - Diagnostics
JF - Diagnostics
IS - 15
M1 - 1944
ER -