Development and validation of a radiomic model for the diagnosis of dopaminergic denervation on [18F]FDOPA PET/CT

Abstract

Purpose FDOPA PET shows good performance for the diagnosis of striatal dopaminergic denervation, making it a valuable tool for the differential diagnosis of Parkinsonism. Textural features are image biomarkers that could potentially improve the early diagnosis and monitoring of neurodegenerative parkinsonian syndromes. We explored the performances of textural features for binary classification of FDOPA scans. Methods We used two FDOPA PET datasets: 443 scans for feature selection, and 100 scans from a different PET/CT system for model testing. Scans were labelled according to expert interpretation (dopaminergic denervation versus no dopaminergic denervation). We built LASSO logistic regression models using 43 biomarkers including 32 textural features. Clinical data were also collected using a shortened UPDRS scale. Results The model built from the clinical data alone had a mean area under the receiver operating characteristics (AUROC) of 63.91. Conventional imaging features reached a maximum score of 93.47 but the addition of textural features significantly improved the AUROC to 95.73 (p < 0.001), and 96.10 (p < 0.001) when limiting the model to the top three features: GLCM_Correlation, Skewness and Compacity. Testing the model on the external dataset yielded an AUROC of 96.00, with 95% sensitivity and 97% specificity. GLCM_Correlation was one of the most independent features on correlation analysis, and systematically had the heaviest weight in the classification model. Conclusion A simple model with three radiomic features can identify pathologic FDOPA PET scans with excellent sensitivity and specificity. Textural features show promise for the diagnosis of parkinsonian syndromes.

Relevance of 18F-DOPA visual and semi-quantitative PET metrics for the diagnostic of Parkinson disease in clinical practice: a machine learning-based inference study

“…In this context, automated image processing workflows have emerged, and could facilitate the interpretation of physicians in daily practice. Motivated by its rational in high spatially resolved morphological imaging, radiomics gradually invades nuclear imaging of oncological and non-oncological diseases, including Parkinsonian syndromes [ 40 – 44 ]. In their very recent paper, Comte et al trained and validated a logistic regression model with L1 regularization to identify dopaminergic denervation on 18 F-DOPA PET/CT [ 44 ].…”

“…Motivated by its rational in high spatially resolved morphological imaging, radiomics gradually invades nuclear imaging of oncological and non-oncological diseases, including Parkinsonian syndromes [ 40 – 44 ]. In their very recent paper, Comte et al trained and validated a logistic regression model with L1 regularization to identify dopaminergic denervation on 18 F-DOPA PET/CT [ 44 ]. Among 43 first and higher-orders parameters, three textural features were found to identify abnormal 18 F-DOPA PET almost as well as a nuclear imaging expert, considered here as the gold standard and study outcome.…”

“…In this context, automated image processing workflows have emerged, and could facilitate the interpretation of physicians in daily practice. Motivated by its rational in high spatially resolved morphological imaging, radiomics gradually invades nuclear imaging of oncological and non-oncological diseases, including Parkinsonian syndromes [40][41][42][43][44].…”

“…In their very recent paper, Comte et al trained and validated a logistic regression model with L1 regularization to identify dopaminergic denervation on 18 F-DOPA PET/ CT [44]. Among 43 first and higher-orders parameters, three textural features were found to identify abnormal 18 F-DOPA PET almost as well as a nuclear imaging expert, considered here as the gold standard and study outcome.…”

Towards an Automated Approach to the Semi-Quantification of [18F]F-DOPA PET in Pediatric-Type Diffuse Gliomas

“…Approaches for analyzing [ 18 F]F-DOPA PET/CT images, either semi-automated or fully automated, have been developed for use in Parkinson's disease, where they can benefit from prior knowledge of the target and reference regions. A variety of techniques can be employed, including the extraction of radiomic features from the image, the application of classical machine learning methods, and the calculation of the striatal-to-occipital ratio [21,22]. Defining target and normalization regions in oncological PET imaging is a challenging task due to the inherent variability and the methodological drawbacks of common manual or threshold-based procedures (e.g., time consumption, low reproducibility, scanner type, reconstruction algorithm, and image noise [23]).…”