ECEESPE2025 Poster Presentations Pituitary, Neuroendocrinology and Puberty (162 abstracts)
MRI-based radiomics of the pineal gland in girls does not provide informative data for the diagnosis of central precocious puberty
Anna-Mariia Shulhai 1 , Maddalena Petraroli 2 , Michele Maddalo 3 , Marco Masetti 4 , Francesca Ormitti 5 , Alice Fulgoni 1 , Benedetta Piccolo 2 , Claudia Turco 2 , Nicola Sverzellati 6 , Caterina Ghetti 3 , Susanna Esposito 1 & Maria Street 1
1University of Parma, Unit of Paediatrics, University Hospital of Parma, Department of Medicine and Surgery, Parma, Italy; 2Unit of Paediatrics, University Hospital of Parma, Parma, Italy, Parma, Italy; 3University Hospital of Parma, Medical Physics Unit, Parma, Italy; 4University of Parma, Medicine and Surgery, Parma, Italy; 5University Hospital of Parma, Neuroradiology Unit, Parma, Italy; 6University of Parma, Unit of Radiological Sciences, University Hospital of Parma, Department of Medicine and Surgery, Parma, Italy
JOINT1538
Introduction: The diagnostic gold standard for central precocious puberty (CPP) is the gonadotropin-releasing hormone (GnRH) stimulation test. Additionally, magnetic resonance imaging (MRI) of the brain and of the hypothalamus-pituitary region is required to exclude central organic causes. Recent technological advancements have contributed to the development of a new approach in medical imaging called radiomics. Our recent study has shown that radiomics of the pituitary gland is a promising tool for diagnosing CPP. The role of the pineal gland in the onset of puberty is long debated with conflicting Results.
Aim: Herewith, we investigated the features of the pineal gland in relationship with the onset of puberty, using radiomics, with the aim to assess whether there are any specific changes that could assist physicians in the diagnostic workup of CPP.
Methods: Forty-five girls with a confirmed diagnosis of CPP and 47 pre-pubertal, age- and sex-matched subjects (control group) were retrospectively enrolled. Two readers (R1, R2) with different levels of expertise in pediatric neuroradiology blindly segmented the pineal gland on MRI studies for radiomic features (RFs) calculation and performed a manual evaluation of the number and the diameter of pineal cysts. Cross-validated linear discriminant analysis was used to develop both a radiomic model and a reference model for each reader based on the pineal cysts features. Radiomics was evaluated in terms of 1) predictive performances (metrics: ROC-AUC, accuracy, sensitivity, and specificity); and 2) reliability of predictors between readers (metric: intraclass correlation coefficient, ICC). Finally, the correlation between cysts features and basal/peak gonadotropin levels was also investigated.
Results: Two radiomic features were identified as the most predictive of CPP for both readers. However, these features were not the same for R1 and R2 readers, and their values showed poor inter-reader reliability. Unpromising performances in the validation set were obtained for the radiomics of the pineal gland (ROC-AUC of 0.64 for R1 and 0.59 for R2). These results were significantly lower than the findings we had found for the pituitary gland, which achieved ROC-AUC of 0.81 and 0.76 for R1 and R2, respectively. Similarly, the reference model based on pineal cysts features demonstrated poor performance (ROC-AUC = 0.52, both readers). No significant correlations (α=0.05) between cysts features and basal/peak gonadotropin levels were observed.
Conclusion: Radiomic features of the pineal gland in girls with CPP have shown no supporting evidence of differences compared with prepubertal controls.
Volume 110
Article tools
My recent searches
My recently viewed abstracts
Authors
Endocrine Abstracts
ISSN 1470-3947 (print) | ISSN 1479-6848 (online)
© Bioscientifica 2025 |
Privacy policy |
Cookie settings
BiosciAbstracts
Bioscientifica Abstracts is the gateway to a series of products that provide a permanent, citable record of abstracts for biomedical and life science conferences.
Find out more