ECE2024 Eposter Presentations Adrenal and Cardiovascular Endocrinology (155 abstracts)
Radiomics for immunohistochemistry prediction in pheochromocytoma: a pilot study
Lorenzo Tucci 1,2 , Antonio De Leo 1,3 , Giulio Vara 4,5 , Kimberly Coscia 1,2 , Saverio Selva 6 , Claudio Ricci 1,6 , Laura Alberici 6 , Caterina Balacchi 7 , Donatella Santini 3 , Valentina Vicennati 1,2 , Uberto Pagotto 1,2 , Cristina Mosconi 1,7 , Giovanni Tallini 1,3 & Guido Di Dalmazi 1,2
1Alma Mater Studiorum - Bologna University, Medical and Surgical Sciences Department, Bologna, Italy; 2IRCCS S. Orsola-Malpighi Polyclinic, Endocrinology and Diabetes care and Prevention Unit, Bologna, Italy; 3IRCCS S. Orsola-Malpighi Polyclinic, Anatomic Pathology Unit, Bologna, Italy; 4Alma Mater Studiorum - Bologna University, Biomedical and Neuromotor Sciences Department, Bologna, Italy; 5Civil Hospital "Umberto I", Radiodiagnostic Unit, Lugo, Italy; 6IRCCS S. Orsola-Malpighi Polyclinic, Division of Pancreatic and Endocrine Surgery, Bologna, Italy; 7IRCCS S. Orsola-Malpighi Polyclinic, Diagnostic and interventional abdominal-pelvic radiology Unit, Bologna
Background: Radiomics, or texture analysis, is gaining growing interest for its high prediction performances, mainly for clinical purposes. Radiomics application for pheochromocytoma immunohistochemistry (IHC) and molecular biology prediction is still unexplored.
Aim: To evaluate radiomics ability to predict pheochromocytoma IHC.
Methods: We retrospectively enrolled 38 pheochromocytoma who underwent surgery at Sant’Orsola-Malpighi Polyclinic since 1999 to 2023 with availability of pre-surgery basal computerized tomography (CT) scan and post-surgery IHC results on formalin-fixed, paraffin-embed tissues. IHC for Succinate Dehydrogenase Subunit A (SDHA), B (SDHB) and Somatostatin Receptor 2 (SSTR2A) was performed using Ventana Benchmark Ultra (©Roche Ventana Medical System, USA). IHC scores ranged from 0 (negative) to 3 (strongly positive). Texture analysis was performed on CT basal scan with LifeX software (version 7.2.0, ©LITO, France). Logistic regression was used to assess texture analysis ability to predict IHC scores. Sensitivity, specificity, negative (NPV) and positive predictive value (PPV) of significant predictors were estimated through receiver operating characteristic curve analysis.
Results: 0 patients displayed SDHA negativity, 5 patients displayed SDHB negativity, 27 patients displayed SSTR2A IHC positivity. A model including Maximum Grey Level and Strength predicted SDHB negativity (Odds Ratio (OR): 2.743; 95% Confidence Interval (CI): 1.544 – 4.873; P<0.001) with sensitivity 100.0%, specificity 60.6%, NPV 100.0%, PPV 28.0%. A model including Zone Percentage predicted SSTR2A positivity (OR: 2.718; CI: 1.435 – 5.149; P<0.001) with sensitivity 77.8%, specificity 80.0%, NPV 57.0%, PPV 91%. A model including Joint Maximum predicted SSTR2A score equal to 3 (OR: 2.718; CI: 1.509 – 4.896; P<0.001) with sensitivity 87.5%, specificity 65.5%, NPV 95.0%, PPV 41.2%. A model including Maximum Grey Level and Strength predicted the combination of SDHB negativity and SSTR2A positivity (OR: 2.689; CI: 1.439 – 5.024; P<0.001) with sensitivity 75.0%, specificity 93.0%, NPV 96.9%, PPV 75.0%.
Conclusion: Radiomics has shown good performance in predict pheochromocytoma IHC. These findings, if confirmed with wider and prospective studies, may open a new scenario for radiomics. Hence, in the context of pheochromocytoma, texture analysis may reflect pathological molecular pathways, absence or presence of somatic mutations and the individuation and selection of potentially sensitive tumours to nuclear medicine test or treatment.
Article tools
My recent searches
My recently viewed abstracts
Authors
Endocrine Abstracts
ISSN 1470-3947 (print) | ISSN 1479-6848 (online)
© Bioscientifica 2024 |
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