F Torresan1, F Crimì2, F Ceccato3, F Zavan2, M Barbot3, C Lacognata4, R Motta2, C Armellin1, C Scaroni3, E Quaia2, C Campi5, M Iacobone1. 1. Endocrine Surgery Unit, Department of Surgery, Oncology and Gastroenterology DISCOG, University Hospital of Padova, Padua, Italy. 2. Radiology Unit, Department of Medicine DIMED, University Hospital of Padua, Padua, Italy. 3. Endocrinology Unit, Department of Medicine DIMED, University Hospital of Padua, Padua, Italy. 4. Radiology Department, University Hospital of Padua, Padua, Italy. 5. Department of Mathematics 'Tullio Levi-Civita', University of Padua, Padua, Italy.
Abstract
BACKGROUND: The main challenge in the management of indeterminate incidentally discovered adrenal tumours is to differentiate benign from malignant lesions. In the absence of clear signs of invasion or metastases, imaging techniques do not always precisely define the nature of the mass. The present pilot study aimed to determine whether radiomics may predict malignancy in adrenocortical tumours. METHODS: CT images in unenhanced, arterial, and venous phases from 19 patients who had undergone resection of adrenocortical tumours and a cohort who had undergone surveillance for at least 5 years for incidentalomas were reviewed. A volume of interest was drawn for each lesion using dedicated software, and, for each phase, first-order (histogram) and second-order (grey-level colour matrix and run-length matrix) radiological features were extracted. Data were revised by an unsupervised machine learning approach using the K-means clustering technique. RESULTS: Of operated patients, nine had non-functional adenoma and 10 carcinoma. There were 11 patients in the surveillance group. Two first-order features in unenhanced CT and one in arterial CT, and 14 second-order parameters in unenhanced and venous CT and 10 second-order features in arterial CT, were able to differentiate adrenocortical carcinoma from adenoma (P < 0.050). After excluding two malignant outliers, the unsupervised machine learning approach correctly predicted malignancy in seven of eight adrenocortical carcinomas in all phases. CONCLUSION: Radiomics with CT texture analysis was able to discriminate malignant from benign adrenocortical tumours, even by an unsupervised machine learning approach, in nearly all patients.
BACKGROUND: The main challenge in the management of indeterminate incidentally discovered adrenal tumours is to differentiate benign from malignant lesions. In the absence of clear signs of invasion or metastases, imaging techniques do not always precisely define the nature of the mass. The present pilot study aimed to determine whether radiomics may predict malignancy in adrenocortical tumours. METHODS: CT images in unenhanced, arterial, and venous phases from 19 patients who had undergone resection of adrenocortical tumours and a cohort who had undergone surveillance for at least 5 years for incidentalomas were reviewed. A volume of interest was drawn for each lesion using dedicated software, and, for each phase, first-order (histogram) and second-order (grey-level colour matrix and run-length matrix) radiological features were extracted. Data were revised by an unsupervised machine learning approach using the K-means clustering technique. RESULTS: Of operated patients, nine had non-functional adenoma and 10 carcinoma. There were 11 patients in the surveillance group. Two first-order features in unenhanced CT and one in arterial CT, and 14 second-order parameters in unenhanced and venous CT and 10 second-order features in arterial CT, were able to differentiate adrenocortical carcinoma from adenoma (P < 0.050). After excluding two malignant outliers, the unsupervised machine learning approach correctly predicted malignancy in seven of eight adrenocortical carcinomas in all phases. CONCLUSION: Radiomics with CT texture analysis was able to discriminate malignant from benign adrenocortical tumours, even by an unsupervised machine learning approach, in nearly all patients.
Authors: Michael A Blake; Mannudeep K Kalra; Ann T Sweeney; Brian C Lucey; Michael M Maher; Dushyant V Sahani; Elkan F Halpern; Peter R Mueller; Peter F Hahn; Giles W Boland Journal: Radiology Date: 2005-12-21 Impact factor: 11.105
Authors: Lisa M Ho; Ehsan Samei; Maciej A Mazurowski; Yuese Zheng; Brian C Allen; Rendon C Nelson; Daniele Marin Journal: AJR Am J Roentgenol Date: 2019-01-08 Impact factor: 3.959
Authors: S Bovio; A Cataldi; G Reimondo; P Sperone; S Novello; A Berruti; P Borasio; C Fava; L Dogliotti; G V Scagliotti; A Angeli; M Terzolo Journal: J Endocrinol Invest Date: 2006-04 Impact factor: 4.256
Authors: M Terzolo; A Stigliano; I Chiodini; P Loli; L Furlani; G Arnaldi; G Reimondo; A Pia; V Toscano; M Zini; G Borretta; E Papini; P Garofalo; B Allolio; B Dupas; F Mantero; A Tabarin Journal: Eur J Endocrinol Date: 2011-04-06 Impact factor: 6.664
Authors: A De Leo; G Vara; G Di Dalmazi; C Mosconi; A Paccapelo; C Balacchi; V Vicennati; L Tucci; U Pagotto; S Selva; C Ricci; L Alberici; F Minni; C Nanni; F Ambrosi; D Santini; R Golfieri Journal: J Endocrinol Invest Date: 2022-06-10 Impact factor: 5.467