Characterization of Adrenal Lesions on Unenhanced MRI Using Texture Analysis: A Machine‐Learning Approach

• Published in: Journal of magnetic resonance imaging Vol. 48; no. 1; pp. 198 - 204
• Main Authors: Romeo, Valeria, Maurea, Simone, Cuocolo, Renato, Petretta, Mario, Mainenti, Pier Paolo, Verde, Francesco, Coppola, Milena, Dell'Aversana, Serena, Brunetti, Arturo
• Format: Journal Article
• Language: English
• Published: United States Wiley Subscription Services, Inc 01.07.2018
• Subjects: adrenal glands; Artificial intelligence; Classifiers; Diagnostic systems; Feature extraction; Field strength; Image acquisition; Learning algorithms; Lesions; Machine learning; Magnetic resonance imaging; Medical imaging; Neuroendocrine tumors; Object recognition; Parameters; Pattern recognition; Population (statistical); Population studies; Statistical analysis; Statistical tests; Texture; texture analysis; magnetic resonance imaging; machine learning; adrenal glands; texture analysis

Background Adrenal adenomas (AA) are the most common benign adrenal lesions, often characterized based on intralesional fat content as either lipid‐rich (LRA) or lipid‐poor (LPA). The differentiation of AA, particularly LPA, from nonadenoma adrenal lesions (NAL) may be challenging. Texture analysis...