Characterization of Adrenal Lesions on Unenhanced MRI Using Texture Analysis: A Machine-Learning Approach(61 visite) Romeo V, Maurea S, Cuocolo R, Petretta M, Mainenti PP, Verde F, Coppola M, Dell'Aversana S, Brunetti A
Impact factor: 1.302, Impact factor a 5 anni: 3.007
Url: Non disponibile.
Parole chiave: Adrenal Glands, Machine Learning, Magnetic Resonance Imaging, Texture Analysis,
Affiliazioni:
*** IBB - CNR *** Department of Advanced Biomedical Sciences, University of Naples "Federico II,", Naples, Italy., Department of Translational Medical Sciences, University of Naples "Federico II,", Naples, Italy., Institute of Biostructures and Bioimaging of the National Research Council (CNR), Naples, Italy.,
Riferimenti:
Non disponibile.
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 (TA) can extract quantitative parameters from MR images. Machine learning is a technique for recognizing patterns that can be applied to medical images by identifying the best combination of TA features to create a predictive model for the diagnosis of interest. PURPOSE/HYPOTHESIS: To assess the diagnostic efficacy of TA-derived parameters extracted from MR images in characterizing LRA, LPA, and NAL using a machine-learning approach. STUDY TYPE: Retrospective, observational study. POPULATION/SUBJECTS/PHANTOM/SPECIMEN/ANIMAL MODEL: Sixty MR examinations, including 20 LRA, 20 LPA, and 20 NAL. FIELD STRENGTH/SEQUENCE: Unenhanced T1 -weighted in-phase (IP) and out-of-phase (OP) as well as T2 -weighted (T2 -w) MR images acquired at 3T. ASSESSMENT: Adrenal lesions were manually segmented, placing a spherical volume of interest on IP, OP, and T2 -w images. Different selection methods were trained and tested using the J48 machine-learning classifiers. STATISTICAL TESTS: The feature selection method that obtained the highest diagnostic performance using the J48 classifier was identified; the diagnostic performance was also compared with that of a senior radiologist by means of McNemar's test. RESULTS: A total of 138 TA-derived features were extracted; among these, four features were selected, extracted from the IP (Short_Run_High_Gray_Level_Emphasis), OP (Mean_Intensity and Maximum_3D_Diameter), and T2 -w (Standard_Deviation) images; the J48 classifier obtained a diagnostic accuracy of 80%. The expert radiologist obtained a diagnostic accuracy of 73%. McNemar's test did not show significant differences in terms of diagnostic performance between the J48 classifier and the expert radiologist. DATA CONCLUSION: Machine learning conducted on MR TA-derived features is a potential tool to characterize adrenal lesions. LEVEL OF EVIDENCE: 4 Technical Efficacy: Stage 2 J. Magn. Reson. Imaging 2018.
Antonini A, Vitale C, Barone P, Cilia R, Righini A, Bonuccelli U, Abbruzzese G, Ramat S, Petrone A, Quatrale R, Marconi R, Ceravolo R, Stefani A, Lopiano L, Zappia M, Capus L, Morgante L, Tamma F, Tinazzi M, Colosimo C, Guerra UP, Valzania F, Fagioli G, Distefano A, Bagnato A, Feggi L, Anna S, Maria Teresa Rosaria De Cr, Nobili F, Mazzuca N, Baldari S, Eleopra R, Bestetti A, Benti R, Varrone A, Volterrani D, Massa R, Stocchi F, Schillaci O, Dore F, Zibetti M, Castellano G, Battista SG, Giorgetti G * The relationship between cerebral vascular disease and parkinsonism: The VADO study(163 visite) Parkinsonism Relat Disord (ISSN: 1353-8020, 1873-5126, 1873-5126electronic), 2012; 18(6): 775-780. Impact Factor:3.274 DettagliEsporta in BibTeXEsporta in EndNote
Malvindi MA, Greco A, Conversano F, Figuerola A, Corti M, Bonora M, Lascialfari A, Doumari HA, Moscardini M, Cingolani R, Gigli G, Casciaro S, Pellegrino T, Ragusa A * MR Contrast Agents(122 visite) Small Animal Imaging, 2011 Jul 8; 21(13): 2548-2555. Impact Factor:1.784 DettagliEsporta in BibTeXEsporta in EndNote
Ntziachristos V, Cuénod CA, Fournier L, Balvay D, Pradel C, Siauve N, Clement O, Jouannot E, Lucidarme O, Vecchio SD, Salvatore M, Law B, Tung C-H, Jain RK, Fukumura D, Munn LL, Brown EB, Schellenberger E, Montet X, Weissleder R, Clerck ND, Postnov A * Tumor Imaging(124 visite) Textbook Of In Vivo Imaging In Vertebrates (ISSN: 9780-4700), 2007 Jul 16; 1: 277-309. Impact Factor:1.148 DettagliEsporta in BibTeXEsporta in EndNote
Hesse B, Tagil K, Cuocolo A, Anagnostopoulos C, Bardies M, Bax J, Bengel F, Busemann Sokole E, Davies G, Dondi M, Edenbrandt L, Franken P, Kjaer A, Knuuti J, Lassmann M, Ljungberg M, Marcassa C, Marie PY, Mckiddie F, O'connor M, Prvuolovich E, Underwood R * 3. 0 T perfusion MR imaging(305 visite) Rivista Di Neuroradiologia (ISSN: 1120-9976), 2004; 17(6): 807-812. Impact Factor:0.023 DettagliEsporta in BibTeXEsporta in EndNote
330 Records (308 escludendo Abstract e Conferenze). Impact factor totale: 1044.791 (995.941 escludendo Abstract e Conferenze). Impact factor a 5 anni totale: 1130.212 (1077.351 escludendo Abstract e Conferenze).
ibb.cnr.it