Susanna Nuvoli1, Angela Spanu2, Mario Luca Fravolini3, Francesco Bianconi3, Silvia Cascianelli3, Giuseppe Madeddu2, Barbara Palumbo4. 1. Unit of Nuclear Medicine, Department of Medicine, Surgical and Experimental Science, University of Sassari, Viale San Pietro 8, 07100, Sassari, Italy. snuvoli@uniss.it. 2. Unit of Nuclear Medicine, Department of Medicine, Surgical and Experimental Science, University of Sassari, Viale San Pietro 8, 07100, Sassari, Italy. 3. Department of Engineering, University of Perugia, Perugia, Italy. 4. Section of Nuclear Medicine and Health Physics, Department of Surgical and Biomedical Sciences, University of Perugia, Perugia, Italy.
Abstract
PURPOSE: To provide reliable and reproducible heart/mediastinum (H/M) ratio cut-off values for parkinsonian disorders using two machine learning techniques, Support Vector Machines (SVM) and Random Forest (RF) classifier, applied to [123I]MIBG cardiac scintigraphy. PROCEDURES: We studied 85 subjects, 50 with idiopathic Parkinson's disease, 26 with atypical Parkinsonian syndromes (P), and 9 with essential tremor (ET). All patients underwent planar early and delayed cardiac scintigraphy after [123I]MIBG (111 MBq) intravenous injection. Images were evaluated both qualitatively and quantitatively; the latter by the early and delayed H/M ratio obtained from regions of interest (ROIt1 and ROIt2) drawn on planar images. SVM and RF classifiers were finally used to obtain the correct cut-off value. RESULTS: SVM and RF produced excellent classification performances: SVM classifier achieved perfect classification and RF also attained very good accuracy. The better cut-off for H/M value was 1.55 since it remains the same for both ROIt1 and ROIt2. This value allowed to correctly classify PD from P and ET: patients with H/M ratio less than 1.55 were classified as PD while those with values higher than 1.55 were considered as affected by parkinsonism and/or ET. No difference was found when early or late H/M ratio were considered separately thus suggesting that a single early evaluation could be sufficient to obtain the final diagnosis. CONCLUSIONS: Our results evidenced that the use of SVM and CT permitted to define the better cut-off value for H/M ratios both in early and in delayed phase thus underlining the role of [123I]MIBG cardiac scintigraphy and the effectiveness of H/M ratio in differentiating PD from other parkinsonism or ET. Moreover, early scans alone could be used for a reliable diagnosis since no difference was found between early and late. Definitely, a larger series of cases is needed to confirm this data.
PURPOSE: To provide reliable and reproducible heart/mediastinum (H/M) ratio cut-off values for parkinsonian disorders using two machine learning techniques, Support Vector Machines (SVM) and Random Forest (RF) classifier, applied to [123I]MIBG cardiac scintigraphy. PROCEDURES: We studied 85 subjects, 50 with idiopathic Parkinson's disease, 26 with atypical Parkinsonian syndromes (P), and 9 with essential tremor (ET). All patients underwent planar early and delayed cardiac scintigraphy after [123I]MIBG (111 MBq) intravenous injection. Images were evaluated both qualitatively and quantitatively; the latter by the early and delayed H/M ratio obtained from regions of interest (ROIt1 and ROIt2) drawn on planar images. SVM and RF classifiers were finally used to obtain the correct cut-off value. RESULTS: SVM and RF produced excellent classification performances: SVM classifier achieved perfect classification and RF also attained very good accuracy. The better cut-off for H/M value was 1.55 since it remains the same for both ROIt1 and ROIt2. This value allowed to correctly classify PD from P and ET: patients with H/M ratio less than 1.55 were classified as PD while those with values higher than 1.55 were considered as affected by parkinsonism and/or ET. No difference was found when early or late H/M ratio were considered separately thus suggesting that a single early evaluation could be sufficient to obtain the final diagnosis. CONCLUSIONS: Our results evidenced that the use of SVM and CT permitted to define the better cut-off value for H/M ratios both in early and in delayed phase thus underlining the role of [123I]MIBG cardiac scintigraphy and the effectiveness of H/M ratio in differentiating PD from other parkinsonism or ET. Moreover, early scans alone could be used for a reliable diagnosis since no difference was found between early and late. Definitely, a larger series of cases is needed to confirm this data.
Entities:
Keywords:
Automated classification techniques; Heart/mediastinum ratio cut-off value; Parkinson disease; Parkinsonism; Random Forest classifier; Support vector machines; [123I]MIBG cardiac scintigraphy
Authors: A Berardelli; G K Wenning; A Antonini; D Berg; B R Bloem; V Bonifati; D Brooks; D J Burn; C Colosimo; A Fanciulli; J Ferreira; T Gasser; F Grandas; P Kanovsky; V Kostic; J Kulisevsky; W Oertel; W Poewe; J-P Reese; M Relja; E Ruzicka; A Schrag; K Seppi; P Taba; M Vidailhet Journal: Eur J Neurol Date: 2013-01 Impact factor: 6.089
Authors: Ronald B Postuma; Werner Poewe; Irene Litvan; Simon Lewis; Anthony E Lang; Glenda Halliday; Christopher G Goetz; Piu Chan; Elizabeth Slow; Klaus Seppi; Eva Schaffer; Silvia Rios-Romenets; Taomian Mi; Corina Maetzler; Yuan Li; Beatrice Heim; Ian O Bledsoe; Daniela Berg Journal: Mov Disord Date: 2018-08-25 Impact factor: 10.338
Authors: Charles H Adler; Thomas G Beach; Joseph G Hentz; Holly A Shill; John N Caviness; Erika Driver-Dunckley; Marwan N Sabbagh; Lucia I Sue; Sandra A Jacobson; Christine M Belden; Brittany N Dugger Journal: Neurology Date: 2014-06-27 Impact factor: 9.910
Authors: Wendy R Galpern; Jacqueline Corrigan-Curay; Anthony E Lang; Jeffrey Kahn; Danilo Tagle; Roger A Barker; Thomas B Freeman; Christopher G Goetz; Karl Kieburtz; Scott Y H Kim; Steven Piantadosi; Amy Comstock Rick; Howard J Federoff Journal: Lancet Neurol Date: 2012-07 Impact factor: 44.182
Authors: Gregor K Wenning; Felix Geser; Florian Krismer; Klaus Seppi; Susanne Duerr; Sylvia Boesch; Martin Köllensperger; Georg Goebel; Karl P Pfeiffer; Paolo Barone; Maria Teresa Pellecchia; Niall P Quinn; Vasiliki Koukouni; Clare J Fowler; Anette Schrag; Christopher J Mathias; Nir Giladi; Tanya Gurevich; Erik Dupont; Karen Ostergaard; Christer F Nilsson; Håkan Widner; Wolfgang Oertel; Karla Maria Eggert; Alberto Albanese; Francesca del Sorbo; Eduardo Tolosa; Adriana Cardozo; Günther Deuschl; Helge Hellriegel; Thomas Klockgether; Richard Dodel; Cristina Sampaio; Miguel Coelho; Ruth Djaldetti; Eldad Melamed; Thomas Gasser; Christoph Kamm; Giuseppe Meco; Carlo Colosimo; Olivier Rascol; Wassilios G Meissner; François Tison; Werner Poewe Journal: Lancet Neurol Date: 2013-02-05 Impact factor: 44.182