Accuracy and generalization capability of an automatic method for the detection of typical brain hypometabolism in prodromal Alzheimer disease

被引：20

作者：

De Carli, Fabrizio ^{[1
]}

Nobili, Flavio ^{[2
]}

Pagani, Marco ^{[3
,4
]}

Bauckneht, Matteo ^{[5
,6
]}

Massa, Federico ^{[2
]}

Grazzini, Matteo ^{[2
]}

Jonsson, Cathrine ^{[4
]}

Peira, Enrico ^{[7
]}

Morbelli, Silvia ^{[5
,6
]}

Arnaldi, Dario ^{[2
]}

Weiner, Michael W. ^{[8
,91
]}

Aisen, Paul ^{[9
]}

Weiner, Michael ^{[8
]}

Petersen, Ronald ^{[10
]}

Jack, Clifford R., Jr. ^{[10
]}

Jagust, William ^{[11
,91
]}

Trojanowki, John Q. ^{[12
,37
,92
,93
]}

Toga, Arthur W. ^{[9
,13
]}

Beckett, Laurel ^{[14
]}

Saykin, Andrew J. ^{[15
]}

Morris, John ^{[16
]}

Shaw, Leslie M. ^{[12
,37
,92
]}

Khachaturian, Zaven ^{[17
]}

Sorensen, Greg ^{[18
]}

Carrillo, Maria ^{[19
]}

Kuller, Lew ^{[20
]}

Raichle, Marc ^{[16
]}

Paul, Steven ^{[21
]}

Davies, Peter ^{[22
]}

Fillit, Howard ^{[23
]}

Hefti, Franz ^{[24
]}

Holtzman, David ^{[16
]}

Mesulam, M. Marcel ^{[25
]}

Potter, William ^{[26
]}

Snyder, Peter ^{[27
]}

Logovinsky, Veronika

Montine, Tom ^{[16
,29
]}

Jimenez, Gustavo ^{[13
]}

Donohue, Michael ^{[13
,30
]}

Gessert, Devon ^{[13
]}

Harless, Kelly ^{[13
]}

Salazar, Jennifer ^{[13
]}

Cabrera, Yuliana ^{[13
]}

Walter, Sarah ^{[13
]}

Hergesheimer, Lindsey ^{[13
]}

Bernstein, Matthew ^{[10
]}

Fox, Nick ^{[31
]}

Thompson, Paul ^{[32
]}

Schuff, Norbert ^{[33
]}

DeCArli, Charles ^{[14
]}

机构：

[1] CNR, Inst Mol Bioimaging & Physiol, Largo Paolo Daneo 3, I-16132 Genoa, Italy

[2] Univ Genoa, IRCCS Polyclin San Martino IST, Dept Neurosci DINOGMI, Genoa, Italy

[3] CNR, Inst Cognit Sci & Technol, Rome, Italy

[4] Karolinska Univ Hosp, Imaging & Physiol, Med Radiat Phys & Nucl Med, Stockholm, Sweden

[5] Univ Genoa, Dept Hlth Sci DISSAL, Genoa, Italy

[6] Polyclin San Martino Hosp, Nucl Med Unit, Genoa, Italy

[7] Natl Inst Nucl Phys INFN, Genoa, Italy

[8] UC San Francisco, San Francisco, CA USA

[9] Univ Southern Calif, Los Angeles, CA 90089 USA

[10] Mayo Clin, Rochester, MN USA

[11] Univ Calif Berkeley, Berkeley, CA USA

[12] Univ Penn, Philadelphia, PA 19104 USA

[13] USC, Los Angeles, CA USA

[14] Univ Calif Davis, Davis, CA USA

[15] Indiana Univ, Bloomington, IN 47405 USA

[16] Washington Univ, St Louis, MO 63130 USA

[17] Prevent Alzheimers Dis 2020, Rockville, MD USA

[18] Siemens, Munich, Germany

[19] Alzheimers Assoc, Chicago, IL USA

[20] Univ Pittsburgh, Pittsburgh, PA 15260 USA

[21] Cornell Univ, Ithaca, NY 14853 USA

[22] Yeshiva Univ, Albert Einstein Col Med, New York, NY 10033 USA

[23] AD Drug Discovery Fdn, New York, NY USA

[24] Acumen Pharmceut, Livermore, CA USA

[25] Northwestern Univ, Evanston, IL 60208 USA

[26] NIMH, Rockville, MD 20852 USA

[27] Brown Univ, Providence, RI 02912 USA

[28] HMS, BWH, Boston, MA USA

[29] Univ Washington, Seattle, WA 98195 USA

[30] Univ Calif San Diego, La Jolla, CA USA

[31] Univ London, London, England

[32] Univ Calif Los Angeles, Sch Med, Los Angeles, CA 90024 USA

[33] UCSF, MRI, San Francisco, CA USA

[34] Univ Michigan, Ann Arbor, MI 48109 USA

[35] Univ Utah, Salt Lake City, UT 84112 USA

[36] Banner Alzheimers Inst, Phoenix, AZ USA

[37] UPenn Sch Med, Philadelphia, PA USA

[38] UC Irvine, Irvine, CA USA

[39] NIA, Bethesda, MD 20892 USA

[40] Johns Hopkins Univ, Baltimore, MD 21218 USA

[41] Richard Frank Consulting, Sacramento, CA USA

[42] Oregon Hlth & Sci Univ, Portland, OR 97201 USA

[43] Univ Calif San Diego, La Jolla, CA 92093 USA

[44] Baylor Coll Med, Houston, TX 77030 USA

[45] Columbia Univ, Med Ctr, New York, NY 10027 USA

[46] Univ Alabama Birmingham, Birmingham, AL USA

[47] Mt Sinai Sch Med, New York, NY USA

[48] Rush Univ, Med Ctr, Chicago, IL 60612 USA

[49] Wien Ctr, Vienna, Austria

[50] NYU, New York, NY 10003 USA

来源：

EUROPEAN JOURNAL OF NUCLEAR MEDICINE AND MOLECULAR IMAGING | 2019年 / 46卷 / 02期

基金：

美国国家卫生研究院; 加拿大健康研究院;

关键词：

Alzheimer disease; MCI due to AD; FDG-PET; Discriminant analysis; Neuroimage classification; Classification and prediction; Neurodegenerative disorders; Support vector machine; MILD COGNITIVE IMPAIRMENT; FDG-PET; ASSOCIATION WORKGROUPS; DIAGNOSTIC GUIDELINES; NATIONAL INSTITUTE; MCI; DEMENTIA; RECOMMENDATIONS; VALIDATION; CONFIDENCE;

D O I：

10.1007/s00259-018-4197-7

中图分类号：

R8 [特种医学]; R445 [影像诊断学];

学科分类号：

1002 ; 100207 ; 1009 ;

摘要：

PurposeThe aim of this study was to verify the reliability and generalizability of an automatic tool for the detection of Alzheimer-related hypometabolic pattern based on a Support-Vector-Machine (SVM) model analyzing F-18-fluorodeoxyglucose (FDG) PET data.MethodsThe SVM model processed metabolic data from anatomical volumes of interest also considering interhemispheric asymmetries. It was trained on a homogeneous dataset from a memory clinic center and tested on an independent multicentric dataset drawn from the Alzheimer's Disease Neuroimaging Initiative. Subjects were included in the study and classified based on a diagnosis confirmed after an adequate follow-up time.ResultsThe accuracy of the discrimination between patients with Alzheimer Disease (AD), in either prodromal or dementia stage, and normal aging subjects was 95.8%, after cross-validation, in the training set. The accuracy of the same model in the testing set was 86.5%. The role of the two datasets was then reversed, and the accuracy was 89.8% in the multicentric training set and 88.0% in the monocentric testing set. The classification rate was also evaluated in different subgroups, including non-converter mild cognitive impairment (MCI) patients, subjects with MCI reverted to normal conditions and subjects with non-confirmed memory concern. The percent of pattern detections increased from 77% in early prodromal AD to 91% in AD dementia, while it was about 10% for healthy controls and non-AD patients.ConclusionsThe present findings show a good level of reproducibility and generalizability of a model for detecting the hypometabolic pattern in AD and confirm the accuracy of FDG-PET in Alzheimer disease.

引用

页码：334 / 347

页数：14

共 44 条

[1] The diagnosis of mild cognitive impairment due to Alzheimer's disease: Recommendations from the National Institute on Aging-Alzheimer's Association workgroups on diagnostic guidelines for Alzheimer's disease [J].

Albert, Marilyn S. ;

DeKosky, Steven T. ;

Dickson, Dennis ;

Dubois, Bruno ;

Feldman, Howard H. ;

Fox, Nick C. ;

Gamst, Anthony ;

Holtzman, David M. ;

Jagust, William J. ;

Petersen, Ronald C. ;

Snyder, Peter J. ;

Carrillo, Maria C. ;

Thies, Bill ;

Phelps, Creighton H. .

ALZHEIMERS & DEMENTIA, 2011, 7 (03) :270-279

[2] Functional neuroimaging and clinical features of drug naive patients with de novo Parkinson's disease and probable RBD [J].

Arnaldi, Dario ;

Morbelli, Silvia ;

Brugnolo, Andrea ;

Girtler, Nicola ;

Picco, Agnese ;

Ferrara, Michela ;

Accardo, Jennifer ;

Buschiazzo, Ambra ;

de Carli, Fabrizio ;

Pagani, Marco ;

Nobili, Flavio .

PARKINSONISM & RELATED DISORDERS, 2016, 29 :47-53

[3] Metabolic correlates of reserve and resilience in MCI due to Alzheimer's Disease (AD) [J].

Bauckneht, Matteo ;

Chincarini, Andrea ;

Piva, Roberta ;

Arnaldi, Dario ;

Girtler, Nicola ;

Massa, Federico ;

Pardini, Matteo ;

Grazzini, Matteo ;

Efeturk, Hulya ;

Pagani, Marco ;

Sambuceti, Gianmario ;

Nobili, Flavio ;

Morbelli, Silvia .

ALZHEIMERS RESEARCH & THERAPY, 2018, 10

[4] Patterns of regional cerebellar atrophy in genetic frontotemporal dementia [J].

Bocchetta, Martina ;

Cardoso, M. Jorge ;

Cash, David M. ;

Ourselin, Sebastien ;

Warren, Jason D. ;

Rohrer, Jonathan D. .

NEUROIMAGE-CLINICAL, 2016, 11 :287-290

[5] ALZHEIMERS-DISEASE - AMYLOID PLAQUES IN THE CEREBELLUM [J].

BRAAK, H ;

BRAAK, E ;

BOHL, J ;

LANG, W .

JOURNAL OF THE NEUROLOGICAL SCIENCES, 1989, 93 (2-3) :277-287

[6] Interval estimation for a binomial proportion - Comment - Rejoinder [J].

Brown, LD ;

Cai, TT ;

DasGupta, A ;

Agresti, A ;

Coull, BA ;

Casella, G ;

Corcoran, C ;

Mehta, C ;

Ghosh, M ;

Santner, TJ ;

Brown, LD ;

Cai, TT ;

DasGupta, A .

STATISTICAL SCIENCE, 2001, 16 (02) :101-133

[7] Predicting conversion from MCI to AD with FDG-PET brain images at different prodromal stages [J].

Cabral, Carlos ;

Morgado, Pedro M. ;

Costa, Durval Campos ;

Silveira, Margarida .

COMPUTERS IN BIOLOGY AND MEDICINE, 2015, 58 :101-109

[8] FDG-PET and CSF biomarker accuracy in prediction of conversion to different dementias in a large multicentre MCI cohort [J].

Caminiti, Silvia Paola ;

Ballarini, Tommaso ;

Sala, Arianna ;

Cerami, Chiara ;

Presotto, Luca ;

Santangelo, Roberto ;

Fallanca, Federico ;

Vanoli, Emilia Giovanna ;

Gianolli, Luigi ;

Iannaccone, Sandro ;

Magnani, Giuseppe ;

Perani, Daniela .

NEUROIMAGE-CLINICAL, 2018, 18 :167-177

[9] Summary Metrics to Assess Alzheimer Disease Related Hypometabolic Pattern with 18F-FDG PET: Head-to-Head Comparison [J].

Caroli, Anna ;

Prestia, Annapaola ;

Chen, Kewei ;

Ayutyanont, Napatkamon ;

Landau, Susan M. ;

Madison, Cindee M. ;

Haense, Cathleen ;

Herholz, Karl ;

Nobili, Flavio ;

Reiman, Eric M. ;

Jagust, William J. ;

Frisoni, Giovanni B. .

JOURNAL OF NUCLEAR MEDICINE, 2012, 53 (04) :592-600

[10] Cerebellar Amyloid-β Plaques: How Frequent Are They, and Do They Influence 18F-Florbetaben SUV Ratios? [J].

Catafau, Ana M. ;

Bullich, Santiago ;

Seibyl, John P. ;

Barthel, Henryk ;

Ghetti, Bernardino ;

Leverenz, James ;

Ironside, James W. ;

Schulz-Schaeffer, Walter J. ;

Hoffmann, Anja ;

Sabri, Osama .

JOURNAL OF NUCLEAR MEDICINE, 2016, 57 (11) :1740-1745

← 1 2 3 4 5 →