Literature DB >> 35674825

Use of deep learning-based radiomics to differentiate Parkinson's disease patients from normal controls: a study based on [18F]FDG PET imaging.

Xiaoming Sun1, Jingjie Ge2, Lanlan Li1, Qi Zhang1, Wei Lin3, Yue Chen4, Ping Wu2, Likun Yang3, Chuantao Zuo5,6, Jiehui Jiang7.   

Abstract

OBJECTIVES: We proposed a novel deep learning-based radiomics (DLR) model to diagnose Parkinson's disease (PD) based on [18F]fluorodeoxyglucose (FDG) PET images.
METHODS: In this two-center study, 255 normal controls (NCs) and 103 PD patients were enrolled from Huashan Hospital, China; 26 NCs and 22 PD patients were enrolled as a separate test group from Wuxi 904 Hospital, China. The proposed DLR model consisted of a convolutional neural network-based feature encoder and a support vector machine (SVM) model-based classifier. The DLR model was trained and validated in the Huashan cohort and tested in the Wuxi cohort, and accuracy, sensitivity, specificity and receiver operator characteristic (ROC) curve graphs were used to describe the model's performance. Comparative experiments were performed based on four other models including the scale model, radiomics model, standard uptake value ratio (SUVR) model and DLR model.
RESULTS: The DLR model demonstrated superiority in differentiating PD patients and NCs in comparison to other models, with an accuracy of 95.17% [90.35%, 98.13%] (95% confidence intervals, CI) in the Huashan cohort. Moreover, the DLR model also demonstrated greater performance in diagnosing PD early than routine methods, with an accuracy of 85.58% [78.60%, 91.57%] in the Huashan cohort.
CONCLUSIONS: We developed a DLR model based on [18F]FDG PET images that showed good performance in the noninvasive, individualized prediction of PD and was superior to traditional handcrafted methods. This model has the potential to guide and facilitate clinical diagnosis and contribute to the development of precision treatment. KEY POINTS: The DLR method on [18F]FDG PET images helps clinicians to diagnose PD and PD subgroups from normal controls. A prospective two-center study showed that the DLR method provides greater diagnostic accuracy.
© 2022. The Author(s), under exclusive licence to European Society of Radiology.

Entities:  

Keywords:  Deep learning radiomics; Parkinson’s disease; Support vector machine; [18F]fluorodeoxyglucose PET

Year:  2022        PMID: 35674825     DOI: 10.1007/s00330-022-08799-z

Source DB:  PubMed          Journal:  Eur Radiol        ISSN: 0938-7994            Impact factor:   5.315


  18 in total

Review 1.  Positron emission tomography in diagnosis and differential diagnosis of Parkinson's disease.

Authors:  Klaus Tatsch
Journal:  Neurodegener Dis       Date:  2010-07-12       Impact factor: 2.977

Review 2.  Alpha-synuclein: Pathology, mitochondrial dysfunction and neuroinflammation in Parkinson's disease.

Authors:  Emily M Rocha; Briana De Miranda; Laurie H Sanders
Journal:  Neurobiol Dis       Date:  2017-04-08       Impact factor: 5.996

3.  International multicenter pilot study of the first comprehensive self-completed nonmotor symptoms questionnaire for Parkinson's disease: the NMSQuest study.

Authors:  Kallol Ray Chaudhuri; Pablo Martinez-Martin; Anthony H V Schapira; Fabrizio Stocchi; Kapil Sethi; Per Odin; Richard G Brown; William Koller; Paolo Barone; Graeme MacPhee; Linda Kelly; Martin Rabey; Doug MacMahon; Sue Thomas; William Ondo; David Rye; Alison Forbes; Susanne Tluk; Vandana Dhawan; Annette Bowron; Adrian J Williams; Charles W Olanow
Journal:  Mov Disord       Date:  2006-07       Impact factor: 10.338

4.  Nonmotor symptoms in Parkinson's disease.

Authors:  Anna Hussl; Klaus Seppi; Werner Poewe
Journal:  Expert Rev Neurother       Date:  2013-06       Impact factor: 4.618

Review 5.  Molecular imaging to track Parkinson's disease and atypical parkinsonisms: New imaging frontiers.

Authors:  Antonio P Strafella; Nicolaas I Bohnen; Joel S Perlmutter; David Eidelberg; Nicola Pavese; Thilo Van Eimeren; Paola Piccini; Marios Politis; Stephane Thobois; Roberto Ceravolo; Makoto Higuchi; Valtteri Kaasinen; Mario Masellis; M Cecilia Peralta; Ignacio Obeso; Jose Ángel Pineda-Pardo; Roberto Cilia; Benedicte Ballanger; Martin Niethammer; Jon A Stoessl
Journal:  Mov Disord       Date:  2017-02-02       Impact factor: 10.338

Review 6.  The epidemiology of Parkinson's disease: risk factors and prevention.

Authors:  Alberto Ascherio; Michael A Schwarzschild
Journal:  Lancet Neurol       Date:  2016-10-11       Impact factor: 44.182

7.  The utility of FDG-PET in the differential diagnosis of Parkinsonism.

Authors:  Leposava Brajkovic; Vladimir Kostic; Dragana Sobic-Saranovic; Elka Stefanova; Milica Jecmenica-Lukic; Ana Jesic; Milica Stojiljkovic; Strahinja Odalovic; Francesca Gallivanone; Isabella Castiglioni; Branislava Radovic; Goran Trajkovic; Vera Artiko
Journal:  Neurol Res       Date:  2017-04-05       Impact factor: 2.448

8.  Two-year follow-up in 150 consecutive cases with normal dopamine transporter imaging.

Authors:  Vicky L Marshall; Jim Patterson; Donald M Hadley; Katherine A Grosset; Donald G Grosset
Journal:  Nucl Med Commun       Date:  2006-12       Impact factor: 1.690

9.  Importance of motor vs. non-motor symptoms for health-related quality of life in early Parkinson's disease.

Authors:  Bernd Müller; Jörg Assmus; Karen Herlofson; Jan Petter Larsen; Ole-Bjørn Tysnes
Journal:  Parkinsonism Relat Disord       Date:  2013-08-02       Impact factor: 4.891

Review 10.  Imaging biomarkers in Parkinson's disease.

Authors:  David J Brooks; Nicola Pavese
Journal:  Prog Neurobiol       Date:  2011-08-30       Impact factor: 11.685

View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.