Top

Published in:

08-06-2022 | Positron Emission Tomography | Imaging Informatics and Artificial Intelligence

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

Authors: Xiaoming Sun, Jingjie Ge, Lanlan Li, Qi Zhang, Wei Lin, Yue Chen, Ping Wu, Likun Yang, Chuantao Zuo, Jiehui Jiang

Published in: European Radiology | Issue 11/2022

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 [ ¹⁸ F]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.

Available only for authorised users

Rocha EM, De Miranda B, Sanders LH (2018) Alpha-synuclein: pathology, mitochondrial dysfunction and neuroinflammation in Parkinson’s disease. Neurobiol Dis 109:249–257. https://doi.org/10.1016/j.nbd.2017.04.004CrossRef

Rahmim A, Huang P, Shenkov N et al (2017) Improved prediction of outcome in Parkinson’s disease using radiomics analysis of longitudinal DAT SPECT images. Neuroimage Cl 16:539–544. https://doi.org/10.1016/j.nicl.2017.08.021

Hussl A, Seppi K, Poewe W (2013) Nonmotor symptoms in Parkinson’s disease. Expert Rev Neurother 13:581–583. https://doi.org/10.1586/ern.13.53CrossRef

Chaudhuri KR, Martinez-Martin P, Schapira AHV et al (2006) International multicenter pilot study of the first comprehensive self-completed nonmotor symptoms questionnaire for Parkinson’s disease: the NMSQuest study. Mov Disord 21:916–923. https://doi.org/10.1002/mds.20844CrossRef

Müller B, Assmus J, Herlofson K et al (2013) Importance of motor vs. non-motor symptoms for health-related quality of life in early Parkinson’s disease. Parkinsonism Relat Disord 19:1027–1032. https://doi.org/10.1016/j.parkreldis.2013.07.010CrossRef

Ascherio A, Schwarzschild MA (2016) The epidemiology of Parkinson’s disease: risk factors and prevention. Lancet Neurol 15:1257–1272. https://doi.org/10.1016/S1474-4422(16)30230-7CrossRef

Tatsch K (2010) Positron emission tomography in diagnosis and differential diagnosis of Parkinson’s disease. Neurodegener Dis 7:330–340. https://doi.org/10.1159/000314499CrossRef

Strafella AP, Bohnen NI, Perlmutter JS et al (2017) Molecular imaging to track Parkinson’s disease and atypical parkinsonisms: new imaging frontiers. Mov Disord 32:181–192. https://doi.org/10.1002/mds.26907CrossRef

Marshall VL, Patterson J, Hadley DM et al (2006) Two-year follow-up in 150 consecutive cases with normal dopamine transporter imaging. Nucl Med Commun 27:933–937. https://doi.org/10.1097/01.mnm.0000243374.11260.5bCrossRef

10.

Brooks DJ, Pavese N (2011) Imaging biomarkers in Parkinson’s disease. Prog Neurobiol 95:614–628. https://doi.org/10.1016/j.pneurobio.2011.08.009CrossRef

11.

Brajkovic L, Kostic V, Sobic-Saranovic D et al (2017) The utility of FDG-PET in the differential diagnosis of Parkinsonism. Neurol Res 39:675–684. https://doi.org/10.1080/01616412.2017.1312211CrossRef

12.

Eckert T, Barnes A, Dhawan V et al (2005) FDG PET in the differential diagnosis of parkinsonian disorders. Neuroimage 26:912–921. https://doi.org/10.1016/j.neuroimage.2005.03.012CrossRef

13.

Wu Y, Jiang J-H, Chen L et al (2019) Use of radiomic features and support vector machine to distinguish Parkinson’s disease cases from normal controls. Ann Transl Med 7:773–773. https://doi.org/10.21037/atm.2019.11.26CrossRef

14.

Xie Y, Zhang J, Xia Y et al (2018) Fusing texture, shape and deep model-learned information at decision level for automated classification of lung nodules on chest CT. Inf Fusion 42:102–110. https://doi.org/10.1016/j.inffus.2017.10.005CrossRef

15.

Wang K, Lu X, Zhou H et al (2019) Deep learning radiomics of shear wave elastography significantly improved diagnostic performance for assessing liver fibrosis in chronic hepatitis B: a prospective multicenter study. Gut 68:729–741. https://doi.org/10.1136/gutjnl-2018-316204

16.

Zheng X, Yao Z, Huang Y et al (2020) Deep learning radiomics can predict axillary lymph node status in early-stage breast cancer. Nat Commun 11:1–9. https://doi.org/10.1038/s41467-020-15027-zCrossRef

17.

Hu Y, Xie C, Yang H et al (2021) Computed tomography-based deep-learning prediction of neoadjuvant chemoradiotherapy treatment response in esophageal squamous cell carcinoma. Radiother Oncol 154:6–13. https://doi.org/10.1016/j.radonc.2020.09.014CrossRef

18.

Berg D, Adler CH, Bloem BR et al (2018) Movement disorder society criteria for clinically established early Parkinson’s disease. Mov Disord 33:1643–1646. https://doi.org/10.1002/mds.27431CrossRef

19.

Postuma RB, Berg D, Stern M et al (2015) MDS clinical diagnostic criteria for Parkinson’s disease. Mov Disord 30:1591–1601. https://doi.org/10.1002/mds.26424CrossRef

20.

Postuma RB, Poewe W, Litvan I et al (2018) Validation of the MDS clinical diagnostic criteria for Parkinson’s disease. Mov Disord 33:1601–1608. https://doi.org/10.1002/mds.27362CrossRef

21.

Hughes AJ, Daniel SE, Kilford L, Lees AJ (1992) Accuracy of clinical diagnosis of idiopathic Parkinson’s disease: a clinico-pathological study of 100 cases. J Neurol Neurosurg Psychiatry 55:181–184. https://doi.org/10.1136/jnnp.55.3.181CrossRef

22.

Gonzalez-Escamilla G, Lange C, Teipel S et al (2017) PETPVE12: an SPM toolbox for partial volume effects correction in brain PET – application to amyloid imaging with AV45-PET. Neuroimage 147:669–677. https://doi.org/10.1016/j.neuroimage.2016.12.077CrossRef

23.

Pirooznia M, Deng Y (2006) SVM Classifier - a comprehensive java interface for support vector machine classification of microarray data. BMC Bioinformatics 7. https://doi.org/10.1186/1471-2105-7-S4-S25

24.

Lu S, Lu Z, Zhang YD (2019) Pathological brain detection based on AlexNet and transfer learning. J Comput Sci 30:41–47. https://doi.org/10.1016/j.jocs.2018.11.008CrossRef

25.

Sengupta A, Ye Y, Wang R et al (2019) Going deeper in spiking neural networks: VGG and residual architectures. Front Neurosci 13:1–10. https://doi.org/10.3389/fnins.2019.00095CrossRef

26.

He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. Proc IEEE Comput Soc Conf Comput Vis Pattern Recognit 2016-Decem:770–778. https://doi.org/10.1109/CVPR.2016.90CrossRef

27.

Nie D, Lu J, Zhang H et al (2019) Multi-channel 3D deep feature learning for survival time prediction of brain tumor patients using multi-modal neuroimages. Sci Rep 9:1–14. https://doi.org/10.1038/s41598-018-37387-9CrossRef

28.

Li Z, Wang Y, Yu J et al (2017) Deep Learning based Radiomics (DLR) and its usage in noninvasive IDH1 prediction for low grade glioma. Sci Rep 7:1–11. https://doi.org/10.1038/s41598-017-05848-2CrossRef

29.

Sateesh Babu G, Suresh S, Mahanand BS (2014) A novel PBL-McRBFN-RFE approach for identification of critical brain regions responsible for Parkinson’s disease. Expert Syst Appl 41:478–488. https://doi.org/10.1016/j.eswa.2013.07.073CrossRef

30.

Giancardo L, Sánchez-Ferro A, Arroyo-Gallego T et al (2016) Computer keyboard interaction as an indicator of early Parkinson’s disease. Sci Rep 6:1–10. https://doi.org/10.1038/srep34468CrossRef

31.

Arroyo-Gallego T, Ledesma-Carbayo MJ, Butterworth I et al (2018) Detecting motor impairment in early Parkinson’s disease via natural typing interaction with keyboards: validation of the neuroQWERTY approach in an uncontrolled at-home setting. J Med Internet Res 20:1–14. https://doi.org/10.2196/jmir.9462CrossRef

Title: Use of deep learning-based radiomics to differentiate Parkinson’s disease patients from normal controls: a study based on [18F]FDG PET imaging
Authors: Xiaoming Sun
Jingjie Ge
Lanlan Li
Qi Zhang
Wei Lin
Yue Chen
Ping Wu
Likun Yang
Chuantao Zuo
Jiehui Jiang
Publication date: 08-06-2022
Publisher: Springer Berlin Heidelberg
Keywords: Positron Emission Tomography
Parkinson's Disease
Published in: European Radiology / Issue 11/2022
Print ISSN: 0938-7994
Electronic ISSN: 1432-1084
DOI: https://doi.org/10.1007/s00330-022-08799-z

At a glance: The STEP trials

Springer Medicine

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

Abstract

Objectives

Methods

Results

Conclusions

Key Points

At a glance: The STEP trials

Springer Medicine

Abstract

Objectives

Methods

Results

Conclusions

Key Points

Please log in to get access to this content

Other articles of this Issue 11/2022

Combining multiparametric MRI features-based transfer learning and clinical parameters: application of machine learning for the differentiation of uterine sarcomas from atypical leiomyomas

Determining the suitability of definitive radiation therapy in patients with metastatic nasopharyngeal carcinoma based on PET/CT: a large cohort study

Treatment of chronic lateral epicondylosis: a randomized trial comparing the efficacy of ultrasound-guided tendon dry needling and open-release surgery

CT-based radiomics signature analysis for sevaluation of response to induction chemotherapy and progression-free survival in locally advanced hypopharyngeal carcinoma

Deep learning–based algorithm improved radiologists’ performance in bone metastases detection on CT

Comparison between CT volumetry and extracellular volume fraction using liver dynamic CT for the predictive ability of liver fibrosis in patients with hepatocellular carcinoma