Top

Published in:

01-09-2021 | Parkinson's Disease | Nuclear Medicine

The role of the deep convolutional neural network as an aid to interpreting brain [¹⁸F]DOPA PET/CT in the diagnosis of Parkinson’s disease

Authors: Arnoldo Piccardo, Roberto Cappuccio, Gianluca Bottoni, Diego Cecchin, Luca Mazzella, Alessio Cirone, Sergio Righi, Martina Ugolini, Pietro Bianchi, Pietro Bertolaccini, Elena Lorenzini, Michela Massollo, Antonio Castaldi, Francesco Fiz, Laura Strada, Angelina Cistaro, Massimo Del Sette

Published in: European Radiology | Issue 9/2021

Abstract

Objectives

To test the performance of a 3D convolutional neural network (CNN) in analysing brain [¹⁸F]DOPA PET/CT in order to identify patients with nigro-striatal neurodegeneration. We evaluated the robustness of the 3D CNN by testing it against a manual regional analysis of the striata by using a striatal-to-occipital ratio (SOR).

Methods

We analyzed patients who had undergone [¹⁸F]DOPA PET/CT from 2016 to 2018. Two examiners interpreted PET/CT images as positive or negative. Only patients with at least 2 years of follow-up and an ascertained neurological diagnosis were included. A 3D CNN was developed to evaluate [¹⁸F]DOPA PET/CT and refine the diagnosis of movement disorder. This system required training and testing, which were carried out on 2/3 and 1/3 of patients, respectively. A regional analysis was also conducted by drawing region of interest on T1-weighted 3D MRI scans, on which the [¹⁸F]DOPA PET images were first co-registered.

Results

Ninety-eight patients were enrolled: 43 presented nigro-striatal degeneration and 55 negative cases used as controls. After training on 69 patients, the diagnostic performance of the 3D CNN was then calculated in 29 patients. Sensitivity, specificity, negative predictive value, positive predictive value and accuracy were 100%, 89%, 100%, 85% and 93%, respectively. When we compared the 3D CNN results with the SOR analysis, we found that the two patients falsely classified as positive by the 3D CNN procedure showed SOR values ≤ 5^th percentile of the negative cases’ distribution.

Conclusions

3D CNNs are able to interpret [¹⁸F]DOPA PET/CT properly, revealing patients affected by Parkinson’s disease.

Key Points

• [ ¹⁸ F]DOPA PET/CT is a sensitive diagnostic tool to identify patients with nigro-striatal neurodegeneration.

• A semiquantitative evaluation of the images allows a more confident interpretation of the PET findings.

• 3D convolutional neural network allows an accurate interpretation of 18F-DOPA PET/CT images, revealing patients affected by Parkinson’s disease.

Available only for authorised users

Eshuis SA, Maguire RP, Leenders KL, Jonkman S, Jager PL (2006) Comparison of FP-CIT SPECT with F-DOPA PET in patients with de novo and advanced Parkinson's disease. Eur J Nucl Med Mol Imaging 33:200–209. https://doi.org/10.1007/s00259-005-1904-yCrossRefPubMed

Eshuis SA, Jager PL, Maguire RP, Jonkman S, Dierckx RA, Leenders KL (2009) Direct comparison of FP-CIT SPECT and F-DOPA PET in patients with Parkinson's disease and healthy controls. Eur J Nucl Med Mol Imaging 36:454–462. https://doi.org/10.1007/s00259-008-0989-5CrossRefPubMed

Picco A, Morbelli S, Piccardo A et al (2015) Brain (18)F-DOPA PET and cognition in de novo Parkinson’s disease. Eur J Nucl Med Mol Imaging 42:1062–1070. https://doi.org/10.1007/s00259-015-3039-0CrossRefPubMed

Morbelli S, Esposito G, Arbizu J et al (2020) EANM practice guideline/SNMMI procedure standard for dopaminergic imaging in Parkinsonian syndromes 1.0 Eur J Nucl Med Mol Imaging:2020. https://doi.org/10.1007/s00259-020-04817-8

Booij J, Habraken JB, Bergmans P et al (1998) Imaging of dopamine transporters with iodine-123-FP-CIT SPECT in healthy controls and patients with Parkinson’s disease. J Nucl Med 39:1879–1884PubMed

Calvini P, Rodriguez G, Inguglia F, Mignone A, Guerra UP, Nobili F (2007) The basal ganglia matching tools package for striatal uptake semi-quantification: description and validation. Eur J Nucl Med Mol Imaging 34:1240–1253. https://doi.org/10.1007/s00259-006-0357-2CrossRefPubMed

Matesan M, Gaddikeri S, Longfellow K et al (2018) I-123 DaTscan SPECT brain imaging in parkinsonian syndromes: utility of the putamen-to-caudate ratio. J Neuroimaging 28:629–634. https://doi.org/10.1111/jon.12530CrossRefPubMed

Zubal IG, Early M, Yuan O, Jennings D, Marek K, Seibyl JP (2007) Optimized, automated striatal uptake analysis applied to SPECT brain scans of Parkinson's disease patients. J Nucl Med 48:857–864. https://doi.org/10.2967/jnumed.106.037432CrossRefPubMed

Morton RJ, Guy MJ, Clauss R, Hinton PJ, Marshall CA, Clarke EA (2005) Comparison of different methods of DatSCAN quantification. Nucl Med Commun 26:1139–1146. https://doi.org/10.1186/s40658-017-0196-1CrossRefPubMed

10.

Nobili F, Naseri M, De Carli F et al (2013) Automatic semi-quantification of [123I]FP-CIT SPECT scans in healthy volunteers using BasGan version 2: results from the ENC-DAT database. Eur J Nucl Med Mol Imaging 40:565–567. https://doi.org/10.1007/s00259-012-2304-8CrossRefPubMed

11.

Chang IC, Lue KH, Hsieh HJ, Liu SH, Kao CH (2011) Automated striatal uptake analysis of ¹⁸F-FDOPA PET images applied to Parkinson’s disease patients. Ann Nucl Med 25:796–803. https://doi.org/10.1007/s12149-011-0533-8CrossRefPubMed

12.

Punjabi A, Martersteck A, Wang Y, Parrish TB, Katsaggelos AK (2019) Alzheimer’s disease neuroimaging initiative. Neuroimaging modality fusion in Alzheimer’s classification using convolutional neural networks. PLoS One 14:e0225759. https://doi.org/10.1371/journal.pone.0225759CrossRefPubMedPubMedCentral

13.

Huang Y, Xu J, Zhou Y, Tong T, Zhuang X (2019) Alzheimer’s Disease Neuroimaging Initiative (ADNI). Diagnosis of Alzheimer’s disease via multi-modality 3D convolutional neural network. Front Neurosci 13:509. https://doi.org/10.3389/fnins.2019.00509CrossRefPubMedPubMedCentral

14.

Ortiz A, Munilla J, Martínez-Ibañez M, Górriz JM, Ramírez J, Salas-Gonzalez D (2019) Parkinson’s disease detection using isosurfaces-based features and convolutional neural networks. Front Neuroinform 13:48. https://doi.org/10.3389/fninf.2019.00048CrossRefPubMedPubMedCentral

15.

Choi H, Ha S, Im HJ, Paek SH, Lee DS (2017) Refining diagnosis of Parkinson’s disease with deep learning-based interpretation of dopamine transporter imaging. Neuroimage Clin 16:586–594. https://doi.org/10.1016/j.nicl.2017.09.010CrossRefPubMedPubMedCentral

16.

Marinelli L, Piccardo A, Mori L et al (2015) Orbitofrontal (18) F-DOPA uptake and movement preparation in Parkinson’s disease. Parkinsons Dis 180940. https://doi.org/10.1155/2015/180940

17.

Bhatia KP, Bain P, Bajaj N et al (2018) Tremor Task Force of the International Parkinson and Movement Disorder Society. Consensus Statement on the classification of tremors. From the task force on tremor of the International Parkinson and Movement Disorder Society. Mov Disord 33:75–87. https://doi.org/10.1002/mds.27121CrossRefPubMed

18.

Pretze M, Wängler C, Wängler B (2014) 6-[18F]fluoro-L-DOPA: a well-established neurotracer with expanding application spectrum and strongly improved radiosyntheses. Biomed Res Int 2014:674063. https://doi.org/10.1155/2014/674063CrossRefPubMedPubMedCentral

19.

Jokinen P, Helenius H, Rauhala E, Brück A, Eskola O, Rinne JO (2009) Simple ratio analysis of 18F-fluorodopa uptake in striatal subregions separates patients with early Parkinson disease from healthy controls. J Nucl Med 50:893–899. https://doi.org/10.2967/jnumed.108.061572CrossRefPubMed

20.

Rizzo G, Copetti M, Arcuti S, Martino D, Fontana A, Logroscino G (2016) Accuracy of clinical diagnosis of Parkinson disease: a systematic review and meta-analysis. Neurology. 86:566–576. https://doi.org/10.1212/WNL.0000000000002350CrossRefPubMed

Title: The role of the deep convolutional neural network as an aid to interpreting brain [18F]DOPA PET/CT in the diagnosis of Parkinson’s disease
Authors: Arnoldo Piccardo
Roberto Cappuccio
Gianluca Bottoni
Diego Cecchin
Luca Mazzella
Alessio Cirone
Sergio Righi
Martina Ugolini
Pietro Bianchi
Pietro Bertolaccini
Elena Lorenzini
Michela Massollo
Antonio Castaldi
Francesco Fiz
Laura Strada
Angelina Cistaro
Massimo Del Sette
Publication date: 01-09-2021
Publisher: Springer Berlin Heidelberg
Keyword: Parkinson's Disease
Published in: European Radiology / Issue 9/2021
Print ISSN: 0938-7994
Electronic ISSN: 1432-1084
DOI: https://doi.org/10.1007/s00330-021-07779-z

Keynote webinar | Spotlight on medication adherence

Springer Medicine

The role of the deep convolutional neural network as an aid to interpreting brain [¹⁸F]DOPA PET/CT in the diagnosis of Parkinson’s disease

Abstract

Objectives

Methods

Results

Conclusions

Key Points

Keynote webinar | Spotlight on medication adherence

Springer Medicine

Abstract

Objectives

Methods

Results

Conclusions

Key Points

Please log in to get access to this content

Other articles of this Issue 9/2021

Pulmonary artery pseudoaneurysms: endovascular management after adequate imaging diagnosis

Ossification of the acetabular rim: a highly prevalent finding in asymptomatic non-osteoarthritic hips of all ages

Advanced MR techniques in glioblastoma imaging—upcoming challenges and how to face them

Studying local tumour heterogeneity on MRI and FDG-PET/CT to predict response to neoadjuvant chemoradiotherapy in rectal cancer

Threshold-dependent iodine imaging and spectral separation in a whole-body photon-counting CT system

AI-based detection and classification of distal radius fractures using low-effort data labeling: evaluation of applicability and effect of training set size