Skip to main content
Erschienen in: European Journal of Nuclear Medicine and Molecular Imaging 2/2020

25.11.2019 | Original Article

Cognitive signature of brain FDG PET based on deep learning: domain transfer from Alzheimer’s disease to Parkinson’s disease

verfasst von: Hongyoon Choi, Yu Kyeong Kim, Eun Jin Yoon, Jee-Young Lee, Dong Soo Lee, for the Alzheimer’s Disease Neuroimaging Initiative

Erschienen in: European Journal of Nuclear Medicine and Molecular Imaging | Ausgabe 2/2020

Einloggen, um Zugang zu erhalten

Abstract

Purpose

Although functional brain imaging has been used for the early and objective assessment of cognitive dysfunction, there is a lack of generalized image-based biomarker which can evaluate individual’s cognitive dysfunction in various disorders. To this end, we developed a deep learning-based cognitive signature of FDG brain PET adaptable for Parkinson’s disease (PD) as well as Alzheimer’s disease (AD).

Methods

A deep learning model for discriminating AD from normal controls (NCs) was built by a training set consisting of 636 FDG PET obtained from Alzheimer’s Disease Neuroimaging Initiative database. The model was directly transferred to images of mild cognitive impairment (MCI) patients (n = 666) for identifying who would rapidly convert to AD and another independent cohort consisting of 62 PD patients to differentiate PD patients with dementia. The model accuracy was measured by area under curve (AUC) of receiver operating characteristic (ROC) analysis. The relationship between all images was visualized by two-dimensional projection of the deep learning-based features. The model was also designed to predict cognitive score of the subjects and validated in PD patients. Cognitive dysfunction-related regions were visualized by feature maps of the deep CNN model.

Results

AUC of ROC for differentiating AD from NC was 0.94 (95% CI 0.89–0.98). The transfer of the model could differentiate MCI patients who would convert to AD (AUC = 0.82) and PD with dementia (AUC = 0.81). The two-dimensional projection mapping visualized the degree of cognitive dysfunction compared with normal brains regardless of different disease cohorts. Predicted cognitive score, an output of the model, was highly correlated with the mini-mental status exam scores. Individual cognitive dysfunction-related regions included cingulate and high frontoparietal cortices, while they showed individual variability.

Conclusion

The deep learning-based cognitive function evaluation model could be successfully transferred to multiple disease domains. We suggest that this approach might be extended to an objective cognitive signature that provides quantitative biomarker for cognitive dysfunction across various neurodegenerative disorders.
Anhänge
Nur mit Berechtigung zugänglich
Literatur
1.
Zurück zum Zitat Chaudhuri KR, Healy DG, Schapira AH. Non-motor symptoms of Parkinson’s disease: diagnosis and management. Lancet Neurol. 2006;5(3):235–45.CrossRef Chaudhuri KR, Healy DG, Schapira AH. Non-motor symptoms of Parkinson’s disease: diagnosis and management. Lancet Neurol. 2006;5(3):235–45.CrossRef
2.
Zurück zum Zitat Emre M, et al. Clinical diagnostic criteria for dementia associated with Parkinson’s disease. Mov Disord. 2007;22(12):1689–707.CrossRef Emre M, et al. Clinical diagnostic criteria for dementia associated with Parkinson’s disease. Mov Disord. 2007;22(12):1689–707.CrossRef
3.
Zurück zum Zitat McKinlay A, et al. A profile of neuropsychiatric problems and their relationship to quality of life for Parkinson’s disease patients without dementia. Parkinsonism Relat Disord. 2008;14(1):37–42.CrossRef McKinlay A, et al. A profile of neuropsychiatric problems and their relationship to quality of life for Parkinson’s disease patients without dementia. Parkinsonism Relat Disord. 2008;14(1):37–42.CrossRef
4.
Zurück zum Zitat Schrag A, Jahanshahi M, Quinn N. What contributes to quality of life in patients with Parkinson’s disease? J Neurol Neurosurg Psychiatry. 2000;69(3):308–12.CrossRef Schrag A, Jahanshahi M, Quinn N. What contributes to quality of life in patients with Parkinson’s disease? J Neurol Neurosurg Psychiatry. 2000;69(3):308–12.CrossRef
5.
Zurück zum Zitat Ravina B, et al. The role of radiotracer imaging in Parkinson disease. Neurology. 2005;64(2):208–15.CrossRef Ravina B, et al. The role of radiotracer imaging in Parkinson disease. Neurology. 2005;64(2):208–15.CrossRef
6.
Zurück zum Zitat Brooks DJ. Imaging approaches to Parkinson disease. J Nucl Med. 2010;51(4):596–609.CrossRef Brooks DJ. Imaging approaches to Parkinson disease. J Nucl Med. 2010;51(4):596–609.CrossRef
7.
Zurück zum Zitat Eidelberg D. Metabolic brain networks in neurodegenerative disorders: a functional imaging approach. Trends Neurosci. 2009;32(10):548–57.CrossRef Eidelberg D. Metabolic brain networks in neurodegenerative disorders: a functional imaging approach. Trends Neurosci. 2009;32(10):548–57.CrossRef
8.
Zurück zum Zitat Eckert T, et al. FDG PET in the differential diagnosis of parkinsonian disorders. Neuroimage. 2005;26(3):912–21.CrossRef Eckert T, et al. FDG PET in the differential diagnosis of parkinsonian disorders. Neuroimage. 2005;26(3):912–21.CrossRef
9.
Zurück zum Zitat Huang C, et al. Metabolic abnormalities associated with mild cognitive impairment in Parkinson disease. Neurology. 2008;70(16 Part 2):1470–7.CrossRef Huang C, et al. Metabolic abnormalities associated with mild cognitive impairment in Parkinson disease. Neurology. 2008;70(16 Part 2):1470–7.CrossRef
10.
Zurück zum Zitat Huang C, et al. Metabolic brain networks associated with cognitive function in Parkinson’s disease. Neuroimage. 2007;34(2):714–23.CrossRef Huang C, et al. Metabolic brain networks associated with cognitive function in Parkinson’s disease. Neuroimage. 2007;34(2):714–23.CrossRef
11.
Zurück zum Zitat Svenningsson P, Westman E, Ballard C, Aarsland D. Cognitive impairment in patients with Parkinson’s disease: diagnosis, biomarkers, and treatment. Lancet Neurol. 2012;11(8):697–707.CrossRef Svenningsson P, Westman E, Ballard C, Aarsland D. Cognitive impairment in patients with Parkinson’s disease: diagnosis, biomarkers, and treatment. Lancet Neurol. 2012;11(8):697–707.CrossRef
12.
Zurück zum Zitat Choi H. Deep learning in nuclear medicine and molecular imaging: current perspectives and future directions. Nucl Med Mol Imaging. 2017:1–10. Choi H. Deep learning in nuclear medicine and molecular imaging: current perspectives and future directions. Nucl Med Mol Imaging. 2017:1–10.
13.
Zurück zum Zitat Oquab M, Bottou L, Laptev I, & Sivic J. Learning and transferring mid-level image representations using convolutional neural networks. Proceedings of the IEEE conference on computer vision and pattern recognition. 2014; pp 1717–1724. Oquab M, Bottou L, Laptev I, & Sivic J. Learning and transferring mid-level image representations using convolutional neural networks. Proceedings of the IEEE conference on computer vision and pattern recognition. 2014; pp 1717–1724.
14.
Zurück zum Zitat Yosinski J, Clune J, Bengio Y, & Lipson H. How transferable are features in deep neural networks? Advances in neural information processing systems. 2014 pp 3320–3328. Yosinski J, Clune J, Bengio Y, & Lipson H. How transferable are features in deep neural networks? Advances in neural information processing systems. 2014 pp 3320–3328.
15.
Zurück zum Zitat Gibb W, Lees A. The relevance of the Lewy body to the pathogenesis of idiopathic Parkinson’s disease. J Neurol Neurosurg Psychiatry. 1988;51(6):745–52.CrossRef Gibb W, Lees A. The relevance of the Lewy body to the pathogenesis of idiopathic Parkinson’s disease. J Neurol Neurosurg Psychiatry. 1988;51(6):745–52.CrossRef
16.
Zurück zum Zitat Jagust WJ, et al. The Alzheimer’s disease neuroimaging initiative 2 PET Core: 2015. Alzheimer’s & dementia: the journal of the Alzheimer’s Association. 2015;11(7):757–71.CrossRef Jagust WJ, et al. The Alzheimer’s disease neuroimaging initiative 2 PET Core: 2015. Alzheimer’s & dementia: the journal of the Alzheimer’s Association. 2015;11(7):757–71.CrossRef
17.
Zurück zum Zitat Kingma D & Ba J. Adam: a method for stochastic optimization. arXiv preprint arXiv. 2014;1412.6980. Kingma D & Ba J. Adam: a method for stochastic optimization. arXiv preprint arXiv. 2014;1412.6980.
18.
Zurück zum Zitat van der Maaten L. Learning a parametric embedding by preserving local structure. RBM. 2009;500(500):26. van der Maaten L. Learning a parametric embedding by preserving local structure. RBM. 2009;500(500):26.
19.
Zurück zum Zitat Zhou B, Khosla A, Lapedriza A, Oliva A, & Torralba A. Learning deep features for discriminative localization. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2016; pp 2921–2929. Zhou B, Khosla A, Lapedriza A, Oliva A, & Torralba A. Learning deep features for discriminative localization. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2016; pp 2921–2929.
20.
Zurück zum Zitat Zintgraf LM, Cohen TS, Adel T, & Welling M. Visualizing deep neural network decisions: prediction difference analysis. arXiv preprint arXiv. 2017;1702.04595. Zintgraf LM, Cohen TS, Adel T, & Welling M. Visualizing deep neural network decisions: prediction difference analysis. arXiv preprint arXiv. 2017;1702.04595.
21.
Zurück zum Zitat Rajpurkar P, et al. Chexnet: radiologist-level pneumonia detection on chest x-rays with deep learning. arXiv preprint arXiv. 2017;1711.05225. Rajpurkar P, et al. Chexnet: radiologist-level pneumonia detection on chest x-rays with deep learning. arXiv preprint arXiv. 2017;1711.05225.
22.
Zurück zum Zitat Aarsland D, Andersen K, Larsen JP, Lolk A. Prevalence and characteristics of dementia in Parkinson disease: an 8-year prospective study. Arch Neurol. 2003;60(3):387–92.CrossRef Aarsland D, Andersen K, Larsen JP, Lolk A. Prevalence and characteristics of dementia in Parkinson disease: an 8-year prospective study. Arch Neurol. 2003;60(3):387–92.CrossRef
23.
Zurück zum Zitat Schroeter ML, Stein T, Maslowski N, Neumann J. Neural correlates of Alzheimer’s disease and mild cognitive impairment: a systematic and quantitative meta-analysis involving 1351 patients. Neuroimage. 2009;47(4):1196–206.CrossRef Schroeter ML, Stein T, Maslowski N, Neumann J. Neural correlates of Alzheimer’s disease and mild cognitive impairment: a systematic and quantitative meta-analysis involving 1351 patients. Neuroimage. 2009;47(4):1196–206.CrossRef
24.
Zurück zum Zitat Bohnen NI, et al. Cerebral glucose metabolic features of Parkinson disease and incident dementia: longitudinal study. J Nucl Med. 2011;52(6):848–55.CrossRef Bohnen NI, et al. Cerebral glucose metabolic features of Parkinson disease and incident dementia: longitudinal study. J Nucl Med. 2011;52(6):848–55.CrossRef
25.
Zurück zum Zitat Greenspan H, van Ginneken B, Summers RM. Guest editorial deep learning in medical imaging: overview and future promise of an exciting new technique. IEEE Trans Med Imaging. 2016;35(5):1153–9.CrossRef Greenspan H, van Ginneken B, Summers RM. Guest editorial deep learning in medical imaging: overview and future promise of an exciting new technique. IEEE Trans Med Imaging. 2016;35(5):1153–9.CrossRef
26.
Zurück zum Zitat Tajbakhsh N, et al. Convolutional neural networks for medical image analysis: full training or fine tuning? IEEE Trans Med Imaging. 2016;35(5):1299–312.CrossRef Tajbakhsh N, et al. Convolutional neural networks for medical image analysis: full training or fine tuning? IEEE Trans Med Imaging. 2016;35(5):1299–312.CrossRef
27.
Zurück zum Zitat Gulshan V, et al. Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs. Jama. 2016;316(22):2402–10.CrossRef Gulshan V, et al. Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs. Jama. 2016;316(22):2402–10.CrossRef
28.
Zurück zum Zitat Esteva A, et al. Dermatologist-level classification of skin cancer with deep neural networks. Nature. 2017;542(7639):115.CrossRef Esteva A, et al. Dermatologist-level classification of skin cancer with deep neural networks. Nature. 2017;542(7639):115.CrossRef
29.
Zurück zum Zitat Coudray N, et al. Classification and mutation prediction from non–small cell lung cancer histopathology images using deep learning. Nat Med. 2018:1. Coudray N, et al. Classification and mutation prediction from non–small cell lung cancer histopathology images using deep learning. Nat Med. 2018:1.
30.
Zurück zum Zitat Cheng B, Zhang D, & Shen D. Domain transfer learning for MCI conversion prediction. Medical Image Computing and Computer-Assisted Intervention–MICCAI. 2012;2012:82–90 Cheng B, Zhang D, & Shen D. Domain transfer learning for MCI conversion prediction. Medical Image Computing and Computer-Assisted Intervention–MICCAI. 2012;2012:82–90
31.
Zurück zum Zitat Choi H, Jin KH, Initiative AsDN. Predicting cognitive decline with deep learning of brain metabolism and amyloid imaging. Behav Brain Res. 2018;344:103–9.CrossRef Choi H, Jin KH, Initiative AsDN. Predicting cognitive decline with deep learning of brain metabolism and amyloid imaging. Behav Brain Res. 2018;344:103–9.CrossRef
32.
Zurück zum Zitat Choi H, et al. Deep learning only by normal brain PET identify unheralded brain anomalies. EBioMedicine. 2019. 2019;43:447-53. Choi H, et al. Deep learning only by normal brain PET identify unheralded brain anomalies. EBioMedicine. 2019. 2019;43:447-53.
Metadaten
Titel
Cognitive signature of brain FDG PET based on deep learning: domain transfer from Alzheimer’s disease to Parkinson’s disease
verfasst von
Hongyoon Choi
Yu Kyeong Kim
Eun Jin Yoon
Jee-Young Lee
Dong Soo Lee
for the Alzheimer’s Disease Neuroimaging Initiative
Publikationsdatum
25.11.2019
Verlag
Springer Berlin Heidelberg
Erschienen in
European Journal of Nuclear Medicine and Molecular Imaging / Ausgabe 2/2020
Print ISSN: 1619-7070
Elektronische ISSN: 1619-7089
DOI
https://doi.org/10.1007/s00259-019-04538-7

Weitere Artikel der Ausgabe 2/2020

European Journal of Nuclear Medicine and Molecular Imaging 2/2020 Zur Ausgabe