Deep Learning-Driven Estimation of Centiloid Scales from Amyloid PET Images with C-PiB and F-Labeled Tracers in Alzheimer's Disease

Overview

Journal Brain Sci

Publisher MDPI

Date 2024 Apr 27

PMID 38672055

Authors

Tensho Yamao

Kenta Miwa

Yuta Kaneko

Noriyuki Takahashi

Noriaki Miyaji

Koki Hasegawa

Kei Wagatsuma

Yuto Kamitaka

Hiroshi Ito

Hiroshi Matsuda

Affiliations

Soon will be listed here.

Abstract

Background: Standard methods for deriving Centiloid scales from amyloid PET images are time-consuming and require considerable expert knowledge. We aimed to develop a deep learning method of automating Centiloid scale calculations from amyloid PET images with C-Pittsburgh Compound-B (PiB) tracer and assess its applicability to F-labeled tracers without retraining.

Methods: We trained models on 231 C-PiB amyloid PET images using a 50-layer 3D ResNet architecture. The models predicted the Centiloid scale, and accuracy was assessed using mean absolute error (MAE), linear regression analysis, and Bland-Altman plots.

Results: The MAEs for Alzheimer's disease (AD) and young controls (YC) were 8.54 and 2.61, respectively, using C-PiB, and 8.66 and 3.56, respectively, using F-NAV4694. The MAEs for AD and YC were higher with F-florbetaben (39.8 and 7.13, respectively) and F-florbetapir (40.5 and 12.4, respectively), and the error rate was moderate for F-flutemetamol (21.3 and 4.03, respectively). Linear regression yielded a slope of 1.00, intercept of 1.26, and R of 0.956, with a mean bias of -1.31 in the Centiloid scale prediction.

Conclusions: We propose a deep learning means of directly predicting the Centiloid scale from amyloid PET images in a native space. Transferring the model trained on C-PiB directly to F-NAV4694 without retraining was feasible.

References

Choi H, Lee D . Generation of Structural MR Images from Amyloid PET: Application to MR-Less Quantification. J Nucl Med. 2017; 59(7):1111-1117. PMC: 6910644. DOI: 10.2967/jnumed.117.199414. View

Oh H, Mormino E, Madison C, Hayenga A, Smiljic A, Jagust W . β-Amyloid affects frontal and posterior brain networks in normal aging. Neuroimage. 2010; 54(3):1887-95. PMC: 3038633. DOI: 10.1016/j.neuroimage.2010.10.027. View

Navitsky M, Joshi A, Kennedy I, Klunk W, Rowe C, Wong D . Standardization of amyloid quantitation with florbetapir standardized uptake value ratios to the Centiloid scale. Alzheimers Dement. 2018; 14(12):1565-1571. DOI: 10.1016/j.jalz.2018.06.1353. View

Jureus A, Swahn B, Sandell J, Jeppsson F, Johnson A, Johnstrom P . Characterization of AZD4694, a novel fluorinated Abeta plaque neuroimaging PET radioligand. J Neurochem. 2010; 114(3):784-94. DOI: 10.1111/j.1471-4159.2010.06812.x. View

Villemagne V, Mulligan R, Pejoska S, Ong K, Jones G, OKeefe G . Comparison of 11C-PiB and 18F-florbetaben for Aβ imaging in ageing and Alzheimer's disease. Eur J Nucl Med Mol Imaging. 2012; 39(6):983-9. DOI: 10.1007/s00259-012-2088-x. View

Rowe C, Ng S, Ackermann U, Gong S, Pike K, Savage G . Imaging beta-amyloid burden in aging and dementia. Neurology. 2007; 68(20):1718-25. DOI: 10.1212/01.wnl.0000261919.22630.ea. View

Jack Jr C, Wiste H, Weigand S, Therneau T, Lowe V, Knopman D . Defining imaging biomarker cut points for brain aging and Alzheimer's disease. Alzheimers Dement. 2016; 13(3):205-216. PMC: 5344738. DOI: 10.1016/j.jalz.2016.08.005. View

Rowe C, Dore V, Jones G, Baxendale D, Mulligan R, Bullich S . F-Florbetaben PET beta-amyloid binding expressed in Centiloids. Eur J Nucl Med Mol Imaging. 2017; 44(12):2053-2059. PMC: 5656696. DOI: 10.1007/s00259-017-3749-6. View

Rowe C, Pejoska S, Mulligan R, Jones G, Chan J, Svensson S . Head-to-head comparison of 11C-PiB and 18F-AZD4694 (NAV4694) for β-amyloid imaging in aging and dementia. J Nucl Med. 2013; 54(6):880-6. DOI: 10.2967/jnumed.112.114785. View

10.

Kang S, Kim D, Shin S, Kim Y, Choi H, Lee J . Fast and Accurate Amyloid Brain PET Quantification Without MRI Using Deep Neural Networks. J Nucl Med. 2022; 64(4):659-666. PMC: 10071781. DOI: 10.2967/jnumed.122.264414. View

11.

Jack Jr C, Bennett D, Blennow K, Carrillo M, Dunn B, Budd Haeberlein S . NIA-AA Research Framework: Toward a biological definition of Alzheimer's disease. Alzheimers Dement. 2018; 14(4):535-562. PMC: 5958625. DOI: 10.1016/j.jalz.2018.02.018. View

12.

Lee S, Kang H, Jeong J, Kang D . Performance evaluation in [18F]Florbetaben brain PET images classification using 3D Convolutional Neural Network. PLoS One. 2021; 16(10):e0258214. PMC: 8528306. DOI: 10.1371/journal.pone.0258214. View

13.

Jeong Y, Yoon H, Kang D, Park K . Quantitative comparative analysis of amyloid PET images using three radiopharmaceuticals. Ann Nucl Med. 2023; 37(5):271-279. PMC: 10129914. DOI: 10.1007/s12149-023-01824-1. View

14.

Aizenstein H, Nebes R, Saxton J, Price J, Mathis C, Tsopelas N . Frequent amyloid deposition without significant cognitive impairment among the elderly. Arch Neurol. 2008; 65(11):1509-17. PMC: 2636844. DOI: 10.1001/archneur.65.11.1509. View

15.

Matsuda H, Yamao T, Shakado M, Shigemoto Y, Okita K, Sato N . Amyloid PET quantification using low-dose CT-guided anatomic standardization. EJNMMI Res. 2021; 11(1):125. PMC: 8671596. DOI: 10.1186/s13550-021-00867-7. View

16.

Klunk W, Koeppe R, Price J, Benzinger T, Devous Sr M, Jagust W . The Centiloid Project: standardizing quantitative amyloid plaque estimation by PET. Alzheimers Dement. 2014; 11(1):1-15.e1-4. PMC: 4300247. DOI: 10.1016/j.jalz.2014.07.003. View

17.

Serrano-Pozo A, Frosch M, Masliah E, Hyman B . Neuropathological alterations in Alzheimer disease. Cold Spring Harb Perspect Med. 2012; 1(1):a006189. PMC: 3234452. DOI: 10.1101/cshperspect.a006189. View

18.

Oh H, Madison C, Haight T, Markley C, Jagust W . Effects of age and β-amyloid on cognitive changes in normal elderly people. Neurobiol Aging. 2012; 33(12):2746-55. PMC: 3381075. DOI: 10.1016/j.neurobiolaging.2012.02.008. View

19.

Bullich S, Roe-Vellve N, Marquie M, Landau S, Barthel H, Villemagne V . Early detection of amyloid load using F-florbetaben PET. Alzheimers Res Ther. 2021; 13(1):67. PMC: 8005243. DOI: 10.1186/s13195-021-00807-6. View

20.

Wolk D, Zhang Z, Boudhar S, Clark C, Pontecorvo M, Arnold S . Amyloid imaging in Alzheimer's disease: comparison of florbetapir and Pittsburgh compound-B positron emission tomography. J Neurol Neurosurg Psychiatry. 2012; 83(9):923-6. PMC: 4479493. DOI: 10.1136/jnnp-2012-302548. View