Improved amyloid burden quantification with nonspecific estimates using deep learning

• Published in: European journal of nuclear medicine and molecular imaging Vol. 48; no. 6; pp. 1842 - 1853
• Main Authors: Liu, Haohui, Nai, Ying-Hwey, Saridin, Francis, Tanaka, Tomotaka, O’ Doherty, Jim, Hilal, Saima, Gyanwali, Bibek, Chen, Christopher P., Robins, Edward G., Reilhac, Anthonin
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer Berlin Heidelberg 01.06.2021; Springer Nature B.V
• Subjects: Alzheimer Disease; Alzheimer's disease; Amyloid - metabolism; Amyloid beta-Peptides; Aniline Compounds; Artificial neural networks; Brain - metabolism; Cardiology; Cerebrovascular diseases; Cognitive ability; Deep Learning; Functional testing; Generative adversarial networks; Harnesses; Humans; Imaging; Intermodal; Medical imaging; Medicine; Medicine & Public Health; Neural networks; Neurodegenerative diseases; Neurology – Dementia; Nuclear Medicine; Oncology; Original; Original Article; Orthopedics; Positron emission; Positron emission tomography; Radiology; Substantia grisea; Tomography; Deep learning; Nonspecific uptake; Positron emission tomography (PET); Amyloid; Alzheimer’s disease; Quantification
• ISSN: 1619-7070; 1619-7089
• DOI: 10.1007/s00259-020-05131-z

Purpose Standardized uptake value ratio (SUVr) used to quantify amyloid-β burden from amyloid-PET scans can be biased by variations in the tracer’s nonspecific (NS) binding caused by the presence of cerebrovascular disease (CeVD). In this work, we propose a novel amyloid-PET quantification approach that harnesses the intermodal image translation capability of convolutional networks to remove this undesirable source of variability. Methods Paired MR and PET images exhibiting very low specific uptake were selected from a Singaporean amyloid-PET study involving 172 participants with different severities of CeVD. Two convolutional neural networks (CNN), ScaleNet and HighRes3DNet, and one conditional generative adversarial network (cGAN) were trained to map structural MR to NS PET images. NS estimates generated for all subjects using the most promising network were then subtracted from SUVr images to determine specific amyloid load only (SAβ L ). Associations of SAβ L with various cognitive and functional test scores were then computed and compared to results using conventional SUVr. Results Multimodal ScaleNet outperformed other networks in predicting the NS content in cortical gray matter with a mean relative error below 2%. Compared to SUVr, SAβ L showed increased association with cognitive and functional test scores by up to 67%. Conclusion Removing the undesirable NS uptake from the amyloid load measurement is possible using deep learning and substantially improves its accuracy. This novel analysis approach opens a new window of opportunity for improved data modeling in Alzheimer’s disease and for other neurodegenerative diseases that utilize PET imaging.