Home › Research › Biomarkers
Amyloid PET Quantification Via End-to-End Training of a Deep Learning
Kim JY, Suh HY, Ryoo HG, Oh D, Choi H, Paeng JC, Cheon GJ, Kang KW et al.. Nuclear medicine and molecular imaging, 2019-10-14
Topic: Amyloid, tau and blood-test diagnosis
Purpose Although quantification of amyloid positron emission tomography (PET) is important for evaluating patients with cognitive impairment, its routine clinical use is hampered by complicated preprocessing steps and required MRI. Here, we suggested a one-step quantification based on deep learning using native-space amyloid PET images of different radiotracers acquired from multiple centers. Methods Amyloid PET data of the Alzheimer Disease Neuroimaging Initiative (ADNI) were used for this study. A training/validation consists of 850 florbetapir PET images. Three hundred sixty-six florbetapir and 89 florbetaben PET images were used as test sets to evaluate the model. Native-space amyloid PET images were used as inputs, and the outputs were standardized uptake value ratios (SUVRs) calculated by the conventional MR-based method. Results The mean absolute errors (MAEs) of the composite SUVR were 0.040, 0.060, and 0.050 of training/validation and test sets for florbetapir PET and a test set for florbetaben PET, respectively. The agreement of amyloid positivity measured by Cohen's kappa for test sets of florbetapir and florbetaben PET were 0.87 and 0.89, respectively. Conclusion We suggest a one-step quantification method for amyloid PET via a deep learning model. The model is highly reliable to quantify the amyloid PET regardless of multicenter images and various radiotracers.
Cite this study APA, Vancouver, BibTeX · download .bib or .ris
APA 7th
Kim, J. Y., Suh, H. Y., Ryoo, H. G., Oh, D., Choi, H., Paeng, J. C., et al. (2019). Amyloid PET Quantification Via End-to-End Training of a Deep Learning. Nuclear medicine and molecular imaging. https://doi.org/10.1007/s13139-019-00610-0
Vancouver
Kim JY, Suh HY, Ryoo HG, Oh D, Choi H, Paeng JC, et al. Amyloid PET Quantification Via End-to-End Training of a Deep Learning. Nuclear medicine and molecular imaging. 2019. doi:10.1007/s13139-019-00610-0. PMID: 31723364.
BibTeX
@article{kim2019-31723364,
author = {Kim, J. Y. and Suh, H. Y. and Ryoo, H. G. and Oh, D. and Choi, H. and Paeng, J. C. and Cheon, G. J. and Kang, K. W. and others},
title = {{Amyloid PET Quantification Via End-to-End Training of a Deep Learning}},
journal = {Nuclear medicine and molecular imaging},
year = {2019},
doi = {10.1007/s13139-019-00610-0},
pmid = {31723364},
url = {https://doi.org/10.1007/s13139-019-00610-0}
}
Built from the record alzhub holds for this paper, not looked up. Volume, issue and page numbers are not held in the record. The record's author list ends in “et al.”, so not every author is named. Check the citation against the original before you use it.
Key findings
- Results The mean absolute errors (MAEs) of the composite SUVR were 0.040, 0.060, and 0.050 of training/validation and test sets for florbetapir PET and a test set for florbetaben PET, respectively.
Why it matters
This study developed a deep learning model to quantify amyloid PET scans without MRI preprocessing, achieving high agreement with conventional methods. It is a technical imaging study and does not test any treatment, cure, or prevention for Alzheimer's disease.
New to this subject? Start with our plain-English guide: Blood tests & biomarkers →
Study details
- Evidence strengthLow
How this study scored 36/100
Published in a peer-reviewed journal. Scored zero for study design, sample size, effect reported, studied in people and randomised / blinded because the record does not state it.
| Component | Points | Why |
|---|---|---|
| Journal tier | 7 / 10 | Tier 3 — peer-reviewed journal (Nuclear medicine and molecular imaging) |
| Journal's citation record | 0 / 4 | Nuclear Medicine and Molecular Imaging: journal h-index 43 (OpenAlex, 2026-10-29) |
| Study design | 0 / 12 | No study design recorded — scores zero, not guessed (not stated in the record — scored 0) |
| Strength of evidence | 1 / 5 | Rated “low” in our summary |
| Peer-review validation | 10 / 10 | Peer-reviewed. Published as an article in a named peer-reviewed journal. |
| How recent | 2 / 5 | 2019 — within 10 year(s) of the newest study here |
| Sample size | 0 / 4 | Participant count not stated — scores zero (not stated in the record — scored 0) |
| Effect reported | 0 / 3 | No effect size reported — scores zero (not stated in the record — scored 0) |
| Studied in people | 0 / 3 | Not stated whether this was studied in people — scores zero (not stated in the record — scored 0) |
| Randomised / blinded | 0 / 2 | No randomisation or blinding stated — scores zero (not stated in the record — scored 0) |
| Times cited | 3 / 7 | Cited 35 times (OpenAlex, 2026-10-10) |
| Citations per year | 2 / 5 | 3.9 citations a year over 9 year(s) since 2019 |
| Impact for its field and year | 3 / 6 | Cited 3.7× the average for papers of its field and year (OpenAlex FWCI) |
| Cited by studies here | 1 / 6 | Cited by 2 other studies in this library |
| Still being cited | 1 / 4 | Cited 9 times in 2024–2026 (2026 still in progress; OpenAlex) |
| Senior author's track record | 2 / 4 | Last-listed author Dong Soo Lee: h-index 40 (OpenAlex, whole career) |
| Institution's track record | 1 / 3 | Seoul National University: institution h-index 1,053 (OpenAlex) |
| Multi-centre collaboration | 1 / 3 | OpenAlex lists 2 institution(s) in 1 country |
| Indexed in PubMed | 2 / 2 | Indexed in PubMed (PMID 31723364) |
| Free to read | 0 / 2 | Behind a paywall — scores zero |
| Total | 36 / 100 | — |
What each of these 20 components measures, and what this score is not →
Read the original
Full text: free to read — PubMed Central lists this copy as free to read: the link above (checked 10 Oct 2026).
Studies this one cites
Referenced by this study and also in the alzhub library, so you can read them here.
Later studies that cite this one
2 studies in the alzhub library list this one in their references.
Related studies in Biomarkers
Also tagged “classification”
835 studies in the library carry the topic tag “classification”; these are this study's neighbours in a fixed, alphabetical-by-hash tour of them, not the closest in content. All 835 tagged studies.