An interventional study of Neurophet SCALE PET in Alzheimer's Disease (AD) and Mild Cognitive Impairment (MCI), sponsored by NEUROPHET. Completed at 1 site in South Korea. Open to participants aged 50 Years and older. Per ClinicalTrials.gov, last updated 2026-02-18.
Sponsored by NEUROPHET · Not applicable, Interventional, and Diagnostic
The goal of this study is to learn if medical image analysis software, Neurophet SCALE PET, can enhance readers' amyloid beta positivity performance in people with Alzheimer's Disease. The main question it aims to answer is:
Does the use of medical image analysis software assistance result in a statistically significant difference in readers' sensitivity and specificity for the classification of amyloid-β (Aβ) positivity?
Four readers will interpret amyloid PET images in two sessions (with and without software assistance), separated by a 4-week washout period, and will record Aβ positivity and diagnostic confidence using predefined rating scales.
Data Collection and Reference Standard The investigators will retrospectively collect medical data from a total of 194 patients (97 Aβ-positive and 97 Aβ-negative cases).
Data Sources: De-identified data will be obtained from Ajou University Hospital and the Alzheimer's Disease Neuroimaging Initiative (ADNI) database.
Study Procedures (Reader Study) The reader study consists of two main reading sessions separated by a 4-week washout period to minimize memory bias and order effects. Four readers will be randomly assigned to two groups (Reader Group 1 and Reader Group 2).
During each session, readers will rate Aβ positivity on a 5-point scale (1: Definitely negative, 2: Probably negative, 3: Equivocal, 4: Probably positive, 5: Definitely positive) and record their diagnostic confidence level on a 3-point scale (1: low confidence, 2: moderate confidence, 3: high confidence).
Statistical Analysis The efficacy of the software will be assessed by comparing the diagnostic performance between the SW-assisted and unassisted conditions.
3,678 studies on the registry are indexed under Alzheimer Disease; 872 are open to participants now.
This study's enrollment of 190 is above the median of 70 across 2,808 interventional studies indexed under Alzheimer Disease.
Browse Alzheimer Disease studies →NEUROPHET is the lead sponsor of 3 studies on the registry; 2 are open to participants now.
Counted across the registry records on this site, refreshed daily.
Inclusion Criteria: Medical imaging datasets meeting all of the following criteria will be eligible for inclusion in this study.
Participants meeting one of the following predefined groups based on prior visual interpretation of amyloid PET:
Exclusion Criteria: Medical imaging datasets meeting any of the following criteria will be excluded from the study.
In Session 1, readers in this group interpret Case Group A with software (SW) assistance and Case Group B without assistance (visual read). Following a 4-week washout period, the conditions are swapped for Session 2: readers interpret Case Group A without SW assistance and Case Group B with SW assistance.
Device: Neurophet SCALE PET
In Session 1, readers in this group interpret Case Group B with software (SW) assistance and Case Group A without assistance (visual read). Following a 4-week washout period, the conditions are swapped for Session 2: readers interpret Case Group B without SW assistance and Case Group A with SW assistance.
Device: Neurophet SCALE PET
Neurophet SCALE PET is an artificial intelligence-based medical image analysis software designed for the quantitative analysis of brain PET images. It provides automated quantification of amyloid-beta (Aβ) deposition using standardized uptake value ratios (SUVR) and the Centiloid scale. In this study, the software is used as a diagnostic support tool to assist clinicians in evaluating Aβ positivity.
Difference in readers' sensitivity in SW-assisted vs. unassisted classification of Aβ positivity
Comparison of the sensitivity for amyloid-beta positivity between the software-assisted and unassisted reading conditions, based on the expert-established reference standard.
Time frame: At the completion of two reading sessions (approximately 3 months)
Difference in readers' specificity in SW-assisted vs. unassisted classification of Aβ positivity
Comparison of the specificity for amyloid-beta negativity between the software-assisted and unassisted reading conditions, based on the expert-established reference standard.
Time frame: At the completion of the reading study (approximately 3 months)
Difference in readers' diagnostic accuracy in SW-assisted vs. unassisted classification of Aβ positivity
The difference in diagnostic accuracy is evaluated using the Area Under the Receiver Operating Characteristic (ROC) Curve (AUC).
Time frame: At the completion of the reading study (approximately 3 months)
Difference in number of cases rated as equivocal in SW-assisted vs. unassisted classification of Aβ positivity
Comparison of the frequency of cases rated as "3: Equivocal" on the 5-point scale between the software-assisted and unassisted conditions.
Time frame: At the completion of the reading study (approximately 3 months)
Difference in confidence level of readers in SW-assisted vs. unassisted classification of Aβ positivity
Comparison of the readers' self-reported confidence levels when making a diagnosis
Time frame: At the completion of the reading study (approximately 3 months)
Inter-rater Agreement
Evaluation of the consistency in amyloid-beta positivity ratings among the four readers
Time frame: At the completion of the reading study (approximately 3 months)
Number of analysis failure cases
The number of cases where the 'Neurophet SCALE PET' software fails to complete the automated quantitative analysis or produces uninterpretable results due to technical errors, such as pre-processing failure or software crashes.
Time frame: At the completion of the reading study (approximately 3 months)
Plan to share: No
No publications or documents are linked to this record.
This study is completed, as verified in Feb 2026. You cannot join it, but the record below documents what was studied.
Get an email when the registry record changes — status, dates, results — or when someone posts here.
Sign in to followQuestions and observations about this study, from anyone following it. Not medical advice, and not a channel to the study team — their contact details are on the registry record.
Sign in to join the discussion. Reading takes no account; posting does. You choose a display name, and a pseudonym is the default.
Nothing here yet. If you are running this trial, taking part in it, or weighing whether to, this is the place to say so.
NEUROPHET