Leveraging healthy population variability in deep learning unsupervised anomaly detection in brain FDG PET

Maëlys Solal; Ravi Hassanaly; Ninon Burgos

doi:10.1117/12.2691683

2 April 2024 Leveraging healthy population variability in deep learning unsupervised anomaly detection in brain FDG PET

Maëlys Solal, Ravi Hassanaly, Ninon Burgos

Proceedings Volume 12926, Medical Imaging 2024: Image Processing; 129261F (2024) https://doi.org/10.1117/12.2691683
Event: SPIE Medical Imaging, 2024, San Diego, California, United States

Conference Poster

Abstract

Unsupervised anomaly detection is a popular approach for the analysis of neuroimaging data as it allows identifying a wide variety of anomalies from unlabelled data. It relies on reconstructing a subject-specific model of healthy appearance to which a subject’s image can be compared to detect anomalies. In the literature, it is common for anomaly detection to rely on analysing the residual image between the subject’s real image and its pseudo-healthy reconstruction. This approach however has limitations partly due to the pseudo-healthy reconstructions being imperfect and to the lack of natural thresholding mechanism. Our proposed method, inspired by Z-scores, leverages the healthy population variability to overcome these limitations. Our experiments conducted on 3D FDG PET scans from the ADNI database demonstrate the effectiveness of our approach in accurately identifying simulated Alzheimer’s disease related anomalies.

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Maëlys Solal, Ravi Hassanaly, and Ninon Burgos "Leveraging healthy population variability in deep learning unsupervised anomaly detection in brain FDG PET", Proc. SPIE 12926, Medical Imaging 2024: Image Processing, 129261F (2 April 2024); https://doi.org/10.1117/12.2691683

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available