Leveraging healthy population variability in deep learning unsupervised anomaly detection in brain FDG PET
This is an incremental improvement for neuroimaging researchers and clinicians analyzing brain anomalies, specifically in Alzheimer's disease detection.
The paper tackled the problem of imperfect pseudo-healthy reconstructions and lack of natural thresholding in unsupervised anomaly detection for brain FDG PET scans by proposing a method inspired by Z-scores that leverages healthy population variability. The result demonstrated effectiveness in accurately identifying Alzheimer's disease related anomalies on the ADNI database.
Unsupervised anomaly detection is a popular approach for the analysis of neuroimaging data as it allows to identify a wide variety of anomalies from unlabelled data. It relies on building 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 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 FDG PET scans from the ADNI database demonstrate the effectiveness of our approach in accurately identifying Alzheimer's disease related anomalies.