SEGMENTATION OF DYNAMIC TOTAL-BODY -FDG PET IMAGES USING UNSUPERVISED CLUSTERING
02:06 Share

Link to bioRxiv paper: http://biorxiv.org/cgi/content/short/2023.06.20.545535v1?rss=1

Authors: Jaakkola, M. K., Rantala, M., Jalo, A., Saari, T., Hentila, J., Helin, J. S., Nissinen, T. A., Eskola, O., Rajander, J., Virtanen, K. A., Hannukainen, J. C., Lopez-Picon, F., Klen, R.

Abstract: Clustering time activity curves of PET images has been used to separate clinically relevant areas of the brain or tumours. However, such applications on segmenting PET images in organ level are much less studied due to the available total-body data being limited to animal studies. Now the new PET scanners providing the opportunity to acquire total-body PET scans also from humans are becoming more common, which opens plenty of new clinically interesting opportunities. Therefore, organ level segmentation of PET images has important applications, yet it lacks sufficient research. In this proof of concept study, we evaluate if the previously used segmentation approaches are suitable for segmenting dynamic human total-body PET images in organ level. First we excluded methods that were computationally too demanding for the large datasets from human total-body PET scanners. This criteria filtered out most of the commonly used approaches. Then we tested how well the usable methods segment PET images in organ level, highlight the best approaches together with their limitations, and discuss how further research could tackle the observed shortcomings. We used 40 total-body [18F]fluorodeoxyglucose PET images of rats to mimic the coming large human PET images and a few actual human total-body images to ensure that our conclusions from the rat data generalise to the human data. Our results show that independent component analysis has weaker performance than the other two computationally usable approaches and that certain organs are easier to segment than others. While Gaussian mixture model performed sufficiently, it was by far the slowest one among the tested methods, making k-means combined with principal component analysis the most promising candidate for further development.

Copy rights belong to original authors. Visit the link for more info

Podcast created by Paper Player, LLC