bioRxiv2023
AO_SCPLOWBSTRACTC_SCPLOWClustering time activity curves of PET images has been used to separate clinically relevant areas of the brain or tumours. However, PET image segmentation in multi-organ level is 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. Our focus is on general-purpose unsupervised methods that are independent of external data and can be used for all tracers, organisms, and health conditions. Additional anatomical image modalities, such as CT or MRI, are not used, but the segmentation is done purely based on the dynamic PET images. The tested methods are commonly used building blocks of the more sophisticated methods rather than final methods as such, and our goal is to evaluate if these basic tools are suited for the arising human total-body PET image segmentation. 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, leaving only two clustering methods, k-means and Gaussian mixture model (GMM), for further analyses. We combined k-means with two different pre-processings, namely principal component analysis (PCA) and independent component analysis (ICA). Then we selected a suitable number of clusters using 10 images. Finally, we tested how well the usable approaches segment the remaining PET images in organ level, highlight the best approaches together with their limitations, and discuss how further research could tackle the observed shortcomings. In this study, we utilised 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 ICA combined with k-means has weaker performance than the other two computationally usable approaches and that certain organs are easier to segment than others. While GMM performed sufficiently, it was by far the slowest one among the tested approaches, making k-means combined with PCA the most promising candidate for further development. However, even with the best methods the mean Jaccard index was slightly below 0.5 for the easiest tested organ and below 0.2 for the most challenging organ. Thus, we conclude that there is a lack of accurate and computationally light general-purpose segmentation method that can analyse dynamic total-body PET images. Key pointsO_LIMajority of the considered clustering methods were computationally too intense even for our total-body rat images. The coming total-body human images are 10-fold bigger. C_LIO_LIHeterogeneous VOIs like brain require more sophisticated segmentation method than the basic clustering tested here. C_LIO_LIPCA combined with k-means had the best balance between performance and running speed among the tested methods, but without further preprocessing, it is not accurate enough for practical applications. C_LI FundingResearch of both first authors was supported by donation funds of Faculty of Medicine at University of Turku. JCH reports funding from The Academy of Finland (decision 317332), the Finnish Cultural Foundation, the Finnish Cultural Foundation Varsinais-Suomi Regional Fund, the Diabetes Research Foundation of Finland, and State Research Funding/Hospital District of Southwest Finland. KAV report funding from The Academy of Finland (decision 343410), Sigrid Juselius Foundation and State Research Funding/Hospital District of Southwest Finland. JH reports funding from The Finnish Cultural Foundation Varsinais-Suomi Regional Fund. These funding sources do not present any conflict of interest. Data availabilityThe codes used in this study are available from Github page https://github.com/rklen/Dynamic_FDG_PET_clustering. The example data used in this study have not been published at the time of writing.