Quantitative evaluation of unsupervised clustering algorithms for dynamic total-body PET image analysis

TL;DR

This study systematically evaluates 15 unsupervised clustering algorithms for classifying dynamic total-body PET image time activity curves, identifying GMM, FCM, and ICA with mini batch K-means as the most effective methods.

Contribution

It provides a comprehensive comparison of clustering algorithms specifically for dynamic total-body PET image analysis, highlighting the most accurate and efficient methods.

Findings

GMM, FCM, and ICA with mini batch K-means achieved median accuracies of 89%, 83%, and 81%.

The best algorithms processed each image in half a second or less.

The study offers guidance for selecting clustering methods in PET image analysis.

Abstract

Background. Recently, dynamic total-body positron emission tomography (PET) imaging has become possible due to new scanner devices. While clustering algorithms have been proposed for PET analysis already earlier, there is still little research systematically evaluating these algorithms for processing of dynamic total-body PET images. Materials and methods. Here, we compare the performance of 15 unsupervised clustering methods, including K-means either by itself or after principal component analysis (PCA) or independent component analysis (ICA), Gaussian mixture model (GMM), fuzzy c-means (FCM), agglomerative clustering, spectral clustering, and several newer clustering algorithms, for classifying time activity curves (TACs) in dynamic PET images. We use dynamic total-body $^{15}$O-water PET images collected from 30 patients with suspected or confirmed coronary artery disease. To evaluate the clustering algorithms in a quantitative way, we use them to classify 5000 TACs from each image based on whether the curve is taken from brain, right heart ventricle, right kidney, lower right lung lobe, or urinary bladder. Results. According to our results, the best methods are GMM, FCM, and ICA combined with mini batch K-means, which classified the TACs with a median accuracies of 89\%, 83\%, and 81\%, respectively, in a processing time of half a second or less on average for each image. Conclusion. GMM, FCM, and ICA with mini batch K-means show promise for dynamic total-body PET analysis.