Comparison of five cluster validity indices performance in brain [18 F]FET-PET image segmentation using k-means.

PURPOSE: Dynamic [18 F]fluoro-ethyl-L-tyrosine positron emission tomography ([18 F]FET-PET) is used to identify tumor lesions for radiotherapy treatment planning, to differentiate glioma recurrence from radiation necrosis and to classify gliomas grading. To segment different regions in the brain k-means cluster analysis can be used. The main disadvantage of k-means is that the number of clusters must be pre-defined. In this study, we therefore compared different cluster validity indices for automated and reproducible determination of the optimal number of clusters based on the dynamic PET data. METHODS: The k-means algorithm was applied to dynamic [18 F]FET-PET images of 8 patients. Akaike information criterion (AIC), WB, I, modified Dunn's and Silhouette indices were compared on their ability to determine the optimal number of clusters based on requirements for an adequate cluster validity index. To check the reproducibility of k-means, the coefficients of variation CVs of the objective function values OFVs (sum of squared Euclidean distances within each cluster) were calculated using 100 random centroid initialization replications RCI100 for 2 to 50 clusters. k-means was performed independently on three neighboring slices containing tumor for each patient to investigate the stability of the optimal number of clusters within them. To check the independence of the validity indices on the number of voxels, cluster analysis was applied after duplication of a slice selected from each patient. CVs of index values were calculated at the optimal number of clusters using RCI100 to investigate the reproducibility of the validity indices. To check if the indices have a single extremum, visual inspection was performed on the replication with minimum OFV from RCI100 . RESULTS: The maximum CV of OFVs was 2.7 × 10-2 from all patients. The optimal number of clusters given by modified Dunn's and Silhouette indices was 2 or 3 leading to a very poor segmentation. WB and I indices suggested in median 5, [range 4-6] and 4, [range 3-6] clusters, respectively. For WB, I, modified Dunn's and Silhouette validity indices the suggested optimal number of clusters was not affected by the number of the voxels. The maximum coefficient of variation of WB, I, modified Dunn's, and Silhouette validity indices were 3 × 10-2 , 1, 2 × 10-1 and 3 × 10-3 , respectively. WB-index showed a single global maximum, whereas the other indices showed also local extrema. CONCLUSION: From the investigated cluster validity indices, the WB-index is best suited for automated determination of the optimal number of clusters for [18 F]FET-PET brain images for the investigated image reconstruction algorithm and the used scanner: it yields meaningful results allowing better differentiation of tissues with higher number of clusters, it is simple, reproducible and has an unique global minimum.

Effect of reconstruction parameters in high-definition PET/CT on assessment of lymph node metastases in head and neck squamous cell carcinoma.

UNLABELLED: Therapy outcome and overall survival in patients with head and neck squamous cell carcinoma (HNSCC) is influenced by precise localization of the primary tumor and detection of lymph node metastasis involvement at the time of initial diagnosis. Only accurate preoperative staging can improve primary tumor response and avoid early locoregional recurrence with lymph node metastases. The purpose of this study was the optimization of reconstruction parameters in high-definition PET/CT for the improved diagnostic assessment of lymph node metastases. METHODS: In the experimental study, image contrast and signal-to-noise ratio were evaluated using a Jaszczak phantom. In the clinical study, 54 patients underwent head and neck imaging on a PET/CT scanner. Diagnostic findings were correlated with postoperative histopathology. For the 54 patients, 123 lymph nodes were evaluated on PET and histologically correlated with the neck dissection specimen. Forty-one lymph nodes were benign, and 82 findings were confirmed as being malignant. Both experimental and clinical studies were reconstructed into a 200 × 200 matrix using a 3-dimensional iterative reconstruction algorithm (ordered-subset expectation maximization [OSEM], 3 iterative steps, 24 subsets). Postfiltering with a 3-dimensional gaussian filter was applied. To study the effect of smoothing filter strength on the diagnostic accuracy of lymph node metastasis detection, 3 different cutoffs-1, 3, and 6 mm in full width at half maximum-were used to perform reconstructions. RESULTS: Phantom studies showed that images reconstructed with 3-mm gaussian postfiltering gained a higher image quality and signal-to-noise ratio. Overall sensitivities for correctly diagnosed lymph nodes were best in 3-mm postfiltered images. Best results for true-positive lymph node findings were achieved with 3-mm postfiltering. With 1-mm postfiltering, accurate lesion detection was not improved, because increasing sensitivity (95% true-positive) correlated with decreasing specificity (12% false-positive). CONCLUSION: For lymph node assessment on a high-resolution PET/CT scanner, we consider the OSEM algorithm with 3 iterations and 24 subsets, combined with 3-dimensional 3-mm gaussian postfiltering, to be optimal. The continuous application of presently established PET protocols in patients with HNSCC will prove whether current acquisition and reconstruction methods are valuable and should be maintained.