Comparative assessment of segmentation algorithms for tumor delineation on a test-retest 11Ccholine dataset

Abstract

Purpose: Many methods have been proposed for tumor segmentation from positron emission tomography images. Because of the increasingly important role that 11C choline is playing in oncology and because no study has compared segmentation methods on this tracer, the authors assessed several segmentation algorithms on a 11C choline test-retest dataset. Methods: Fixed and adaptive threshold-based methods, fuzzy C-means (FCM), Cannys edge detection method, the watershed transform, and the fuzzy locally adaptive Bayesian algorithm (FLAB) were used. Test-retest 11C choline scans of nine patients with breast cancer were considered and the percent test-retest variability VAR TEST-RETEST of tumor volume (TV) was employed to assess the results. The same methods were then applied to two denoised datasets generated by applying either a Gaussian filter or the wavelet transform. Results: The (semi)automated methods FCM, FLAB, and Canny emerged as the best ones in terms of TV reproducibility. For these methods, the root mean square error RMSE of VAR TEST-RETEST, defined as % RMSE = variance + mean 2, was in the range 10-21.2, depending on the dataset and algorithm. Threshold-based methods gave TV estimates which were extremely variable, particularly on the unsmoothed data; their performance improved on the denoised datasets, whereas smoothing did not have a remarkable impact on the (semi)automated methods. TV variability was comparable to that of SUVMAX and SUVMEAN (range 14.7-21.9 for RMSE of VAR TEST-RETEST, after the exclusion of one outlier, 40-43 when the outlier was included). Conclusions: The TV variability obtained with the best methods was similar to the one reported for TV in previous 18FFDG and 18FFLT studies and to the one of SUVMAXSUVMEAN on the authors' 11Ccholine dataset. The good reproducibility of 11Ccholine TV warrants further studies to test whether TV could predict early response to treatment and survival, as for 18FFDG, to complementsubstitute the use of SUVMAX and SUVMEAN. © 2012 American Association of Physicists in Medicine.