Neural networks combined with region growing techniques for tumor detection in [18F]-fluorothymidine dynamic positron emission tomography breast cancer studies

Early detection and precise localization of malignant tumors has been a primary challenge in medical imaging in recent years. Functional modalities play a continuously increasing role in these efforts. Image segmentation algorithms which enable automatic, accurate tumor visualization and quantification on noisy positron emission tomography (PET) images would significantly improve the quality of treatment planning processes and in turn, the success of treatments. In this work a novel multistep method has been applied in order to identify tumor regions in 4D dynamic [F-18] fluorothymidine (FLT) PET studies of patients with locally advanced breast cancer. In order to eliminate the effect of inherently detectable high inhomogeneity inside tumors, specific voxel-kinetic classes were initially introduced by finding characteristic FLT-uptake curves with K-means algorithm on a set of voxels collected from each tumor. Image voxel sets were then split based on voxel time-activity curve (TAC) similarities, and models were generated separately on each voxel set. At first, artificial neural networks, in comparison with linear classification algorithms were applied to distinguish tumor and healthy regions relying on the characteristics of TACs of the individual voxels. The outputs of the best model with very high specificity were then used as input seeds for region shrinking and growing techniques, the application of which considerably enhanced the sensitivity and specificity (78.65% +/- 0.65% and 98.98% +/- 0.03%, respectively) of the final image segmentation model.