Additional file 1: of Automatic segmentation and classification of breast lesions through identification of informative multiparametric PET/MRI features

Figure S1. Illustration of the influence of logistic model parameters on curve, and the model fitted to a CKC. From left to right: α defines the asymmetry of the logistic model, τ the steepness of the curve and k influences the terminal slope. The regression curve fitted to a given CKC for a malignant (blue) and a benign lesion (green). Figure S2. Boxplot of automatic segmentation performance in terms of Dice similarity coefficient (DSC). DWI, diffusion-weighted imaging; GI, Gini Importance; mRMR, minimum-Redundancy-Maximum-Relevance; PET, positron emission tomography; w/o, without. (DOCX 219 kb)