Fig. 2From: Deep convolutional neural networks for automated segmentation of brain metastases trained on clinical dataSensitivity and Specificity of the developed networks plotted against the minimum volume of the considered target lesions. Dashed lines depict the four quartiles (Qi) of the measured volumes of target lesions in the test data (Q1 = 0.06 ml, Q2 = 0.29 ml, Q3 = 1.29 ml, Q4 = 8.05 ml). The largest drop in both sensitivity and specificity is observed for lesions smaller than 0.06 ml. At this threshold the sensitivities and specificities are 0.97/0.92 and 0.92/1.00 for NetSUM and NetMV respectivelyBack to article page