Fig. 7: Enhanced microtubule segmentation using DeePiCt. | Communications Biology

Fig. 7: Enhanced microtubule segmentation using DeePiCt.

From: cryoTIGER: deep-learning based tilt interpolation generator for enhanced reconstruction in cryo electron tomography

Fig. 7

A Representative tomogram slice with arrows indicating the positions of microtubules (left). The corresponding ground truth segmentation is depicted in white (middle), alongside a 2D projection of the GT segmented 3D volume for visualization (right). B Comparison of the non-interpolated version (in cyan) with interpolation using the DL (Vimeo) model (in red) and the DL (cryo-ET) model (in green). C Overlap-based dice similarity coefficient for three tested tomograms, ranging from 0 (no overlap) to 1 (full overlap). D Overlap-based Jaccard Index for the same tomograms, also ranging from 0 to 1. E Hausdorff distance measuring how far the tested segmentation outlines are from the GT segmentation. Scale bar: 60 nm.

Back to article page