Semi-automatic Brain Tumor Segmentation by Drawing Long Axes on Multi-plane Reformat

A semi-automatic image segmentation method, called SAMBAS, based on workflow familiar to clinical radiologists is described. The user initializes 3D segmentation by drawing a long axis on a multi-plane reformat (MPR). As the user draws, a 2D segmentation updates in real-time for interactive feedback. When necessary, additional long axes, short axes, or other editing operations may be drawn on one or more MPR planes. The method learns probability distributions from the drawing to perform the MPR segmentation, and in turn, it learns from the MPR segmentation to perform the 3D segmentation. As a preliminary experiment, a batch simulation was performed where long and short axes were automatically drawn on each of 285 multispectral MR brain scans of glioma patients in the 2018 BraTS Challenge training data. Average Dice coefficient for tumor core was 0.86, and the Hausdorff-95% distance was 4.4 mm. As another experiment, a convolution neural network was trained on the same data, and applied to the BraTS validation and test data. Its outputs, computed offline, were integrated into the interactive method. Ten volunteers used the interface on the BraTS validation and test data. On the 66 scans of the validation data, average Dice coefficient for core tumor improved from 0.76 with deep learning alone, to 0.82 as an interactive system.