Multimodal MRI brain tumor segmentation using random forests with features learned from fully convolutional neural network
This work addresses brain tumor segmentation for medical imaging analysis, presenting an incremental improvement by integrating learned and hand-crafted features.
The paper tackled automated brain tumor segmentation in multimodal MRI images by combining features from a fully convolutional neural network and hand-designed textons with random forests, achieving Dice scores of 0.88, 0.80, and 0.73 for complete tumor, core, and enhancing tumor, respectively.
In this paper, we propose a novel learning based method for automated segmenta-tion of brain tumor in multimodal MRI images. The machine learned features from fully convolutional neural network (FCN) and hand-designed texton fea-tures are used to classify the MRI image voxels. The score map with pixel-wise predictions is used as a feature map which is learned from multimodal MRI train-ing dataset using the FCN. The learned features are then applied to random for-ests to classify each MRI image voxel into normal brain tissues and different parts of tumor. The method was evaluated on BRATS 2013 challenge dataset. The results show that the application of the random forest classifier to multimodal MRI images using machine-learned features based on FCN and hand-designed features based on textons provides promising segmentations. The Dice overlap measure for automatic brain tumor segmentation against ground truth is 0.88, 080 and 0.73 for complete tumor, core and enhancing tumor, respectively.