Ensemble of Multi-sized FCNs to Improve White Matter Lesion Segmentation
This work addresses a domain-specific medical imaging problem for improved lesion detection, representing an incremental advancement.
The paper tackles white-matter lesion segmentation in brain MR scans by developing a two-stage neural network with multi-sized patches and a novel activation function, achieving effective results as demonstrated on the MICCAI 2017 WMH Segmentation Challenge data.
In this paper, we develop a two-stage neural network solution for the challenging task of white-matter lesion segmentation. To cope with the vast vari- ability in lesion sizes, we sample brain MR scans with patches at three differ- ent dimensions and feed them into separate fully convolutional neural networks (FCNs). In the second stage, we process large and small lesion separately, and use ensemble-nets to combine the segmentation results generated from the FCNs. A novel activation function is adopted in the ensemble-nets to improve the segmen- tation accuracy measured by Dice Similarity Coefficient. Experiments on MICCAI 2017 White Matter Hyperintensities (WMH) Segmentation Challenge data demonstrate that our two-stage-multi-sized FCN approach, as well as the new activation function, are effective in capturing white-matter lesions in MR images.