Multi-stream 3D FCN with Multi-scale Deep Supervision for Multi-modality Isointense Infant Brain MR Image Segmentation
This addresses a challenging medical imaging problem for infant brain analysis, with incremental improvements in segmentation accuracy.
The paper tackles segmentation of multi-modality isointense infant brain MR images into white matter, gray matter, and cerebrospinal fluid, achieving average Dice Overlap Coefficients of 95.4%, 91.6%, and 89.6% respectively on the iSeg-2017 test data.
We present a method to address the challenging problem of segmentation of multi-modality isointense infant brain MR images into white matter (WM), gray matter (GM), and cerebrospinal fluid (CSF). Our method is based on context-guided, multi-stream fully convolutional networks (FCN), which after training, can directly map a whole volumetric data to its volume-wise labels. In order to alleviate the poten-tial gradient vanishing problem during training, we designed multi-scale deep supervision. Furthermore, context infor-mation was used to further improve the performance of our method. Validated on the test data of the MICCAI 2017 Grand Challenge on 6-month infant brain MRI segmentation (iSeg-2017), our method achieved an average Dice Overlap Coefficient of 95.4%, 91.6% and 89.6% for CSF, GM and WM, respectively.