InfiNet: Fully Convolutional Networks for Infant Brain MRI Segmentation
This addresses the problem of efficient and accurate brain segmentation for infants in medical imaging, though it appears incremental as it builds on existing fully convolutional architectures with a novel upsampling approach.
The authors tackled infant brain MRI segmentation at the iso-intense stage by developing InfiNet, a fully convolutional network with double encoder arms for T1 and T2 scans, achieving whole-volume segmentation in under 50 seconds and demonstrating competitive performance against state-of-the-art methods.
We present a novel, parameter-efficient and practical fully convolutional neural network architecture, termed InfiNet, aimed at voxel-wise semantic segmentation of infant brain MRI images at iso-intense stage, which can be easily extended for other segmentation tasks involving multi-modalities. InfiNet consists of double encoder arms for T1 and T2 input scans that feed into a joint-decoder arm that terminates in the classification layer. The novelty of InfiNet lies in the manner in which the decoder upsamples lower resolution input feature map(s) from multiple encoder arms. Specifically, the pooled indices computed in the max-pooling layers of each of the encoder blocks are related to the corresponding decoder block to perform non-linear learning-free upsampling. The sparse maps are concatenated with intermediate encoder representations (skip connections) and convolved with trainable filters to produce dense feature maps. InfiNet is trained end-to-end to optimize for the Generalized Dice Loss, which is well-suited for high class imbalance. InfiNet achieves the whole-volume segmentation in under 50 seconds and we demonstrate competitive performance against multiple state-of-the art deep architectures and their multi-modal variants.