FU-net: Multi-class Image Segmentation Using Feedback Weighted U-net
This work addresses segmentation challenges in medical imaging, such as brain MRI, where class imbalance is common, but it is incremental, building on existing U-net architectures.
The paper tackles multi-class image segmentation with class imbalance by proposing FU-net, which introduces a dynamically weighted cross-entropy loss based on pixel-wise prediction accuracy, and it outperforms baseline models like U-net and BRU-net in dice coefficient, especially with limited training data.
In this paper, we present a generic deep convolutional neural network (DCNN) for multi-class image segmentation. It is based on a well-established supervised end-to-end DCNN model, known as U-net. U-net is firstly modified by adding widely used batch normalization and residual block (named as BRU-net) to improve the efficiency of model training. Based on BRU-net, we further introduce a dynamically weighted cross-entropy loss function. The weighting scheme is calculated based on the pixel-wise prediction accuracy during the training process. Assigning higher weights to pixels with lower segmentation accuracies enables the network to learn more from poorly predicted image regions. Our method is named as feedback weighted U-net (FU-net). We have evaluated our method based on T1- weighted brain MRI for the segmentation of midbrain and substantia nigra, where the number of pixels in each class is extremely unbalanced to each other. Based on the dice coefficient measurement, our proposed FU-net has outperformed BRU-net and U-net with statistical significance, especially when only a small number of training examples are available. The code is publicly available in GitHub (GitHub link: https://github.com/MinaJf/FU-net).