Class Balanced PixelNet for Neurological Image Segmentation
This work addresses automatic segmentation for neurological images, which is incremental as it builds on existing CNN methods with specific improvements for medical data challenges.
The paper tackles brain tumor segmentation by proposing PixelNet, a pixel-level CNN that uses hyper-columns and balanced pixel sampling to address spatial redundancy and class imbalance, achieving promising results on medical datasets.
In this paper, we propose an automatic brain tumor segmentation approach (e.g., PixelNet) using a pixel-level convolutional neural network (CNN). The model extracts feature from multiple convolutional layers and concatenate them to form a hyper-column where samples a modest number of pixels for optimization. Hyper-column ensures both local and global contextual information for pixel-wise predictors. The model confirms the statistical efficiency by sampling a few pixels in the training phase where spatial redundancy limits the information learning among the neighboring pixels in conventional pixel-level semantic segmentation approaches. Besides, label skewness in training data leads the convolutional model often converge to certain classes which is a common problem in the medical dataset. We deal with this problem by selecting an equal number of pixels for all the classes in sampling time. The proposed model has achieved promising results in brain tumor and ischemic stroke lesion segmentation datasets.