Biomedical Image Segmentation by Retina-like Sequential Attention Mechanism Using Only A Few Training Images
This addresses the challenge of accurate segmentation in biomedical imaging when only a few training images are available, representing an incremental advance in method design.
The paper tackles biomedical image segmentation with limited training data by introducing a retina-like sequential attention mechanism that focuses on difficult subareas at higher resolution, achieving improved accuracy over patch-based and fully convolutional methods.
In this paper we propose a novel deep learning-based algorithm for biomedical image segmentation which uses a sequential attention mechanism able to shift the focus of attention across the image in a selective way, allowing subareas which are more difficult to classify to be processed at increased resolution. The spatial distribution of class information in each subarea is learned using a retina-like representation where resolution decreases with distance from the center of attention. The final segmentation is achieved by averaging class predictions over overlapping subareas, utilizing the power of ensemble learning to increase segmentation accuracy. Experimental results for semantic segmentation task for which only a few training images are available show that a CNN using the proposed method outperforms both a patch-based classification CNN and a fully convolutional-based method.