AGD-Autoencoder: Attention Gated Deep Convolutional Autoencoder for Brain Tumor Segmentation
AbstractBrain tumor segmentation is a challenging problem in medical image analysis. The endpoint is to generate the salient masks that accurately identify brain tumor regions in an fMRI screening. In this paper, we propose a novel attention gate (AG model) for brain tumor segmentation that utilizes both the edge detecting unit and the attention gated network to highlight and segment the salient regions from fMRI images. This feature enables us to eliminate the necessity of having to explicitly point towards the damaged area (external tissue localization) and classify (classification) as per classical computer vision techniques. In order to provide the useful constraints to guide feature extraction, we incoorporate the edge attention-gated unit. The explicit edge-attention unit is devoted to model the image boundaries as well as enhancing the representation. AGs can easily be integrated within the deep convolutional neural networks (CNNs). Minimal computional overhead is required while the AGs increase the sensitivity scores significantly. We show that the edge detector along with an attention gated mechanism provide a suffcient enough method for brain segmentation reaching an IOU of 0.78. With this methodology, we attempt to bring deep learning closer to the hands of human level performance providing useful information to the process of diagnosis.