{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/attention-gated-networks-learning-to-leverage","title":"Attention Gated Networks: Learning to Leverage Salient Regions in Medical Images","arxiv_id":"1808.08114","date":"2018-08-22","proceeding":null,"authors":["Jo Schlemper","Ozan Oktay","Michiel Schaap","Mattias Heinrich","Bernhard Kainz","Ben Glocker","Daniel Rueckert"],"abstract":"We propose a novel attention gate (AG) model for medical image analysis that\nautomatically learns to focus on target structures of varying shapes and sizes.\nModels trained with AGs implicitly learn to suppress irrelevant regions in an\ninput image while highlighting salient features useful for a specific task.\nThis enables us to eliminate the necessity of using explicit external\ntissue/organ localisation modules when using convolutional neural networks\n(CNNs). AGs can be easily integrated into standard CNN models such as VGG or\nU-Net architectures with minimal computational overhead while increasing the\nmodel sensitivity and prediction accuracy. The proposed AG models are evaluated\non a variety of tasks, including medical image classification and segmentation.\nFor classification, we demonstrate the use case of AGs in scan plane detection\nfor fetal ultrasound screening. We show that the proposed attention mechanism\ncan provide efficient object localisation while improving the overall\nprediction performance by reducing false positives. For segmentation, the\nproposed architecture is evaluated on two large 3D CT abdominal datasets with\nmanual annotations for multiple organs. Experimental results show that AG\nmodels consistently improve the prediction performance of the base\narchitectures across different datasets and training sizes while preserving\ncomputational efficiency. Moreover, AGs guide the model activations to be\nfocused around salient regions, which provides better insights into how model\npredictions are made. The source code for the proposed AG models is publicly\navailable.","url_abs":"http://arxiv.org/abs/1808.08114v2","url_pdf":"http://arxiv.org/pdf/1808.08114v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"attention-gated-networks-learning-to-leverage","repo_url":"https://github.com/iversonicter/Learn-to-pay-attention","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"attention-gated-networks-learning-to-leverage","repo_url":"https://github.com/wangyongjie-ntu/Learn-to-pay-attention","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"computational-efficiency","task_name":"Computational Efficiency"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"medical-image-analysis","task_name":"Medical Image Analysis"},{"task_slug":"medical-image-classification","task_name":"Medical Image Classification"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1808.08114","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}