{"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/fast-capsnet-for-lung-cancer-screening","title":"Fast CapsNet for Lung Cancer Screening","arxiv_id":"1806.07416","date":"2018-06-19","proceeding":null,"authors":["Aryan Mobiny","Hien Van Nguyen"],"abstract":"Lung cancer is the leading cause of cancer-related deaths in the past several\nyears. A major challenge in lung cancer screening is the detection of lung\nnodules from computed tomography (CT) scans. State-of-the-art approaches in\nautomated lung nodule classification use deep convolutional neural networks\n(CNNs). However, these networks require a large number of training samples to\ngeneralize well. This paper investigates the use of capsule networks (CapsNets)\nas an alternative to CNNs. We show that CapsNets significantly outperforms CNNs\nwhen the number of training samples is small. To increase the computational\nefficiency, our paper proposes a consistent dynamic routing mechanism that\nresults in $3\\times$ speedup of CapsNet. Finally, we show that the original\nimage reconstruction method of CapNets performs poorly on lung nodule data. We\npropose an efficient alternative, called convolutional decoder, that yields\nlower reconstruction error and higher classification accuracy.","url_abs":"http://arxiv.org/abs/1806.07416v1","url_pdf":"http://arxiv.org/pdf/1806.07416v1.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":"fast-capsnet-for-lung-cancer-screening","repo_url":"https://github.com/amobiny/Fast_CapsNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"computational-efficiency","task_name":"Computational Efficiency"},{"task_slug":"computed-tomography-ct","task_name":"Computed Tomography (CT)"},{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"image-reconstruction","task_name":"Image Reconstruction"},{"task_slug":"lung-nodule-classification","task_name":"Lung Nodule Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}