{"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/semantic-segmentation-of-pathological-lung","title":"Semantic Segmentation of Pathological Lung Tissue with Dilated Fully Convolutional Networks","arxiv_id":"1803.06167","date":"2018-03-16","proceeding":null,"authors":["Marios Anthimopoulos","Stergios Christodoulidis","Lukas Ebner","Thomas Geiser","Andreas Christe","Stavroula Mougiakakou"],"abstract":"Early and accurate diagnosis of interstitial lung diseases (ILDs) is crucial\nfor making treatment decisions, but can be challenging even for experienced\nradiologists. The diagnostic procedure is based on the detection and\nrecognition of the different ILD pathologies in thoracic CT scans, yet their\nmanifestation often appears similar. In this study, we propose the use of a\ndeep purely convolutional neural network for the semantic segmentation of ILD\npatterns, as the basic component of a computer aided diagnosis (CAD) system for\nILDs. The proposed CNN, which consists of convolutional layers with dilated\nfilters, takes as input a lung CT image of arbitrary size and outputs the\ncorresponding label map. We trained and tested the network on a dataset of 172\nsparsely annotated CT scans, within a cross-validation scheme. The training was\nperformed in an end-to-end and semi-supervised fashion, utilizing both labeled\nand non-labeled image regions. The experimental results show significant\nperformance improvement with respect to the state of the art.","url_abs":"http://arxiv.org/abs/1803.06167v1","url_pdf":"http://arxiv.org/pdf/1803.06167v1.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":"semantic-segmentation-of-pathological-lung","repo_url":"https://github.com/intact-project/LungNet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"diagnostic","task_name":"Diagnostic"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"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}