{"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/anatomy-specific-classification-of-medical","title":"Anatomy-specific classification of medical images using deep convolutional nets","arxiv_id":"1504.04003","date":"2015-04-15","proceeding":null,"authors":["Holger R. Roth","Christopher T. Lee","Hoo-chang Shin","Ari Seff","Lauren Kim","Jianhua Yao","Le Lu","Ronald M. Summers"],"abstract":"Automated classification of human anatomy is an important prerequisite for\nmany computer-aided diagnosis systems. The spatial complexity and variability\nof anatomy throughout the human body makes classification difficult. \"Deep\nlearning\" methods such as convolutional networks (ConvNets) outperform other\nstate-of-the-art methods in image classification tasks. In this work, we\npresent a method for organ- or body-part-specific anatomical classification of\nmedical images acquired using computed tomography (CT) with ConvNets. We train\na ConvNet, using 4,298 separate axial 2D key-images to learn 5 anatomical\nclasses. Key-images were mined from a hospital PACS archive, using a set of\n1,675 patients. We show that a data augmentation approach can help to enrich\nthe data set and improve classification performance. Using ConvNets and data\naugmentation, we achieve anatomy-specific classification error of 5.9 % and\narea-under-the-curve (AUC) values of an average of 0.998 in testing. We\ndemonstrate that deep learning can be used to train very reliable and accurate\nclassifiers that could initialize further computer-aided diagnosis.","url_abs":"http://arxiv.org/abs/1504.04003v1","url_pdf":"http://arxiv.org/pdf/1504.04003v1.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":"anatomy-specific-classification-of-medical","repo_url":"https://github.com/rsummers11/CADLab","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"anatomy","task_name":"Anatomy"},{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"computed-tomography-ct","task_name":"Computed Tomography (CT)"},{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1504.04003","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}