{"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/deep-generative-classifiers-for-thoracic","title":"Deep Generative Classifiers for Thoracic Disease Diagnosis with Chest X-ray Images","arxiv_id":"1809.07436","date":"2018-09-20","proceeding":null,"authors":["Chengsheng Mao","Yiheng Pan","Zexian Zeng","Liang Yao","Yuan Luo"],"abstract":"Thoracic diseases are very serious health problems that plague a large number\nof people. Chest X-ray is currently one of the most popular methods to diagnose\nthoracic diseases, playing an important role in the healthcare workflow.\nHowever, reading the chest X-ray images and giving an accurate diagnosis remain\nchallenging tasks for expert radiologists. With the success of deep learning in\ncomputer vision, a growing number of deep neural network architectures were\napplied to chest X-ray image classification. However, most of the previous deep\nneural network classifiers were based on deterministic architectures which are\nusually very noise-sensitive and are likely to aggravate the overfitting issue.\nIn this paper, to make a deep architecture more robust to noise and to reduce\noverfitting, we propose using deep generative classifiers to automatically\ndiagnose thorax diseases from the chest X-ray images. Unlike the traditional\ndeterministic classifier, a deep generative classifier has a distribution\nmiddle layer in the deep neural network. A sampling layer then draws a random\nsample from the distribution layer and input it to the following layer for\nclassification. The classifier is generative because the class label is\ngenerated from samples of a related distribution. Through training the model\nwith a certain amount of randomness, the deep generative classifiers are\nexpected to be robust to noise and can reduce overfitting and then achieve good\nperformances. We implemented our deep generative classifiers based on a number\nof well-known deterministic neural network architectures, and tested our models\non the chest X-ray14 dataset. The results demonstrated the superiority of deep\ngenerative classifiers compared with the corresponding deep deterministic\nclassifiers.","url_abs":"http://arxiv.org/abs/1809.07436v2","url_pdf":"http://arxiv.org/pdf/1809.07436v2.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":"deep-generative-classifiers-for-thoracic","repo_url":"https://github.com/mocherson/deep-generative-classifiers","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"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":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}