{"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-autoencoding-models-for-unsupervised","title":"Deep Autoencoding Models for Unsupervised Anomaly Segmentation in Brain MR Images","arxiv_id":"1804.04488","date":"2018-04-12","proceeding":null,"authors":["Christoph Baur","Benedikt Wiestler","Shadi Albarqouni","Nassir Navab"],"abstract":"Reliably modeling normality and differentiating abnormal appearances from\nnormal cases is a very appealing approach for detecting pathologies in medical\nimages. A plethora of such unsupervised anomaly detection approaches has been\nmade in the medical domain, based on statistical methods, content-based\nretrieval, clustering and recently also deep learning. Previous approaches\ntowards deep unsupervised anomaly detection model patches of normal anatomy\nwith variants of Autoencoders or GANs, and detect anomalies either as outliers\nin the learned feature space or from large reconstruction errors. In contrast\nto these patch-based approaches, we show that deep spatial autoencoding models\ncan be efficiently used to capture normal anatomical variability of entire 2D\nbrain MR images. A variety of experiments on real MR data containing MS lesions\ncorroborates our hypothesis that we can detect and even delineate anomalies in\nbrain MR images by simply comparing input images to their reconstruction.\nResults show that constraints on the latent space and adversarial training can\nfurther improve the segmentation performance over standard deep representation\nlearning.","url_abs":"http://arxiv.org/abs/1804.04488v1","url_pdf":"http://arxiv.org/pdf/1804.04488v1.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-autoencoding-models-for-unsupervised","repo_url":"https://github.com/Dai7Igarashi/Anomaly-Detection","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"anatomy","task_name":"Anatomy"},{"task_slug":"anomaly-detection","task_name":"Anomaly Detection"},{"task_slug":"anomaly-segmentation","task_name":"Anomaly Segmentation"},{"task_slug":"clustering","task_name":"Clustering"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"unsupervised-anomaly-detection","task_name":"Unsupervised Anomaly Detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1804.04488","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}