{"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/weakly-supervised-localisation-for-fetal","title":"Weakly Supervised Localisation for Fetal Ultrasound Images","arxiv_id":"1808.00793","date":"2018-08-02","proceeding":null,"authors":["Nicolas Toussaint","Bishesh Khanal","Matthew Sinclair","Alberto Gomez","Emily Skelton","Jacqueline Matthew","Julia A. Schnabel"],"abstract":"This paper addresses the task of detecting and localising fetal anatomical\nregions in 2D ultrasound images, where only image-level labels are present at\ntraining, i.e. without any localisation or segmentation information. We examine\nthe use of convolutional neural network architectures coupled with soft\nproposal layers. The resulting network simultaneously performs anatomical\nregion detection (classification) and localisation tasks. We generate a\nproposal map describing the attention of the network for a particular class.\nThe network is trained on 85,500 2D fetal Ultrasound images and their\nassociated labels. Labels correspond to six anatomical regions: head, spine,\nthorax, abdomen, limbs, and placenta. Detection achieves an average accuracy of\n90\\% on individual regions, and show that the proposal maps correlate well with\nrelevant anatomical structures. This work presents itself as a powerful and\nessential step towards subsequent tasks such as fetal position and pose\nestimation, organ-specific segmentation, or image-guided navigation. Code and\nadditional material is available at https://ntoussaint.github.io/fetalnav.","url_abs":"http://arxiv.org/abs/1808.00793v1","url_pdf":"http://arxiv.org/pdf/1808.00793v1.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":"weakly-supervised-localisation-for-fetal","repo_url":"https://github.com/ntoussaint/fetalnav","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"weakly-supervised-localisation-for-fetal","repo_url":"https://github.com/ntoussaint/qmedbrowser","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"pose-estimation","task_name":"Pose Estimation"},{"task_slug":"segmentation","task_name":"Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}