{"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/standard-plane-detection-in-3d-fetal","title":"Standard Plane Detection in 3D Fetal Ultrasound Using an Iterative Transformation Network","arxiv_id":"1806.07486","date":"2018-06-19","proceeding":null,"authors":["Yuanwei Li","Bishesh Khanal","Benjamin Hou","Amir Alansary","Juan J. Cerrolaza","Matthew Sinclair","Jacqueline Matthew","Chandni Gupta","Caroline Knight","Bernhard Kainz","Daniel Rueckert"],"abstract":"Standard scan plane detection in fetal brain ultrasound (US) forms a crucial\nstep in the assessment of fetal development. In clinical settings, this is done\nby manually manoeuvring a 2D probe to the desired scan plane. With the advent\nof 3D US, the entire fetal brain volume containing these standard planes can be\neasily acquired. However, manual standard plane identification in 3D volume is\nlabour-intensive and requires expert knowledge of fetal anatomy. We propose a\nnew Iterative Transformation Network (ITN) for the automatic detection of\nstandard planes in 3D volumes. ITN uses a convolutional neural network to learn\nthe relationship between a 2D plane image and the transformation parameters\nrequired to move that plane towards the location/orientation of the standard\nplane in the 3D volume. During inference, the current plane image is passed\niteratively to the network until it converges to the standard plane location.\nWe explore the effect of using different transformation representations as\nregression outputs of ITN. Under a multi-task learning framework, we introduce\nadditional classification probability outputs to the network to act as\nconfidence measures for the regressed transformation parameters in order to\nfurther improve the localisation accuracy. When evaluated on 72 US volumes of\nfetal brain, our method achieves an error of 3.83mm/12.7 degrees and\n3.80mm/12.6 degrees for the transventricular and transcerebellar planes\nrespectively and takes 0.46s per plane. Source code is publicly available at\nhttps://github.com/yuanwei1989/plane-detection.","url_abs":"http://arxiv.org/abs/1806.07486v2","url_pdf":"http://arxiv.org/pdf/1806.07486v2.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":"standard-plane-detection-in-3d-fetal","repo_url":"https://github.com/yuanwei1989/plane-detection","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"anatomy","task_name":"Anatomy"},{"task_slug":"multi-task-learning","task_name":"Multi-Task Learning"}],"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}