{"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/sumnet-fully-convolutional-model-for-fast","title":"SUMNet: Fully Convolutional Model for Fast Segmentation of Anatomical Structures in Ultrasound Volumes","arxiv_id":"1901.06920","date":"2019-01-21","proceeding":null,"authors":["Sumanth Nandamuri","Debarghya China","Pabitra Mitra","Debdoot Sheet"],"abstract":"Ultrasound imaging is generally employed for real-time investigation of\ninternal anatomy of the human body for disease identification. Delineation of\nthe anatomical boundary of organs and pathological lesions is quite challenging\ndue to the stochastic nature of speckle intensity in the images, which also\nintroduces visual fatigue for the observer. This paper introduces a fully\nconvolutional neural network based method to segment organ and pathologies in\nultrasound volume by learning the spatial-relationship between closely related\nclasses in the presence of stochastically varying speckle intensity. We propose\na convolutional encoder-decoder like framework with (i) feature concatenation\nacross matched layers in encoder and decoder and (ii) index passing based\nunpooling at the decoder for semantic segmentation of ultrasound volumes. We\nhave experimentally evaluated the performance on publicly available datasets\nconsisting of $10$ intravascular ultrasound pullback acquired at $20$ MHz and\n$16$ freehand thyroid ultrasound volumes acquired $11 - 16$ MHz. We have\nobtained a dice score of $0.93 \\pm 0.08$ and $0.92 \\pm 0.06$ respectively,\nfollowing a $10$-fold cross-validation experiment while processing frame of\n$256 \\times 384$ pixel in $0.035$s and a volume of $256 \\times 384 \\times 384$\nvoxel in $13.44$s.","url_abs":"http://arxiv.org/abs/1901.06920v1","url_pdf":"http://arxiv.org/pdf/1901.06920v1.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":"sumnet-fully-convolutional-model-for-fast","repo_url":"https://github.com/drvelmuruganb/EDD2020-Endoscopy-disease-detection-grand-challenge-2020-","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"anatomy","task_name":"Anatomy"},{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"semantic-segmentation","task_name":"Semantic 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}