{"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/highly-efficient-follicular-segmentation-in","title":"Highly Efficient Follicular Segmentation in Thyroid Cytopathological Whole Slide Image","arxiv_id":"1902.05431","date":"2019-02-13","proceeding":null,"authors":["Siyan Tao","Yao Guo","Chuang Zhu","Huang Chen","Yue Zhang","Jie Yang","Jun Liu"],"abstract":"In this paper, we propose a novel method for highly efficient follicular\nsegmentation of thyroid cytopathological WSIs. Firstly, we propose a hybrid\nsegmentation architecture, which integrates a classifier into Deeplab V3 by\nadding a branch. A large amount of the WSI segmentation time is saved by\nskipping the irrelevant areas using the classification branch. Secondly, we\nmerge the low scale fine features into the original atrous spatial pyramid\npooling (ASPP) in Deeplab V3 to accurately represent the details in\ncytopathological images. Thirdly, our hybrid model is trained by a\ncriterion-oriented adaptive loss function, which leads the model converging\nmuch faster. Experimental results on a collection of thyroid patches\ndemonstrate that the proposed model reaches 80.9% on the segmentation accuracy.\nBesides, 93% time is reduced for the WSI segmentation by using our proposed\nmethod, and the WSI-level accuracy achieves 53.4%.","url_abs":"http://arxiv.org/abs/1902.05431v1","url_pdf":"http://arxiv.org/pdf/1902.05431v1.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":"highly-efficient-follicular-segmentation-in","repo_url":"https://github.com/bupt-ai-cz/Hybrid-Model-Enabling-Highly-Efficient-Follicular-Segmentation","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"segmentation","task_name":"Segmentation"}],"methods":[{"method_slug":"adaptive-loss","method_name":"Adaptive Loss"},{"method_slug":"crf","method_name":"CRF"},{"method_slug":"deeplab","method_name":"DeepLab"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dilated-convolution","method_name":"Dilated Convolution"},{"method_slug":"feedforward-network","method_name":"Feedforward Network"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}