{"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/spotnet-learned-iterations-for-cell-detection","title":"SpotNet - Learned iterations for cell detection in image-based immunoassays","arxiv_id":"1810.06132","date":"2018-10-15","proceeding":null,"authors":["Pol del Aguila Pla","Vidit Saxena","Joakim Jaldén"],"abstract":"Accurate cell detection and counting in the image-based ELISpot and\nFluoroSpot immunoassays is a challenging task. Methodology recently proposed by\nour group matches human accuracy by leveraging knowledge of the underlying\nphysical process of these assays and using state-of-the-art iterative\ntechniques to solve an inverse problem. Nonetheless, thousands of\ncomputationally expensive iterations are often needed to reach a near-optimal\nsolution. In this paper, we exploit the structure of the iterations to design a\nparameterized computation graph, SpotNet, that learns the characteristic\npatterns embedded within several training images and their respective cell\nsecretion information. Further, we compare SpotNet to a customized\nconvolutional neural network layout for cell detection based on recent\nadvances. We show empirical evidence that, while both designs obtain a\ndetection performance far beyond that of a human expert, SpotNet is\nsubstantially easier to train and obtains better estimates of cell secretion.","url_abs":"http://arxiv.org/abs/1810.06132v1","url_pdf":"http://arxiv.org/pdf/1810.06132v1.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":"spotnet-learned-iterations-for-cell-detection","repo_url":"https://github.com/poldap/SpotNet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"cell-detection","task_name":"Cell Detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}