{"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/varifocal-net-a-chromosome-classification","title":"Varifocal-Net: A Chromosome Classification Approach using Deep Convolutional Networks","arxiv_id":"1810.05943","date":"2018-10-13","proceeding":null,"authors":["Yulei Qin","Juan Wen","Hao Zheng","Xiaolin Huang","Jie Yang","Ning Song","Yue-Min Zhu","Lingqian Wu","Guang-Zhong Yang"],"abstract":"Chromosome classification is critical for karyotyping in abnormality\ndiagnosis. To expedite the diagnosis, we present a novel method named\nVarifocal-Net for simultaneous classification of chromosome's type and polarity\nusing deep convolutional networks. The approach consists of one global-scale\nnetwork (G-Net) and one local-scale network (L-Net). It follows three stages.\nThe first stage is to learn both global and local features. We extract global\nfeatures and detect finer local regions via the G-Net. By proposing a varifocal\nmechanism, we zoom into local parts and extract local features via the L-Net.\nResidual learning and multi-task learning strategies are utilized to promote\nhigh-level feature extraction. The detection of discriminative local parts is\nfulfilled by a localization subnet of the G-Net, whose training process\ninvolves both supervised and weakly-supervised learning. The second stage is to\nbuild two multi-layer perceptron classifiers that exploit features of both two\nscales to boost classification performance. The third stage is to introduce a\ndispatch strategy of assigning each chromosome to a type within each patient\ncase, by utilizing the domain knowledge of karyotyping. Evaluation results from\n1909 karyotyping cases showed that the proposed Varifocal-Net achieved the\nhighest accuracy per patient case (%) 99.2 for both type and polarity tasks. It\noutperformed state-of-the-art methods, demonstrating the effectiveness of our\nvarifocal mechanism, multi-scale feature ensemble, and dispatch strategy. The\nproposed method has been applied to assist practical karyotype diagnosis.","url_abs":"http://arxiv.org/abs/1810.05943v4","url_pdf":"http://arxiv.org/pdf/1810.05943v4.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":"varifocal-net-a-chromosome-classification","repo_url":"https://github.com/fcakyon/sahi-benchmark","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"multi-task-learning","task_name":"Multi-Task Learning"},{"task_slug":"weakly-supervised-learning","task_name":"Weakly-supervised Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}