{"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/direct-automated-quantitative-measurement-of","title":"Direct Automated Quantitative Measurement of Spine via Cascade Amplifier Regression Network","arxiv_id":"1806.05570","date":"2018-06-14","proceeding":null,"authors":["Shumao Pang","Stephanie Leung","Ilanit Ben Nachum","Qianjin Feng","Shuo Li"],"abstract":"Automated quantitative measurement of the spine (i.e., multiple indices\nestimation of heights, widths, areas, and so on for the vertebral body and\ndisc) is of the utmost importance in clinical spinal disease diagnoses, such as\nosteoporosis, intervertebral disc degeneration, and lumbar disc herniation, yet\nstill an unprecedented challenge due to the variety of spine structure and the\nhigh dimensionality of indices to be estimated. In this paper, we propose a\nnovel cascade amplifier regression network (CARN), which includes the CARN\narchitecture and local shape-constrained manifold regularization (LSCMR) loss\nfunction, to achieve accurate direct automated multiple indices estimation. The\nCARN architecture is composed of a cascade amplifier network (CAN) for\nexpressive feature embedding and a linear regression model for multiple indices\nestimation. The CAN consists of cascade amplifier units (AUs), which are used\nfor selective feature reuse by stimulating effective feature and suppressing\nredundant feature during propagating feature map between adjacent layers, thus\nan expressive feature embedding is obtained. During training, the LSCMR is\nutilized to alleviate overfitting and generate realistic estimation by learning\nthe multiple indices distribution. Experiments on MR images of 195 subjects\nshow that the proposed CARN achieves impressive performance with mean absolute\nerrors of 1.2496 mm, 1.2887 mm, and 1.2692 mm for estimation of 15 heights of\ndiscs, 15 heights of vertebral bodies, and total indices respectively. The\nproposed method has great potential in clinical spinal disease diagnoses.","url_abs":"http://arxiv.org/abs/1806.05570v1","url_pdf":"http://arxiv.org/pdf/1806.05570v1.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":"direct-automated-quantitative-measurement-of","repo_url":"https://github.com/pangshumao/CARN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"regression-1","task_name":"regression"}],"methods":[{"method_slug":"linear-regression","method_name":"Linear Regression"}],"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}