[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-128015-105":3,"detail-sidebar-cat-0-en-105":81,"doc-detail-128015-en":130},{"code":4,"msg":5,"data":6},0,"ok",{"site_id":7,"language":8,"slug":9,"title":10,"keywords":11,"description":12,"schema_data":13,"social_meta":74,"head_meta":76,"extra_data":78,"updated_unix":80},105,"en","improving-the-segmentation-of-the-vertebrae-using-a-multi-stage-machine-learning-algorithm","Improving the Segmentation of the Vertebrae Using a Multi-Stage Machine Learning Algorithm","","Spine health is closely tied to overall human well-being, and spinal disorders such as osteoporosis, vertebral injuries, and herniated discs can cause severe outcomes. Accurate analysis of X-ray images is central to diagnosis, yet automatic segmentation is challenged by noise, artifacts, and inconsistent exposure. This work investigates a multi-stage machine learning approach to segment four thoracic vertebrae (Th8–Th11) by training successive neural networks and using their outputs in a final pipeline. Multi-stage processing reduces the region of interest and improves segmentation quality, yielding an average accuracy gain of 4.83% across evaluated vertebrae and better results than conventional single-stage segmentation.",{"@graph":14,"@context":73},[15,34,56],{"@type":16,"itemListElement":17},"BreadcrumbList",[18,23,27,31],{"item":19,"name":20,"@type":21,"position":22},"https://docshare.wps.com","Home","ListItem",1,{"item":24,"name":25,"@type":21,"position":26},"https://docshare.wps.com/document/","Document",2,{"item":28,"name":29,"@type":21,"position":30},"https://docshare.wps.com/document/healthcare/","Healthcare",3,{"item":32,"name":10,"@type":21,"position":33},"https://docshare.wps.com/document/improving-the-segmentation-of-the-vertebrae-using-a-multi-stage-machine-learning-algorithm/128015/",4,{"url":32,"name":10,"@type":35,"image":36,"author":41,"headline":10,"publisher":44,"fileFormat":47,"inLanguage":8,"description":12,"dateModified":48,"datePublished":49,"encodingFormat":47,"isAccessibleForFree":50,"interactionStatistic":51},"DigitalDocument",{"url":37,"@type":38,"width":39,"height":40},"https://docshare.wps.com/thumbnails/improving-the-segmentation-of-the-vertebrae-using-a-multi-stage-machine-learning-algorithm/128015.png","ImageObject",300,407,{"name":42,"@type":43},"Theodore","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-09-22","2026-08-05",true,{"@type":52,"interactionType":53,"userInteractionCount":55},"InteractionCounter",{"@type":54},"ViewAction",8,{"@type":57,"mainEntity":58},"FAQPage",[59,65,69],{"name":60,"@type":61,"acceptedAnswer":62},"Why is automatic vertebrae segmentation from X-ray images important?","Question",{"text":63,"@type":64},"X-rays remain a common and low-cost diagnostic source, and automated segmentation can reduce the workload on clinicians while supporting diagnosis and preoperative analysis.","Answer",{"name":66,"@type":61,"acceptedAnswer":67},"What vertebrae are targeted in this study and how is the task structured?",{"text":68,"@type":64},"The study targets Th8, Th9, Th10, and Th11. It trains multiple neural networks in stages: one to produce a mask for four vertebrae, another to segment each vertebra within the found region, and a final stage that combines the trained networks into one algorithm.",{"name":70,"@type":61,"acceptedAnswer":71},"What improvement does the multi-stage approach achieve?",{"text":72,"@type":64},"Using the algorithm for 48 vertebrae, the method delivers an average segmentation accuracy improvement of 4.83%, with multi-stage processing reducing the region of interest by removing unnecessary background.","https://schema.org",{"og:url":32,"og:type":75,"og:title":10,"og:site_name":45,"og:description":12},"article",{"robots":77,"canonical":32},"index,follow",{"doc_id":79,"site_id":7},128015,1785943918,{"code":4,"msg":82,"data":83},"success",[84,88,92,96,101,106,110,114,119,122,126],{"id":22,"doc_module":4,"doc_module_name":25,"category_name":85,"show_sort_weight":86,"slug":87},"Story & Novel",90,"story-novel",{"id":26,"doc_module":4,"doc_module_name":25,"category_name":89,"show_sort_weight":90,"slug":91},"Literature",80,"literature",{"id":33,"doc_module":4,"doc_module_name":25,"category_name":93,"show_sort_weight":94,"slug":95},"Exam",70,"exam",{"id":97,"doc_module":4,"doc_module_name":25,"category_name":98,"show_sort_weight":99,"slug":100},5,"Comic",60,"comic",{"id":102,"doc_module":4,"doc_module_name":25,"category_name":103,"show_sort_weight":104,"slug":105},6,"Technology",50,"technology",{"id":107,"doc_module":4,"doc_module_name":25,"category_name":29,"show_sort_weight":108,"slug":109},7,40,"healthcare",{"id":55,"doc_module":4,"doc_module_name":25,"category_name":111,"show_sort_weight":112,"slug":113},"Research & Report",30,"research-report",{"id":115,"doc_module":4,"doc_module_name":25,"category_name":116,"show_sort_weight":117,"slug":118},9,"Religion & Spirituality",20,"religion-spirituality",{"id":117,"doc_module":4,"doc_module_name":25,"category_name":120,"show_sort_weight":117,"slug":121},"World Cup","world-cup",{"id":123,"doc_module":4,"doc_module_name":25,"category_name":124,"show_sort_weight":123,"slug":125},10,"Lifestyle","lifestyle",{"id":127,"doc_module":4,"doc_module_name":25,"category_name":128,"show_sort_weight":97,"slug":129},19,"General","general",{"code":4,"msg":82,"data":131},{"doc_id":79,"user_id":132,"nickname":42,"user_avatar":133,"doc_module":4,"category_id":107,"category_name":29,"doc_title":10,"doc_description":12,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":55,"is_deleted":4,"is_public":22,"is_downloadable":22,"audit_status":22,"page_count":55,"language":139,"language_code":8,"site_id":7,"html_lang":8,"table_of_contents":140,"faqs":141,"seo_title":142,"seo_description":12,"update_tm":80,"read_time":117},962084931830,"https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd","UDC 004.8 doi: 10.32620/reks.2024.4.07  \nVladyslav KONIUKHOV  \nA. Pidhornyi Institute of Power Machines and Systems of NAS of Ukraine, Kharkiv, Ukraine  \nIMPROVING THE SEGMENTATION OF THE VERTEBRAE USING A MULTI-STAGE MACHINE LEARNING ALGORITHM  \nThe health of the spine is an integral part of human health because the spine itself plays one of the key roles inhuman health, and diseases such as osteoporosis, vertebral injuries, herniated intervertebral discs, and other diseases can not only complicate a person's life but also have serious consequences. The use of X-ray images to diagnose spinal diseases plays a key role in diagnosis. Diagnosis of diseases with the help of X-rays is the most popular and cheapest option for patients to detect pathologies and diseases. The subjects of this article are algorithms for the segmentation of X-ray images of various qualities. The aim is to research the possibility of improving segmentation of vertebrae: Th8, Th9, Th10, Th11 using a multi-stage method of segmentation of the spine using machine learning to improve the accuracy of automation of vertebrae segmentation. Task: train a neural network that will segment the incoming X-ray image and produce a mask of the area of four vertebrae at the output; train a neural network that will segment each vertebra in the area found at the previous stage; cut out a section with one vertebra and train a neural network that will segment it; create an algorithm that, based on three previously trained neural networks, will segment vertebrae on an X-ray image. The following methods were used: a multi-stage approach using machine learning. The following results were obtained: thanks to segmentation in several stages, it was possible to reduce the region of interest, thereby removing unnecessary background when using segmentation. Using this algorithm for 48 vertebrae, an average improvement in segmentation accuracy of 4.83% was obtained. Conclusions. In this research, a multi-stage algorithm was proposed, and an improvement in the accuracy of segmentation of X-ray images in the lateral projection, namely the accuracy of all four vertebrae: Th8, Th9, Th10, Th11-was obtained. The results demonstrate that the use of this method gives a better result than the usual segmentation of the input image.  \nKeywords: artificial intelligence; machine learning; image recognition; neural network; image segmentation, computer vision.  \n1. Introduction  \n1.1. Motivation  \nThe use of X-rays plays a key role in the diagnosis of spine diseases and pathologies. Since the use of this technology remains the most popular and cheapest way to obtain the necessary information about a patient's condition, automatic segmentation can be an important part of helping the physician. To reduce the burden on the doctor and improve the diagnosis process, an automation process is proposed, which makes it possible to identify pathologies, perform preoperative analysis, etc. However, due to the increasing use of X-ray images, there are also problems such as noise, artifacts, and incorrect exposure. All these factors can make the diagnostic process more difficult. It is for this purpose that it is proposed to consider and analyze the multistage method of segmentation of the spine region presented in this work, which includes the following vertebrae: Th8, Th9, Th10, and Th11.  \nThis research used segmentation using neural networks, which nowadays have become a popular tool for solving such problems, however, despite their  \nadvantages, they have some disadvantages. The main problem associated with using a convolutional neural network is the need for a large amount of data for training [1] .  \n1.2. State ofthe Art  \nThe use of classical segmentation methods prior to the advent of machine learning methods were critical to tasks related to medical images. A popular threshold segmentation method is the Otsu method [2]. Different algorithms have been built on this basis, such as the use of this method","cbCaimeBrB67FSdn","https://ap.wps.com/l/cbCaimeBrB67FSdn","pdf",391337,"English","# Introduction\n## Motivation\n## State of the Art","[{\"question\":\"Why is automatic vertebrae segmentation from X-ray images important?\",\"answer\":\"X-rays remain a common and low-cost diagnostic source, and automated segmentation can reduce the workload on clinicians while supporting diagnosis and preoperative analysis.\"},{\"question\":\"What vertebrae are targeted in this study and how is the task structured?\",\"answer\":\"The study targets Th8, Th9, Th10, and Th11. It trains multiple neural networks in stages: one to produce a mask for four vertebrae, another to segment each vertebra within the found region, and a final stage that combines the trained networks into one algorithm.\"},{\"question\":\"What improvement does the multi-stage approach achieve?\",\"answer\":\"Using the algorithm for 48 vertebrae, the method delivers an average segmentation accuracy improvement of 4.83%, with multi-stage processing reducing the region of interest by removing unnecessary background.\"}]","Improving the Segmentation of the Vertebrae Using a Multi-Stage Machine Learning Algorithm | PDF"]