[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-127302-en":3,"doc-seo-127302-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},127302,2336475104957,"Seraphina","https://ap-avatar.wpscdn.com/avatar/22000c4c6bd8a5076e1?x-image-process=image/resize,m_fixed,w_180,h_180&k=1786593998035447633",8,"Research & Report","Relaxing Supervision Requirements for Tomographic Data Analysis with Machine Learning","This doctoral thesis explores the power and potential of advanced imaging—tomographic imaging—in an era of rapidly growing data and the need for effective analysis strategies. It focuses on incorporating machine learning, especially deep learning, to optimize analysis of tomography scans across biology, medicine, and material sciences. The work addresses key challenges in preprocessing, data labeling, and model training, structuring the methods as a practical pipeline. Chapters cover Noise2Noise for multi-channel denoising, optimized CT segmentation labeling, SortingLoss for self-supervised pre-training, and a self-training pseudo-labeling framework with quality selection and knowledge distillation.","INAUGURAL – DISSERTATION  \nzur  \nErlangung der Doktorwürde  \nder  \nGesamtfakultät für Mathematik, Ingenieur-und Naturwissenschaften  \nder  \nRuprecht – Karls – Universität  \nHeidelberg  \nvorgelegt von Zharov, Yaroslav, Dipl.-Ing.  \naus Moskau  \nTag der mündlichen Prüfung:  \nRelaxing Supervision Requirements for Tomographic Data Analysis with Machine  \nLearning  \nProf. Dr. Vincent Heuveline:  \niii  \nPreface  \nThe work on this thesis has led to several publications both in peer-reviewed venues and on preprint servers.  \nPeer-reviewed publications  \n1. Yaroslav Zharov, Evelina Ametova, Rebecca Spiecker, Tilo Baumbach, Genoveva Burca, and Vincent Heuveline (July 2023) . “Shot noise reduction in radiographic and tomographic multi-channel imaging with self-supervised deep learning”. In: Optics Express 31.16, p. 26226. ISSN: 1094-4087 . DOI: 10 . 1364/ OE.492221  \n2. Rebecca Spiecker, Pauline Pfeiffer, Adyasha Biswal, Mykola Shcherbinin, Martin Spiecker, Holger Hessdorfer, Mathias Hurst, Yaroslav Zharov, Valerio Bellucci, Tomáš Faragó, Marcus Zuber, Annette Herz, Angelica Cecilia, Mateusz Czyzycki, Carlos Sato Baraldi Dias, Dmitri Novikov, Lars Krogmann, Elias Hamann, Thomas van de Kamp, and Tilo Baumbach (Dec. 2023b) . “Doseefficient in vivo X-ray phase contrast imaging at micrometer resolution by Bragg magnifiers”. In: Optica 10.12, p. 1633. ISSN: 2334-2536 . DOI: 10 . 1364/ OPTICA .500978  \n3. Jwalin Bhatt, Yaroslav Zharov, Sungho Suh, Tilo Baumbach, Vincent Heuveline, and Paul Lukowicz (Apr. 2023) .“A Knowledge Distillation Framework for Multi-Organ Segmentation of Medaka Fish in Tomographic Image”. In: 2023 IEEE 20th International Symposium on Biomedical Imaging (ISBI). IEEE, pp. 1–  \n5. ISBN: 978-1-6654-7358-3 . DOI: 10 . 1109/ISBI53787 .2023 .10230689  \nPreprints  \n1. Yaroslav Zharov, Alexey Ershov, Tilo Baumbach, and Vincent Heuveline (Mar. 2022) .“Using the Order of Tomographic Slices as a Prior for Neural Networks Pre-Training”. In: URL: [http://arxiv.org/abs/2203.09372](http://arxiv.org/abs/2203.09372)  \n2. Yaroslav Zharov, Tilo Baumbach, and Vincent Heuveline (Mar. 2023) .“Optimizing the Procedure of CT Segmentation Labeling”. In: URL: [http://arxiv](http://arxiv) . org/abs/2303 .14089  \nv  \nAbstract  \nRelaxing Supervision Requirements for Tomographic Data Analysis with  \nMachine Learning  \nIn this doctoral thesis, the power and potential of advanced imaging techniques, specifically Tomographic Imaging (hereinafter tomography), are explored in an era characterized by the rapid growth of data and the critical need for effective analysis strategies. This work engages with different modalities, such as but not limited to parallel beam X-ray Computed Tomography (CT), and Magnetic Resonance Imaging (MRI) . The research is centered around the incorporation of machine learning models, deep learning in particular, to optimize the analysis of tomography scans across various domains, including biology, medicine, and material sciences. This is achieved by navigating the primary challenges associated with the utilization of tomography, namely image preprocessing, data labeling, and model training. This work is organized as a series of chapters, consequently covering those topics in the order in which the proposed techniques would be applied in a practical pipeline of the data analysis.  \nIn Chapter 3 this work explores the applicability of the Noise2Noise denoising technique to the multi-channel imaging datasets, particularly those with significantly reduced Signal-to-Noise Ratio (SNR). Utilizing the self-supervised denoising approach for datasets for biological and material sciences, significant improvements in image quality have been achieved, or, equivalently, the possibility to reduce exposure time has been shown while maintaining image quality.  \nChapter 4 of the thesis details the optimization of dataset preparation procedures for training neural networks, specifically concerning tomography segmentation tasks. The study conducte","cbCaikSXIKiGz1v5","https://ap.wps.com/l/cbCaikSXIKiGz1v5","pdf",8797522,1,96,"English","en",105,"# Preface\n## Peer-reviewed publications\n## Preprints\n# Abstract\n## Chapter 3: Noise2Noise denoising\n## Chapter 4: CT segmentation labeling and dataset preparation\n## Chapter 5: SortingLoss self-supervised pre-training\n## Chapter 6: Self-training for multi-label segmentation","[{\"question\":\"What is the main goal of this thesis?\",\"answer\":\"To optimize tomographic data analysis by integrating machine learning, especially deep learning, while addressing preprocessing, labeling, and training challenges.\"},{\"question\":\"How does Chapter 3 improve tomographic images?\",\"answer\":\"It applies the Noise2Noise self-supervised denoising technique to multi-channel imaging datasets with low signal-to-noise ratio, improving image quality and enabling reduced exposure time.\"},{\"question\":\"What methods are used for segmentation in the later chapters?\",\"answer\":\"Chapter 4 focuses on dataset preparation and an optimized labeling procedure for segmentation, while Chapter 6 introduces a self-training framework using pseudo-labeling, quality classification, and pixel-wise knowledge distillation.\"}]","Relaxing Supervision Requirements for Tomographic Data Analysis with Machine Learning | PDF",1785938189,242,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"relaxing-supervision-requirements-for-tomographic-data-analysis-with-machine-learning","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/relaxing-supervision-requirements-for-tomographic-data-analysis-with-machine-learning/127302/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-05",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What is the main goal of this thesis?","Question",{"text":75,"@type":76},"To optimize tomographic data analysis by integrating machine learning, especially deep learning, while addressing preprocessing, labeling, and training challenges.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does Chapter 3 improve tomographic images?",{"text":80,"@type":76},"It applies the Noise2Noise self-supervised denoising technique to multi-channel imaging datasets with low signal-to-noise ratio, improving image quality and enabling reduced exposure time.",{"name":82,"@type":73,"acceptedAnswer":83},"What methods are used for segmentation in the later chapters?",{"text":84,"@type":76},"Chapter 4 focuses on dataset preparation and an optimized labeling procedure for segmentation, while Chapter 6 introduces a self-training framework using pseudo-labeling, quality classification, and pixel-wise knowledge distillation.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]