[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-126886-en":3,"doc-seo-126886-105":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},126886,1099523885336,"Violet","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",8,"Research & Report","Machine learning approaches for adaptive optics in microscopy - Dissertation - Dr. rer. nat.","Microscopic imaging is fundamental for scientific investigation, and near-diffraction-limited instruments face persistent challenges from aberrating operating conditions. Such aberrations intensify with biological imaging depth and also constrain ground-based astronomy through atmospheric turbulence. The thesis applies adaptive optics to microscopy to compensate sample-induced aberrations, focusing on aberration sensing and wavefront correction. It introduces two machine-learning strategies: deep learning from labeled focus images and corresponding aberrations, and a differentiable, forward-model optimization approach using gradient-based inference with GPU-accelerated automatic differentiation, demonstrated in two configurations and in two-photon laser scanning fluorescence.","Machine learning approaches for adaptive  \noptics in microscopy  \nDissertation  \nzur  \nErlangung des Doktorgrades (Dr. rer. nat.)  \nder  \nMathematisch-Naturwissenschaftlichen Fakultt  \nder  \nRheinischen Friedrich-Wilhelms-Universitt Bonn  \nvorgelegt von  \nIvan Vishniakou  \naus  \nMinsk, Belarus  \nBonn, Dezember 2021  \nAngefertigt mit Genehmigung der Mathematisch-Naturwissenschaftlichen Fakultt der Rheinischen Friedrich-Wilhelms-Universitt Bonn  \n1. Gutachter: Prof. Dr. Matthias Hullin  \n2. Gutachter: Prof. Dr. Reinhard Klein  \nTag der Promotion: 04.07.2022  \nErscheinungsjahr: 2023  \nContents  \nAbstract iii  \nList of abbreviations v  \nAcknowledgements vii  \n1 Introduction 1  \n1.1 Background ................................. 2  \n1.1.1 Wave optics ............................. 2  \n1.1.2 Imaging systems and aberrations .................. 4  \n1.1.3 Adaptive optics ........................... 7  \n1.1.4 Two-photon fluorescence laser scanning microscopy ....... 10  \n1.1.5 Wavefront sensing ......................... 13  \n1.2 Related work – adaptive optics in microscopy ............... 16  \n1.3 Contributions ................................ 23  \n1.3.1 Adaptive optics with reflected light and deep neural networks .. 24  \n1.3.2 Differentiable model-based adaptive optics with transmitted and reflected light ............................ 25  \n1.3.3 Differentiable model-based adaptive optics for two-photon microscopy .............................. 26  \n1.4 Thesis outline ................................ 27  \n1.5 List of publications ............................. 29  \n2 Adaptive optics with reflected light and deep neural networks 31  \n2.1 Introduction ................................. 31  \n2.2 Results .................................... 33  \n2.2.1 Methods .............................. 34  \n2.2.2 Disentangling excitation and detection phase modulations .... 38  \n2.2.3 Focusing through aberrating layers ................. 39  \n2.3 Discussion .................................. 40  \n3 Differentiable model-based adaptive optics with transmitted and reflected light 47  \n3.1 Introduction ................................. 47  \n3.2 Results .................................... 49  \n3.3 Methods ................................... 52  \n3.3.1 Experimental setup and data acquisition .............. 52  \n3.3.2 Computational model ........................ 54  \n3.3.3 Model optimization ......................... 55  \n3.3.4 Evaluation ............................. 56  \n3.4 Discussion .................................. 57  \n4 Differentiable model-based adaptive optics for two-photon microscopy 59  \n4.1 Introduction ................................. 59  \n4.2 Differentiable model-based approach for adaptive optics ......... 60  \n4.3 Setup and image preprocessing ....................... 61  \n4.4 Computational modeling and optimization ................. 61  \n4.4.1 Computational model of the optical setup ............. 61  \n4.4.2 Fitting the computational model to the experimental setup .... 63  \n4.4.3 Model optimization and loss function ............... 64  \n4.5 Two-photon imaging through aberrations .................. 67  \n4.6 Discussion and conclusions ......................... 69  \n5 Conclusion 71  \n5.1 Limitations and future work ........................ 72  \n5.2 Discussion and outlook ........................... 75  \nReferences 79  \nAbstract  \nMicroscopic imaging is an essential tool for science. For instruments that operate close to the physically possible diffraction limit, a main remaining challenge are aberrating operating conditions. For microscopy, such conditions are routinely encountered for example in biology, where tissue samples induce increasingly stronger aberrations with increasing imaging depth. Similar problems are also encountered in astronomy where atmospheric turbulences hinder ground-based telescopes.  \nAdaptive optics – a method originally developed for earthbound telescopes – can be applied in microscopy to compensate for sample-induced abe","cbCaibOESRMgwGbO","https://ap.wps.com/l/cbCaibOESRMgwGbO","pdf",31311943,1,111,"English","en",105,"# Introduction\n## Background\n### Wave optics\n### Imaging systems and aberrations\n### Adaptive optics\n### Two-photon fluorescence laser scanning microscopy\n### Wavefront sensing\n## Related work – adaptive optics in microscopy\n## Contributions\n## Thesis outline\n## List of publications\n# Adaptive optics with reflected light and deep neural networks\n## Introduction\n## Results\n### Methods\n### Disentangling excitation and detection phase modulations\n### Focusing through aberrating layers\n## Discussion\n# Differentiable model-based adaptive optics with transmitted and reflected light\n## Introduction\n## Results\n## Methods\n### Experimental setup and data acquisition\n### Computational model\n### Model optimization\n### Evaluation\n## Discussion\n# Differentiable model-based adaptive optics for two-photon microscopy\n## Introduction\n## Differentiable model-based approach for adaptive optics\n## Setup and image preprocessing\n## Computational modeling and optimization\n### Computational model of the optical setup\n### Fitting the computational model to the experimental setup\n### Model optimization and loss function\n## Two-photon imaging through aberrations\n## Discussion and conclusions\n# Conclusion\n## Limitations and future work\n## Discussion and outlook","[{\"question\":\"What problem does the thesis address in microscopy imaging?\",\"answer\":\"It addresses aberrating operating conditions that degrade imaging close to the diffraction limit, especially when tissue samples introduce stronger aberrations at greater depth.\"},{\"question\":\"What is the first machine learning approach proposed?\",\"answer\":\"Deep learning is trained on labeled datasets of focus images paired with corresponding aberrations, generated using a spatial light modulator to learn aberration detection.\"},{\"question\":\"How does the second approach infer unknown aberrations?\",\"answer\":\"It optimizes a differentiable forward model of image formation: controlled light modulations probe the system, and gradient-based optimization matches the model to observations using automatic differentiation and GPU acceleration.\"}]","Machine learning approaches for adaptive optics in microscopy - Dissertation - Dr. rer. nat. | PDF",1785935419,280,{"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},"machine-learning-approaches-for-adaptive-optics-in-microscopy-dissertation-dr-rer-nat","",{"@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/machine-learning-approaches-for-adaptive-optics-in-microscopy-dissertation-dr-rer-nat/126886/",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 problem does the thesis address in microscopy imaging?","Question",{"text":75,"@type":76},"It addresses aberrating operating conditions that degrade imaging close to the diffraction limit, especially when tissue samples introduce stronger aberrations at greater depth.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What is the first machine learning approach proposed?",{"text":80,"@type":76},"Deep learning is trained on labeled datasets of focus images paired with corresponding aberrations, generated using a spatial light modulator to learn aberration detection.",{"name":82,"@type":73,"acceptedAnswer":83},"How does the second approach infer unknown aberrations?",{"text":84,"@type":76},"It optimizes a differentiable forward model of image formation: controlled light modulations probe the system, and gradient-based optimization matches the model to observations using automatic differentiation and GPU acceleration.","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"]