[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-124429-en":3,"doc-seo-124429-105":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},124429,1374391974585,"Genevieve","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",8,"Research & Report","Machine Learning Model for Complete Reconstruction of Diagnostic Polarimetric Images from partial Mueller polarimetry data","The use of imaging Mueller polarimetry in clinical diagnosis is limited by bulky instruments and relatively slow acquisition. Polarization-sensitive cameras can reduce hardware footprint and enable video-rate streaming, yet they typically measure only the first three rows of the complete 4×4 Mueller matrix. To address this constraint, a machine learning approach based on a sequential neural network reconstructs the missing elements from the measured partial Mueller data. The method is trained and tested on polarimetric images from multiple excised human tissues using two Mueller polarimeters and evaluates accuracy with multiple error metrics.","arXiv :2409 . 13073v1 [physics .optics] 19 Sep 2024  \nMachine Learning Model for Complete Reconstruction of Diagnostic Polarimetric Images  \nfrom partial Mueller polarimetry data†  \nSooyong Chae,‡ Tongyu Huang,¶ Omar Rodr´ıguez-Nu˜nez,‡,∇ Th´eotim Lucas,‡ Jean-Charles Vanel,‡ J´er´emy Vizet,‡,†† Angelo Pierangelo,‡ Gennadii Piavchenko,§ Tsanislava Genova, ∥ Ajmal Ajmal,⊥ Jessica C. Ramella-Roman,⊥ ,\\#  \nAlexander Doronin,@ Hui Ma,¶ ,△ and Tatiana Novikova ∗ ,‡,⊥  \n‡LPICM, CNRS, Ecole polytechnique, IP Paris, Palaiseau, France ¶Graduate School at Shenzhen Tsinghua University, Shenzhen, China  \n§I. M. Sechenov First Moscow State Medical University, Moscow, Russia ∥Biophotonics Laboratory, Institute of Electronics BAS, Sofia, Bulgaria ⊥Department of Biomedical Engineering, Florida International University, Miami, USA  \n\\#Herbert Wertheim College of Medicine, Florida International University, Miami, USA.@School of Computer Sciences, Victoria University, Wellington, New Zealand  \n△Department of Physics, Tsinghua University, Beijing, China ∇Currently with Department of Neurosurgery, Inselspital, University of Bern, Switzerland  \n††Currently with ArianeGroup, Mureaux, France  \nE-mail: [tatiana.novikova@polytechnique.edu](tatiana.novikova@polytechnique.edu)  \n†Sooyong Chae and Tongyu Huang are co-first authors  \nAbstract  \nThe translation of imaging Mueller polarimetry to clinical practice is often hindered by large footprint and relatively slow acquisition speed of the existing instruments. Using polarization-sensitive camera as a detector may reduce instrument dimensions and allow data streaming at video rate. However, only the first three rows of a complete 4×4 Mueller matrix can be measured. To overcome this hurdle we developed a machine learning approach using sequential neural network algorithm for the reconstruction of missing elements of a Mueller matrix from the measured elements of the first three rows. The algorithm was trained and tested on the dataset of polarimetric images of various excised human tissues (uterine cervix, colon, skin, brain) acquired with two different imaging Mueller polarimeters operating in either reflection (wide-field imaging system) or transmission (microscope) configurations at different wavelengths of 550 nm and 385 nm, respectively. The reconstruction performance was evaluated using various error metrics, all of which confirmed low error values. The execution time of the trained neural network algorithm was about 300 microseconds for a single image pixel. It suggests that a machine learning approach with parallel processing of all image pixels combined with the partial Mueller polarimeter operating at video rate can effectively substitute for the complete Mueller polarimeter and produce accurate maps of depolarization, linear retardance and orientation of the optical axis of biological tissues, which can be used for medical diagnosis in clinical settings.  \nIntroduction  \nImaging Mueller polarimetry has already demonstrated its potential in medical diagnosis. 1−14 Despite the promising results, the translation of this modality to clinical practice for realtime applications is challenging due to limitations related to the physical setup of imaging devices and the speed of data acquisition and post-processing, which currently hinder the feasibility of in vivo polarimetric imaging for diagnostic purposes.  \nFor the complete Mueller polarimeters, at least 16 measurements are required to get all elements of 4×4 real-valued Mueller Matrix (MM) . 15–17 Performing the measurements sequentially makes the design and implementation of imaging Mueller polarimetric system simpler, but also less time-efficient. 18–22 The systems with spectral polarization coding can be very compact and measure a MM at the kHz rate. However, taking wide-field polarimetric images with such systems will require its implementation in a scanning mode. 23,24 The use of photoelastic modulators for fast wide-field MM imaging was repo","cbCailtDt4ouWYYM","https://ap.wps.com/l/cbCailtDt4ouWYYM","pdf",6434496,1,35,"English","en",105,"# Abstract\n# Introduction\n## Clinical motivation and realtime constraints\n## Measurement requirements for full 4×4 Mueller matrices\n## Limitations of polarization-sensitive cameras (missing fourth row)\n## Proposed solution using machine learning reconstruction","[{\"question\":\"Why is imaging Mueller polarimetry difficult to use in real-time clinical practice?\",\"answer\":\"Translation to clinical realtime use is hindered by physical setup limitations, slow data acquisition, and slow post-processing, which limit in vivo diagnostic polarimetric imaging feasibility.\"},{\"question\":\"What data limitation occurs when using a polarization-sensitive camera?\",\"answer\":\"A polarization-sensitive camera can measure only linear polarization states, yielding a reduced 3×4 Mueller matrix with the fourth row missing.\"},{\"question\":\"How does the proposed method reconstruct the missing Mueller matrix information?\",\"answer\":\"A sequential neural network model is trained to predict the missing elements of the complete 4×4 Mueller matrix using the measured elements from the first three rows of the partial Mueller matrix.\"}]","Machine Learning Model for Complete Reconstruction of Diagnostic Polarimetric Images from partial Mueller polarimetry data | PDF",1785822260,88,{"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-model-for-complete-reconstruction-of-diagnostic-polarimetric-images-from-partial-mueller-polarimetry-data","",{"@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-model-for-complete-reconstruction-of-diagnostic-polarimetric-images-from-partial-mueller-polarimetry-data/124429/",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","2026-08-04",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},"Why is imaging Mueller polarimetry difficult to use in real-time clinical practice?","Question",{"text":75,"@type":76},"Translation to clinical realtime use is hindered by physical setup limitations, slow data acquisition, and slow post-processing, which limit in vivo diagnostic polarimetric imaging feasibility.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What data limitation occurs when using a polarization-sensitive camera?",{"text":80,"@type":76},"A polarization-sensitive camera can measure only linear polarization states, yielding a reduced 3×4 Mueller matrix with the fourth row missing.",{"name":82,"@type":73,"acceptedAnswer":83},"How does the proposed method reconstruct the missing Mueller matrix information?",{"text":84,"@type":76},"A sequential neural network model is trained to predict the missing elements of the complete 4×4 Mueller matrix using the measured elements from the first three rows of the partial Mueller matrix.","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"]