{"id":12056,"date":"2023-07-06T15:27:02","date_gmt":"2023-07-06T13:27:02","guid":{"rendered":"https:\/\/new.sano.science\/?post_type=people&p=12056"},"modified":"2026-07-16T10:38:22","modified_gmt":"2026-07-16T08:38:22","slug":"tomasz-szczepanski","status":"publish","type":"people","link":"https:\/\/sano.science\/people\/tomasz-szczepanski\/","title":{"rendered":"Tomasz Szczepa\u0144ski"},"excerpt":{"rendered":"

PhD Student in Medical Imaging and Robotics<\/p>\n","protected":false},"featured_media":31801,"template":"","people_teams":[19,35],"class_list":["post-12056","people","type-people","status-publish","has-post-thumbnail","hentry","people_teams-research","people_teams-medical-imaging-and-robotics-group"],"yoast_head":"\nTomasz Szczepa\u0144ski - Centre for Computational Personalized Medicine<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/sano.science\/people\/tomasz-szczepanski\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Tomasz Szczepa\u0144ski\" \/>\n<meta property=\"og:description\" content=\"PhD Student in Medical Imaging and Robotics\" \/>\n<meta property=\"og:url\" content=\"https:\/\/sano.science\/people\/tomasz-szczepanski\/\" \/>\n<meta property=\"og:site_name\" content=\"Centre for Computational Personalized Medicine\" \/>\n<meta property=\"article:publisher\" content=\"https:\/\/www.facebook.com\/sano.science\/\" \/>\n<meta property=\"article:modified_time\" content=\"2026-07-16T08:38:22+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/sano.science\/wp-content\/uploads\/2023\/07\/Tomasz-Szczepanski.png\" \/>\n\t<meta property=\"og:image:width\" content=\"700\" \/>\n\t<meta property=\"og:image:height\" content=\"700\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/png\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:site\" content=\"@sanoscience\" \/>\n<meta name=\"twitter:label1\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data1\" content=\"1 minute\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/sano.science\\\/people\\\/tomasz-szczepanski\\\/\",\"url\":\"https:\\\/\\\/sano.science\\\/people\\\/tomasz-szczepanski\\\/\",\"name\":\"Tomasz Szczepa\u0144ski - Centre for Computational Personalized Medicine\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/sano.science\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/sano.science\\\/people\\\/tomasz-szczepanski\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/sano.science\\\/people\\\/tomasz-szczepanski\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/sano.science\\\/wp-content\\\/uploads\\\/2023\\\/07\\\/Tomasz-Szczepanski.png\",\"datePublished\":\"2023-07-06T13:27:02+00:00\",\"dateModified\":\"2026-07-16T08:38:22+00:00\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/sano.science\\\/people\\\/tomasz-szczepanski\\\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/sano.science\\\/people\\\/tomasz-szczepanski\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/sano.science\\\/people\\\/tomasz-szczepanski\\\/#primaryimage\",\"url\":\"https:\\\/\\\/sano.science\\\/wp-content\\\/uploads\\\/2023\\\/07\\\/Tomasz-Szczepanski.png\",\"contentUrl\":\"https:\\\/\\\/sano.science\\\/wp-content\\\/uploads\\\/2023\\\/07\\\/Tomasz-Szczepanski.png\",\"width\":700,\"height\":700},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/sano.science\\\/people\\\/tomasz-szczepanski\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/sano.science\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"People\",\"item\":\"https:\\\/\\\/sano.science\\\/people\\\/\"},{\"@type\":\"ListItem\",\"position\":3,\"name\":\"Research\",\"item\":\"https:\\\/\\\/sano.science\\\/people-teams\\\/research\\\/\"},{\"@type\":\"ListItem\",\"position\":4,\"name\":\"Tomasz Szczepa\u0144ski\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/sano.science\\\/#website\",\"url\":\"https:\\\/\\\/sano.science\\\/\",\"name\":\"Centre for Computational Personalized Medicine\",\"description\":\"Sano \u2013 Centre for Computational Medicine\",\"publisher\":{\"@id\":\"https:\\\/\\\/sano.science\\\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/sano.science\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"},{\"@type\":\"Organization\",\"@id\":\"https:\\\/\\\/sano.science\\\/#organization\",\"name\":\"Sano \u2013 Centre for Computational Medicine\",\"alternateName\":\"Sano\",\"url\":\"https:\\\/\\\/sano.science\\\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/sano.science\\\/#\\\/schema\\\/logo\\\/image\\\/\",\"url\":\"https:\\\/\\\/sano.science\\\/wp-content\\\/uploads\\\/2024\\\/05\\\/logo_sano_podstawowe.png\",\"contentUrl\":\"https:\\\/\\\/sano.science\\\/wp-content\\\/uploads\\\/2024\\\/05\\\/logo_sano_podstawowe.png\",\"width\":700,\"height\":265,\"caption\":\"Sano \u2013 Centre for Computational Medicine\"},\"image\":{\"@id\":\"https:\\\/\\\/sano.science\\\/#\\\/schema\\\/logo\\\/image\\\/\"},\"sameAs\":[\"https:\\\/\\\/www.facebook.com\\\/sano.science\\\/\",\"https:\\\/\\\/x.com\\\/sanoscience\",\"https:\\\/\\\/www.linkedin.com\\\/company\\\/sanoscience\\\/\",\"https:\\\/\\\/www.youtube.com\\\/channel\\\/UCDZ_8TcjMWUG2ZcgKKgfpwQ\",\"https:\\\/\\\/bsky.app\\\/profile\\\/sanoscience.bsky.social\"]}]}<\/script>\n<!-- \/ Yoast SEO Premium plugin. -->","yoast_head_json":{"title":"Tomasz Szczepa\u0144ski - Centre for Computational Personalized Medicine","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/sano.science\/people\/tomasz-szczepanski\/","og_locale":"en_US","og_type":"article","og_title":"Tomasz Szczepa\u0144ski","og_description":"PhD Student in Medical Imaging and Robotics","og_url":"https:\/\/sano.science\/people\/tomasz-szczepanski\/","og_site_name":"Centre for Computational Personalized Medicine","article_publisher":"https:\/\/www.facebook.com\/sano.science\/","article_modified_time":"2026-07-16T08:38:22+00:00","og_image":[{"width":700,"height":700,"url":"https:\/\/sano.science\/wp-content\/uploads\/2023\/07\/Tomasz-Szczepanski.png","type":"image\/png"}],"twitter_card":"summary_large_image","twitter_site":"@sanoscience","twitter_misc":{"Est. reading time":"1 minute"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/sano.science\/people\/tomasz-szczepanski\/","url":"https:\/\/sano.science\/people\/tomasz-szczepanski\/","name":"Tomasz Szczepa\u0144ski - Centre for Computational Personalized Medicine","isPartOf":{"@id":"https:\/\/sano.science\/#website"},"primaryImageOfPage":{"@id":"https:\/\/sano.science\/people\/tomasz-szczepanski\/#primaryimage"},"image":{"@id":"https:\/\/sano.science\/people\/tomasz-szczepanski\/#primaryimage"},"thumbnailUrl":"https:\/\/sano.science\/wp-content\/uploads\/2023\/07\/Tomasz-Szczepanski.png","datePublished":"2023-07-06T13:27:02+00:00","dateModified":"2026-07-16T08:38:22+00:00","breadcrumb":{"@id":"https:\/\/sano.science\/people\/tomasz-szczepanski\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/sano.science\/people\/tomasz-szczepanski\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/sano.science\/people\/tomasz-szczepanski\/#primaryimage","url":"https:\/\/sano.science\/wp-content\/uploads\/2023\/07\/Tomasz-Szczepanski.png","contentUrl":"https:\/\/sano.science\/wp-content\/uploads\/2023\/07\/Tomasz-Szczepanski.png","width":700,"height":700},{"@type":"BreadcrumbList","@id":"https:\/\/sano.science\/people\/tomasz-szczepanski\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/sano.science\/"},{"@type":"ListItem","position":2,"name":"People","item":"https:\/\/sano.science\/people\/"},{"@type":"ListItem","position":3,"name":"Research","item":"https:\/\/sano.science\/people-teams\/research\/"},{"@type":"ListItem","position":4,"name":"Tomasz Szczepa\u0144ski"}]},{"@type":"WebSite","@id":"https:\/\/sano.science\/#website","url":"https:\/\/sano.science\/","name":"Centre for Computational Personalized Medicine","description":"Sano \u2013 Centre for Computational Medicine","publisher":{"@id":"https:\/\/sano.science\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/sano.science\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Organization","@id":"https:\/\/sano.science\/#organization","name":"Sano \u2013 Centre for Computational Medicine","alternateName":"Sano","url":"https:\/\/sano.science\/","logo":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/sano.science\/#\/schema\/logo\/image\/","url":"https:\/\/sano.science\/wp-content\/uploads\/2024\/05\/logo_sano_podstawowe.png","contentUrl":"https:\/\/sano.science\/wp-content\/uploads\/2024\/05\/logo_sano_podstawowe.png","width":700,"height":265,"caption":"Sano \u2013 Centre for Computational Medicine"},"image":{"@id":"https:\/\/sano.science\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/www.facebook.com\/sano.science\/","https:\/\/x.com\/sanoscience","https:\/\/www.linkedin.com\/company\/sanoscience\/","https:\/\/www.youtube.com\/channel\/UCDZ_8TcjMWUG2ZcgKKgfpwQ","https:\/\/bsky.app\/profile\/sanoscience.bsky.social"]}]}},"acf":[],"meta_data":{"description":"<p>Tomasz Szczepa\u0144ski is a PhD candidate at the Sano Centre for Computational Medicine, where he is a member of the Medical Imaging and Robotics group. His doctoral research, supervised by Prof. Tomasz Trzci\u0144ski (WUT) and co-supervised by Dr. Arkadiusz Sitek (Harvard Medical School), focuses on medical imaging, multimodal data integration, and geometric approaches to 3D image segmentation and generation.<br aria-hidden=\"true\" \/>His work has been presented at MICCAI (2023\u20132025) and ICCS (2022), and published in IEEE Transactions on Medical Imaging and Medical Image Analysis (2025). In 2025 he received an Outstanding Reviewer Award (Honorable Mention) at MICCAI, the only reviewer affiliated with a Polish institution to receive this distinction that year, following his service as a MICCAI reviewer since 2024.<br aria-hidden=\"true\" \/>He holds an MSc in Computer Science from WUT (2022, summa cum laude), for which his thesis on chest X-ray bias analysis in COVID-19 patients received a distinction in the National Master 4 Science competition, and a BEng in Photonics Engineering and Mechatronics, also from WUT (2018).<\/p>\n","email":"","social_media":[{"icon":{"ID":11986,"id":11986,"title":"google","filename":"google.svg","filesize":14070,"url":"https:\/\/sano.science\/wp-content\/uploads\/2023\/05\/google.svg","link":"https:\/\/sano.science\/people\/maciej-malawski\/google\/","alt":"","author":"5","description":"","caption":"","name":"google","status":"inherit","uploaded_to":531,"date":"2023-07-06 10:59:21","modified":"2023-07-06 10:59:21","menu_order":0,"mime_type":"image\/svg+xml","type":"image","subtype":"svg+xml","icon":"https:\/\/sano.science\/wp-includes\/images\/media\/default.png","width":1,"height":1,"sizes":{"thumbnail":"https:\/\/sano.science\/wp-content\/uploads\/2023\/05\/google.svg","thumbnail-width":150,"thumbnail-height":150,"medium":"https:\/\/sano.science\/wp-content\/uploads\/2023\/05\/google.svg","medium-width":300,"medium-height":300,"medium_large":"https:\/\/sano.science\/wp-content\/uploads\/2023\/05\/google.svg","medium_large-width":768,"medium_large-height":1,"large":"https:\/\/sano.science\/wp-content\/uploads\/2023\/05\/google.svg","large-width":1024,"large-height":1024,"1536x1536":"https:\/\/sano.science\/wp-content\/uploads\/2023\/05\/google.svg","1536x1536-width":1,"1536x1536-height":1,"2048x2048":"https:\/\/sano.science\/wp-content\/uploads\/2023\/05\/google.svg","2048x2048-width":1,"2048x2048-height":1}},"link":"https:\/\/scholar.google.pl\/citations?user=Acs36CkAAAAJ&hl=pl&oi=sra","name":"Google Schoolar"},{"icon":{"ID":11990,"id":11990,"title":"research gate","filename":"research-gate.svg","filesize":14281,"url":"https:\/\/sano.science\/wp-content\/uploads\/2023\/05\/research-gate.svg","link":"https:\/\/sano.science\/people\/maciej-malawski\/research-gate\/","alt":"","author":"5","description":"","caption":"","name":"research-gate","status":"inherit","uploaded_to":531,"date":"2023-07-06 11:18:50","modified":"2023-07-06 11:18:50","menu_order":0,"mime_type":"image\/svg+xml","type":"image","subtype":"svg+xml","icon":"https:\/\/sano.science\/wp-includes\/images\/media\/default.png","width":1,"height":1,"sizes":{"thumbnail":"https:\/\/sano.science\/wp-content\/uploads\/2023\/05\/research-gate.svg","thumbnail-width":150,"thumbnail-height":150,"medium":"https:\/\/sano.science\/wp-content\/uploads\/2023\/05\/research-gate.svg","medium-width":300,"medium-height":300,"medium_large":"https:\/\/sano.science\/wp-content\/uploads\/2023\/05\/research-gate.svg","medium_large-width":768,"medium_large-height":1,"large":"https:\/\/sano.science\/wp-content\/uploads\/2023\/05\/research-gate.svg","large-width":1024,"large-height":1024,"1536x1536":"https:\/\/sano.science\/wp-content\/uploads\/2023\/05\/research-gate.svg","1536x1536-width":1,"1536x1536-height":1,"2048x2048":"https:\/\/sano.science\/wp-content\/uploads\/2023\/05\/research-gate.svg","2048x2048-width":1,"2048x2048-height":1}},"link":"https:\/\/www.researchgate.net\/profile\/Tomasz-Szczepanski-7","name":"ResearchGate"},{"icon":{"ID":11992,"id":11992,"title":"orcid","filename":"orcid.svg","filesize":15590,"url":"https:\/\/sano.science\/wp-content\/uploads\/2023\/05\/orcid.svg","link":"https:\/\/sano.science\/people\/maciej-malawski\/orcid\/","alt":"","author":"5","description":"","caption":"","name":"orcid","status":"inherit","uploaded_to":531,"date":"2023-07-06 11:21:29","modified":"2023-07-06 11:21:29","menu_order":0,"mime_type":"image\/svg+xml","type":"image","subtype":"svg+xml","icon":"https:\/\/sano.science\/wp-includes\/images\/media\/default.png","width":1,"height":1,"sizes":{"thumbnail":"https:\/\/sano.science\/wp-content\/uploads\/2023\/05\/orcid.svg","thumbnail-width":150,"thumbnail-height":150,"medium":"https:\/\/sano.science\/wp-content\/uploads\/2023\/05\/orcid.svg","medium-width":300,"medium-height":300,"medium_large":"https:\/\/sano.science\/wp-content\/uploads\/2023\/05\/orcid.svg","medium_large-width":768,"medium_large-height":1,"large":"https:\/\/sano.science\/wp-content\/uploads\/2023\/05\/orcid.svg","large-width":1024,"large-height":1024,"1536x1536":"https:\/\/sano.science\/wp-content\/uploads\/2023\/05\/orcid.svg","1536x1536-width":1,"1536x1536-height":1,"2048x2048":"https:\/\/sano.science\/wp-content\/uploads\/2023\/05\/orcid.svg","2048x2048-width":1,"2048x2048-height":1}},"link":"https:\/\/orcid.org\/0000-0001-6189-478X","name":"ORCID"},{"icon":{"ID":11994,"id":11994,"title":"linkedin","filename":"linkedin.svg","filesize":914,"url":"https:\/\/sano.science\/wp-content\/uploads\/2023\/05\/linkedin.svg","link":"https:\/\/sano.science\/people\/maciej-malawski\/linkedin-2\/","alt":"","author":"5","description":"","caption":"","name":"linkedin-2","status":"inherit","uploaded_to":531,"date":"2023-07-06 11:24:13","modified":"2023-07-06 11:24:13","menu_order":0,"mime_type":"image\/svg+xml","type":"image","subtype":"svg+xml","icon":"https:\/\/sano.science\/wp-includes\/images\/media\/default.png","width":1,"height":1,"sizes":{"thumbnail":"https:\/\/sano.science\/wp-content\/uploads\/2023\/05\/linkedin.svg","thumbnail-width":150,"thumbnail-height":150,"medium":"https:\/\/sano.science\/wp-content\/uploads\/2023\/05\/linkedin.svg","medium-width":300,"medium-height":300,"medium_large":"https:\/\/sano.science\/wp-content\/uploads\/2023\/05\/linkedin.svg","medium_large-width":768,"medium_large-height":1,"large":"https:\/\/sano.science\/wp-content\/uploads\/2023\/05\/linkedin.svg","large-width":1024,"large-height":1024,"1536x1536":"https:\/\/sano.science\/wp-content\/uploads\/2023\/05\/linkedin.svg","1536x1536-width":1,"1536x1536-height":1,"2048x2048":"https:\/\/sano.science\/wp-content\/uploads\/2023\/05\/linkedin.svg","2048x2048-width":1,"2048x2048-height":1}},"link":"https:\/\/pl.linkedin.com\/in\/tomaszszczepanski1","name":"LinkedIn"}],"tabs":false,"quote":"","position_with_team":{"text_before_link":"PhD Student in","link_text":"Medical Imaging and Robotics","text_after_link":"","link":"https:\/\/sano.science\/research-teams\/health-informatics-group-higs\/"},"publications":[{"ID":31940,"post_author":"8","post_date":"2026-07-15 11:49:06","post_date_gmt":"2026-07-15 09:49:06","post_content":"<!-- wp:paragraph {\"epAnimationGeneratedClass\":\"edplus_anim-4kWuNl\",\"epGeneratedClass\":\"eplus-wrapper\"} -->\n<p class=\" eplus-wrapper\">Accurate segmentation of dentomaxillofacial structures in Cone-Beam Computed Tomography (CBCT) scans poses significant technical challenges, particularly for fine anatomical details such as root apices and nerve canals. Precise delineation of these structures is essential for assessing root resorption and supporting surgical planning in digital dentistry.<\/p>\n<!-- \/wp:paragraph -->\n\n<!-- wp:paragraph {\"epAnimationGeneratedClass\":\"edplus_anim-we4yR1\",\"epGeneratedClass\":\"eplus-wrapper\"} -->\n<p class=\" eplus-wrapper\">This work presents a method developed in the scope of the ToothFairy3 Challenge, combining instance detection and multi-class segmentation of dentomaxillofacial structures into a single unified framework. The approach adapts a Deep Watershed technique, representing each anatomical structure as a continuous 3D energy basin that encodes voxel distances to class boundaries. This instance-aware formulation is particularly well-suited to handling the narrow, geometrically complex structures that make this segmentation task demanding.<\/p>\n<!-- \/wp:paragraph -->\n\n<!-- wp:paragraph {\"epAnimationGeneratedClass\":\"edplus_anim-hp5qSn\",\"epGeneratedClass\":\"eplus-wrapper\"} -->\n<p class=\" eplus-wrapper\">The method was trained and evaluated on the ToothFairy3 dataset, comprising 532 CBCT scans with voxel-level annotations, achieving a mean Dice coefficient of 0.742 and HD95 of 111.13 on the test set. The implementation is publicly available.<\/p>\n<!-- \/wp:paragraph -->\n\n<!-- wp:spacer {\"height\":\"10px\",\"epAnimationGeneratedClass\":\"edplus_anim-yK3wlB\",\"epGeneratedClass\":\"eplus-wrapper\"} -->\n<div style=\"height:10px\" aria-hidden=\"true\" class=\"wp-block-spacer eplus-wrapper\"><\/div>\n<!-- \/wp:spacer -->\n\n<!-- wp:paragraph {\"epAnimationGeneratedClass\":\"edplus_anim-hp5qSn\",\"epGeneratedClass\":\"eplus-wrapper\"} -->\n<p class=\" eplus-wrapper\"><strong>Autors<\/strong>: Tomasz Szczepa\u0144ski, Szymon P\u0142otka<\/p>\n<!-- \/wp:paragraph -->\n\n<!-- wp:spacer {\"height\":\"10px\",\"epAnimationGeneratedClass\":\"edplus_anim-Foh52t\",\"epGeneratedClass\":\"eplus-wrapper\"} -->\n<div style=\"height:10px\" aria-hidden=\"true\" class=\"wp-block-spacer eplus-wrapper\"><\/div>\n<!-- \/wp:spacer -->\n\n<!-- wp:acf\/button {\"id\":\"block_6a5756f5675d6\",\"name\":\"acf\/button\",\"data\":{\"title\":\"Read the article\",\"_title\":\"field_61d40397c2f0a\",\"button_type\":\"link\",\"_button_type\":\"field_63bbde3b8f0d0\",\"url\":\"https:\/\/openreview.net\/pdf\/b44be6adb46f5df93fe0acda06485b0aa7d47056.pdf\",\"_url\":\"field_61d4039bc2f0b\",\"button_style\":\"primary\",\"_button_style\":\"field_63872d045d0f0\",\"target\":\"_blank\",\"_target\":\"field_63872c705d0ef\",\"button_extra_classes\":\"\",\"_button_extra_classes\":\"field_642beab6a97de\"},\"align\":\"\",\"mode\":\"edit\"} \/-->","post_title":"Morphology-Driven Deep Watershed Transform for 3D Tooth Segmentation","post_excerpt":"ODIN Workshop @ MICCAI, 2025","post_status":"publish","comment_status":"closed","ping_status":"closed","post_password":"","post_name":"morphology-driven-deep-watershed-transform-for-3d-tooth-segmentation","to_ping":"","pinged":"","post_modified":"2026-07-15 11:49:14","post_modified_gmt":"2026-07-15 09:49:14","post_content_filtered":"","post_parent":0,"guid":"https:\/\/sano.science\/?post_type=research&p=31940","menu_order":0,"post_type":"research","post_mime_type":"","comment_count":"0","filter":"raw"},{"ID":31931,"post_author":"8","post_date":"2026-07-15 11:44:06","post_date_gmt":"2026-07-15 09:44:06","post_content":"<!-- wp:paragraph {\"epAnimationGeneratedClass\":\"edplus_anim-eTNyM8\",\"epGeneratedClass\":\"eplus-wrapper\"} -->\n<p class=\" eplus-wrapper\">Precise segmentation of teeth in Cone-Beam Computed Tomography (CBCT) scans is a longstanding challenge in computational dentistry, particularly when it comes to fine anatomical structures such as root apices \u2014 whose accurate delineation is essential for evaluating root resorption in orthodontic practice.<\/p>\n<!-- \/wp:paragraph -->\n\n<!-- wp:paragraph {\"epAnimationGeneratedClass\":\"edplus_anim-gDMLq9\",\"epGeneratedClass\":\"eplus-wrapper\"} -->\n<p class=\" eplus-wrapper\">This study presents GEPAR3D, a new method that combines instance detection and multi-class segmentation into a single unified pipeline, specifically designed to improve root-level segmentation accuracy. The approach incorporates a Statistical Shape Model of dentition as a geometric prior, enabling the model to capture anatomical context and morphological consistency without imposing rigid spatial constraints. To handle the complexity of narrow root structures, GEPAR3D employs a deep watershed technique that represents each tooth as a continuous 3D energy basin encoding voxel distances to boundaries \u2014 an instance-aware formulation that proves particularly effective for challenging apex regions.<\/p>\n<!-- \/wp:paragraph -->\n\n<!-- wp:paragraph {\"epAnimationGeneratedClass\":\"edplus_anim-cbPeZ2\",\"epGeneratedClass\":\"eplus-wrapper\"} -->\n<p class=\" eplus-wrapper\">Trained on publicly available CBCT data from a single center and evaluated across four external test sets from both in-house and public medical institutions, GEPAR3D demonstrates strong generalization. The method achieves a mean Dice Similarity Coefficient of 95.0% \u2014 2.8 percentage points above the next best approach \u2014 and a recall of 95.2%, representing a 9.5-point improvement. Qualitative results further confirm meaningful gains in root segmentation quality, pointing to real clinical potential for more reliable root resorption assessment and improved orthodontic decision support. Implementation and dataset are publicly available.<\/p>\n<!-- \/wp:paragraph -->\n\n<!-- wp:spacer {\"height\":\"10px\",\"epAnimationGeneratedClass\":\"edplus_anim-jSj8gT\",\"epGeneratedClass\":\"eplus-wrapper\"} -->\n<div style=\"height:10px\" aria-hidden=\"true\" class=\"wp-block-spacer eplus-wrapper\"><\/div>\n<!-- \/wp:spacer -->\n\n<!-- wp:paragraph {\"epAnimationGeneratedClass\":\"edplus_anim-6Kk4KB\",\"epGeneratedClass\":\"eplus-wrapper\"} -->\n<p class=\" eplus-wrapper\"><strong>Autors<\/strong>: Tomasz Szczepa\u0144ski, Szymon P\u0142otka,\u00a0Michal K.\u00a0Grzeszczyk, Arleta\u00a0Adamowicz,\u00a0Piotr\u00a0Fudalej, Przemys\u0142aw\u00a0Korzeniowski,\u00a0Tomasz\u00a0Trzci\u0144ski,\u00a0 Arkadiusz\u00a0Sitek<\/p>\n<!-- \/wp:paragraph -->\n\n<!-- wp:spacer {\"height\":\"10px\",\"epAnimationGeneratedClass\":\"edplus_anim-ObCQst\",\"epGeneratedClass\":\"eplus-wrapper\"} -->\n<div style=\"height:10px\" aria-hidden=\"true\" class=\"wp-block-spacer eplus-wrapper\"><\/div>\n<!-- \/wp:spacer -->\n\n<!-- wp:acf\/button {\"id\":\"block_6a575647ca7cb\",\"name\":\"acf\/button\",\"data\":{\"title\":\"Read the article\",\"_title\":\"field_61d40397c2f0a\",\"button_type\":\"link\",\"_button_type\":\"field_63bbde3b8f0d0\",\"url\":\"https:\/\/papers.miccai.org\/miccai-2025\/0375-Paper1833.html\",\"_url\":\"field_61d4039bc2f0b\",\"button_style\":\"primary\",\"_button_style\":\"field_63872d045d0f0\",\"target\":\"_self\",\"_target\":\"field_63872c705d0ef\",\"button_extra_classes\":\"\",\"_button_extra_classes\":\"field_642beab6a97de\"},\"align\":\"\",\"mode\":\"edit\"} \/-->","post_title":"GEPAR3D: Geometry Prior-Assisted Learning for 3D Tooth Segmentation","post_excerpt":"MICCAI, 2025","post_status":"publish","comment_status":"closed","ping_status":"closed","post_password":"","post_name":"gepar3d-geometry-prior-assisted-learning-for-3d-tooth-segmentation","to_ping":"","pinged":"","post_modified":"2026-07-16 10:52:05","post_modified_gmt":"2026-07-16 08:52:05","post_content_filtered":"","post_parent":0,"guid":"https:\/\/sano.science\/?post_type=research&p=31931","menu_order":0,"post_type":"research","post_mime_type":"","comment_count":"0","filter":"raw"},{"ID":20981,"post_author":"8","post_date":"2025-01-23 16:27:26","post_date_gmt":"2025-01-23 15:27:26","post_content":"<!-- wp:paragraph {\"epAnimationGeneratedClass\":\"edplus_anim-qgykSO\",\"epGeneratedClass\":\"eplus-wrapper\"} -->\n<p class=\" eplus-wrapper\">Twin-to-Twin Transfusion Syndrome (TTTS) occurs in about 15% of monochorionic pregnancies, where identical twins share one placenta.Fetoscopic laser photocoagulation (FLP) is the established therapeutic approach for this condition, substantially enhancing the chances of survival for the fetuses. The procedure aims to locate and eradicate abnormal vascular connections to normalize the blood distribution between the twins. Yet, fetoscopic operations are technically demanding, primarily due to poor visibility, and significant variability among patients and domains.<\/p>\n<!-- \/wp:paragraph -->\n\n<!-- wp:paragraph {\"epAnimationGeneratedClass\":\"edplus_anim-RlsQgH\",\"epGeneratedClass\":\"eplus-wrapper\"} -->\n<p class=\" eplus-wrapper\">To advance the visualization capabilities during these interventions, we have introduced TTTSNet, a specialized network designed to segment placental vessels accurately in real-time. This network integrates innovative elements such as a channel attention module and a feature fusion module that operates at multiple scales, ensuring detailed and precise imaging of the placental vessels, including the smaller ones. Additionally, to overcome the typical visual disturbances encountered during FLP, such as those caused by the fiberscope and amniotic debris, we implemented advanced data augmentation strategies. These strategies effectively recreate various surgical artifacts in the training data, enhancing the model's ability to generalize across different scenarios.<\/p>\n<!-- \/wp:paragraph -->\n\n<!-- wp:paragraph {\"epAnimationGeneratedClass\":\"edplus_anim-qgykSO\",\"epGeneratedClass\":\"eplus-wrapper\"} -->\n<p class=\" eplus-wrapper\">TTTSNet was rigorously trained on a dataset comprising 2060 video frames from 18 distinct fetoscopic surgeries and further validated on an external dataset from 24 in-vivo procedures, which included 2348 video frames. The results were superior to those of current leading methods, achieving a mean Intersection over Union (IoU) of 78.26% across all detected vessels, and 73.35% for smaller vessels specifically. The performance rates of 172 frames per second on an A100 GPU and 152 frames per second on a Clara AGX platform demonstrate the potential of TTTSNet to support real-time surgical applications. For broader accessibility and use, the TTTSNet code has been made publicly available at the following URL: <a target=\"_blank\" href=\"https:\/\/github.com\/SanoScience\/TTTSNet\" rel=\"noreferrer noopener\">https:\/\/github.com\/SanoScience\/TTTSNet<\/a>.<\/p>\n<!-- \/wp:paragraph -->\n\n<!-- wp:spacer {\"height\":\"40px\",\"epAnimationGeneratedClass\":\"edplus_anim-oKrUcQ\",\"epGeneratedClass\":\"eplus-wrapper\"} -->\n<div style=\"height:40px\" aria-hidden=\"true\" class=\"wp-block-spacer eplus-wrapper\"><\/div>\n<!-- \/wp:spacer -->\n\n<!-- wp:paragraph {\"anchor\":\"h-autors-szymon-plotka-tomasz-szczepanski-paula-szenejko-przemyslaw-korzeniowski-jesus-rodriguez-calvo-asma-khalil-alireza-shamshirsaz-robert-brawura-biskupski-samaha-ivana-isgum-clara-i-sanchez-arkadiusz-sitek\",\"epAnimationGeneratedClass\":\"edplus_anim-I2wTFv\",\"epGeneratedClass\":\"eplus-wrapper\"} -->\n<p id=\"h-autors-szymon-plotka-tomasz-szczepanski-paula-szenejko-przemyslaw-korzeniowski-jesus-rodriguez-calvo-asma-khalil-alireza-shamshirsaz-robert-brawura-biskupski-samaha-ivana-isgum-clara-i-sanchez-arkadiusz-sitek\" class=\" eplus-wrapper\"><strong>Autors<\/strong>: Szymon P\u0142otka, Tomasz Szczepa\u0144ski, Paula Szenejko, Przemys\u0142aw Korzeniowski, Jesus Rodriguez Calvo, Asma Khalil, Alireza Shamshirsaz, Robert Brawura-Biskupski Samaha, Ivana I\u0161gum, Clara I. S\u00e1nchez, Arkadiusz Sitek<\/p>\n<!-- \/wp:paragraph -->\n\n<!-- wp:paragraph {\"epAnimationGeneratedClass\":\"edplus_anim-K1RoBV\",\"epGeneratedClass\":\"eplus-wrapper\"} -->\n<p class=\" eplus-wrapper\"><strong>Keywords<\/strong>: Deep learning, Semantic segmentation, Twin-to-Twin Transfusion Syndrome (TTTS), Fetoscopic Laser Surgery<\/p>\n<!-- \/wp:paragraph -->\n\n<!-- wp:paragraph {\"epAnimationGeneratedClass\":\"edplus_anim-K1RoBV\",\"epGeneratedClass\":\"eplus-wrapper\"} -->\n<p class=\" eplus-wrapper\"><strong>DOI<\/strong>: 10.1016\/j.media.2024.103330<\/p>\n<!-- \/wp:paragraph -->\n\n<!-- wp:spacer {\"height\":\"40px\",\"epAnimationGeneratedClass\":\"edplus_anim-oKrUcQ\",\"epGeneratedClass\":\"eplus-wrapper\"} -->\n<div style=\"height:40px\" aria-hidden=\"true\" class=\"wp-block-spacer eplus-wrapper\"><\/div>\n<!-- \/wp:spacer -->\n\n<!-- wp:acf\/button {\"id\":\"block_67925f9cc8fc2\",\"name\":\"acf\/button\",\"data\":{\"title\":\"Read the article\",\"_title\":\"field_61d40397c2f0a\",\"button_type\":\"link\",\"_button_type\":\"field_63bbde3b8f0d0\",\"url\":\"https:\/\/www.sciencedirect.com\/science\/article\/pii\/S136184152400255X?via%3Dihub\",\"_url\":\"field_61d4039bc2f0b\",\"button_style\":\"primary\",\"_button_style\":\"field_63872d045d0f0\",\"target\":\"_self\",\"_target\":\"field_63872c705d0ef\",\"button_extra_classes\":\"\",\"_button_extra_classes\":\"field_642beab6a97de\"},\"align\":\"\",\"mode\":\"edit\"} \/-->","post_title":"Real-time placental vessel segmentation in fetoscopic laser surgery for Twin-to-Twin Transfusion Syndrome","post_excerpt":"Inarticle in journal: Medical Image Analysis, 2025","post_status":"publish","comment_status":"closed","ping_status":"closed","post_password":"","post_name":"real-time-placental-vessel-segmentation-in-fetoscopic-laser-surgery-for-twin-to-twin-transfusion-syndrome","to_ping":"","pinged":"","post_modified":"2026-07-16 10:50:26","post_modified_gmt":"2026-07-16 08:50:26","post_content_filtered":"","post_parent":0,"guid":"https:\/\/sano.science\/?post_type=research&p=20981","menu_order":0,"post_type":"research","post_mime_type":"","comment_count":"0","filter":"raw"},{"ID":31910,"post_author":"8","post_date":"2026-07-15 11:21:29","post_date_gmt":"2026-07-15 09:21:29","post_content":"<!-- wp:paragraph {\"epAnimationGeneratedClass\":\"edplus_anim-jTntAc\",\"epGeneratedClass\":\"eplus-wrapper\"} -->\n<p class=\" eplus-wrapper\">Accurate segmentation of the Inferior Alveolar Canal (IAC) in Cone-Beam Computed Tomography (CBCT) scans is a clinically important yet technically demanding task. Despite growing interest in automated approaches, the field has long lacked publicly available datasets and standardized benchmarks, making systematic comparison between methods difficult.<\/p>\n<!-- \/wp:paragraph -->\n\n<!-- wp:paragraph {\"epAnimationGeneratedClass\":\"edplus_anim-28eVss\",\"epGeneratedClass\":\"eplus-wrapper\"} -->\n<p class=\" eplus-wrapper\">To address this gap, the ToothFairy challenge was organized as part of the MICCAI 2023 conference. A dedicated public dataset of 443 CBCT scans was released, with voxel-level IAC annotations available for 153 of them \u2014 the largest resource of its kind to date. Participants were challenged to develop algorithms capable of accurately identifying the IAC from both 2D and 3D annotated data.<\/p>\n<!-- \/wp:paragraph -->\n\n<!-- wp:paragraph {\"epAnimationGeneratedClass\":\"edplus_anim-jTntAc\",\"epGeneratedClass\":\"eplus-wrapper\"} -->\n<p class=\" eplus-wrapper\">This paper documents the challenge in detail and evaluates the most promising submitted solutions, offering the first comprehensive comparison of IAC segmentation methods on a shared benchmark. Beyond summarizing the current state of the art, the authors identify key open challenges and outline directions for future research. To support reproducibility and continued development, an open-source repository collecting the best-performing implementations has also been made available.<\/p>\n<!-- \/wp:paragraph -->\n\n<!-- wp:spacer {\"height\":\"10px\",\"epAnimationGeneratedClass\":\"edplus_anim-vFQbpj\",\"epGeneratedClass\":\"eplus-wrapper\"} -->\n<div style=\"height:10px\" aria-hidden=\"true\" class=\"wp-block-spacer eplus-wrapper\"><\/div>\n<!-- \/wp:spacer -->\n\n<!-- wp:paragraph {\"epAnimationGeneratedClass\":\"edplus_anim-jTntAc\",\"epGeneratedClass\":\"eplus-wrapper\"} -->\n<p class=\" eplus-wrapper\"><strong>Published by an international team of researchers<\/strong>. Among the co-authors are Sano scientists: Tomasz Szczepa\u0144ski, Michal K. Grzeszczyk and Przemyslaw Korzeniowski.<a href=\"https:\/\/orcid.org\/0000-0001-5391-1295\" target=\"_blank\" rel=\"noreferrer noopener\"><\/a><a href=\"https:\/\/orcid.org\/0000-0001-6189-478X\" target=\"_blank\" rel=\"noreferrer noopener\"><\/a><\/p>\n<!-- \/wp:paragraph -->\n\n<!-- wp:spacer {\"height\":\"10px\",\"epAnimationGeneratedClass\":\"edplus_anim-0l7Odf\",\"epGeneratedClass\":\"eplus-wrapper\"} -->\n<div style=\"height:10px\" aria-hidden=\"true\" class=\"wp-block-spacer eplus-wrapper\"><\/div>\n<!-- \/wp:spacer -->\n\n<!-- wp:acf\/button {\"id\":\"block_6a5750ffc09f8\",\"name\":\"acf\/button\",\"data\":{\"title\":\"Read the article\",\"_title\":\"field_61d40397c2f0a\",\"button_type\":\"link\",\"_button_type\":\"field_63bbde3b8f0d0\",\"url\":\"https:\/\/ieeexplore.ieee.org\/document\/10816445\",\"_url\":\"field_61d4039bc2f0b\",\"button_style\":\"primary\",\"_button_style\":\"field_63872d045d0f0\",\"target\":\"_blank\",\"_target\":\"field_63872c705d0ef\",\"button_extra_classes\":\"\",\"_button_extra_classes\":\"field_642beab6a97de\"},\"align\":\"\",\"mode\":\"edit\"} \/-->","post_title":"Segmenting the Inferior Alveolar Canal in CBCTs Volumes: the ToothFairy Challenge","post_excerpt":"IEEE Transactions on Medical Imaging, 2025","post_status":"publish","comment_status":"closed","ping_status":"closed","post_password":"","post_name":"segmenting-the-inferior-alveolar-canal-in-cbcts-volumes-the-toothfairy-challenge","to_ping":"","pinged":"","post_modified":"2026-07-15 11:31:36","post_modified_gmt":"2026-07-15 09:31:36","post_content_filtered":"","post_parent":0,"guid":"https:\/\/sano.science\/?post_type=research&p=31910","menu_order":0,"post_type":"research","post_mime_type":"","comment_count":"0","filter":"raw"},{"ID":31922,"post_author":"8","post_date":"2026-07-15 11:34:37","post_date_gmt":"2026-07-15 09:34:37","post_content":"<!-- wp:paragraph {\"epAnimationGeneratedClass\":\"edplus_anim-JAQj6P\",\"epGeneratedClass\":\"eplus-wrapper\"} -->\n<p class=\" eplus-wrapper\">Training deep learning models for 3D segmentation remains a demanding task, requiring strategies that are both computationally efficient and capable of generalizing well to unseen data. This study presents DeCode, a novel conditioning approach that leverages label-derived features to dynamically support the decoder during the reconstruction process \u2014 with the goal of improving both training efficiency and segmentation quality.<\/p>\n<!-- \/wp:paragraph -->\n\n<!-- wp:paragraph {\"epAnimationGeneratedClass\":\"edplus_anim-RauE4y\",\"epGeneratedClass\":\"eplus-wrapper\"} -->\n<p class=\" eplus-wrapper\">At the core of DeCode is the use of conditioning embeddings built from learned numerical representations of 3D label shape features. During training, these embeddings guide the network toward more robust segmentation. At inference time, when labels are unavailable, the model predicts the necessary conditioning information directly from the input, using a feed-forward network trained alongside the main model.<\/p>\n<!-- \/wp:paragraph -->\n\n<!-- wp:paragraph {\"epAnimationGeneratedClass\":\"edplus_anim-bx43Al\",\"epGeneratedClass\":\"eplus-wrapper\"} -->\n<p class=\" eplus-wrapper\">DeCode was evaluated on synthetic data and cone-beam computed tomography (CBCT) images of teeth, using three CBCT datasets \u2014 one public and two in-house. The results demonstrate that DeCode consistently outperforms unconditioned baseline models in generalization to new data, achieving higher accuracy at a lower computational cost. This work is the first to explore conditioning strategies specifically in the context of 3D segmentation, offering a more efficient way to make use of annotated training data. Code and pre-trained models are publicly available.<\/p>\n<!-- \/wp:paragraph -->\n\n<!-- wp:spacer {\"height\":\"10px\",\"epAnimationGeneratedClass\":\"edplus_anim-0Z178I\",\"epGeneratedClass\":\"eplus-wrapper\"} -->\n<div style=\"height:10px\" aria-hidden=\"true\" class=\"wp-block-spacer eplus-wrapper\"><\/div>\n<!-- \/wp:spacer -->\n\n<!-- wp:paragraph {\"epAnimationGeneratedClass\":\"edplus_anim-txzgV7\",\"epGeneratedClass\":\"eplus-wrapper\"} -->\n<p class=\" eplus-wrapper\"><strong>Autors<\/strong>: Tomasz Szczepa\u0144ski, \u00a0Michal K.\u00a0 Grzeszczyk, Szymon\u00a0P\u0142otka,\u00a0Arleta\u00a0Adamowicz, Piotr\u00a0\u00a0Fudalej, Przemys\u0142aw\u00a0Korzeniowski,\u00a0Tomasz\u00a0Trzci\u0144ski, Tomasz Sitek<\/p>\n<!-- \/wp:paragraph -->\n\n<!-- wp:spacer {\"height\":\"10px\",\"epAnimationGeneratedClass\":\"edplus_anim-lNok0m\",\"epGeneratedClass\":\"eplus-wrapper\"} -->\n<div style=\"height:10px\" aria-hidden=\"true\" class=\"wp-block-spacer eplus-wrapper\"><\/div>\n<!-- \/wp:spacer -->\n\n<!-- wp:acf\/button {\"id\":\"block_6a57528ef67bc\",\"name\":\"acf\/button\",\"data\":{\"title\":\"\",\"_title\":\"field_61d40397c2f0a\",\"button_type\":\"link\",\"_button_type\":\"field_63bbde3b8f0d0\",\"url\":\"\",\"_url\":\"field_61d4039bc2f0b\",\"button_style\":\"primary\",\"_button_style\":\"field_63872d045d0f0\",\"target\":\"_self\",\"_target\":\"field_63872c705d0ef\",\"button_extra_classes\":\"\",\"_button_extra_classes\":\"field_642beab6a97de\"},\"align\":\"\",\"mode\":\"edit\"} \/-->","post_title":"Let Me DeCode You: Decoder Conditioning with Tabular Data","post_excerpt":"MICCAI, 2024","post_status":"publish","comment_status":"closed","ping_status":"closed","post_password":"","post_name":"let-me-decode-you-decoder-conditioning-with-tabular-data","to_ping":"","pinged":"","post_modified":"2026-07-15 11:34:37","post_modified_gmt":"2026-07-15 09:34:37","post_content_filtered":"","post_parent":0,"guid":"https:\/\/sano.science\/?post_type=research&p=31922","menu_order":0,"post_type":"research","post_mime_type":"","comment_count":"0","filter":"raw"},{"ID":12676,"post_author":"8","post_date":"2023-07-13 13:17:33","post_date_gmt":"2023-07-13 11:17:33","post_content":"<!-- wp:paragraph {\"epAnimationGeneratedClass\":\"edplus_anim-dB1sHB\",\"epGeneratedClass\":\"eplus-wrapper\"} -->\n<p class=\" eplus-wrapper\">Effective screening of patients presenting with severe respiratory symptoms remains a cornerstone of managing infectious disease outbreaks at scale. Chest radiography has emerged as one of the more practical screening tools, and deep learning models applied to chest X-ray analysis have demonstrated strong diagnostic accuracy in numerous studies.<\/p>\n<!-- \/wp:paragraph -->\n\n<!-- wp:paragraph {\"epAnimationGeneratedClass\":\"edplus_anim-eZf0Qc\",\"epGeneratedClass\":\"eplus-wrapper\"} -->\n<p class=\" eplus-wrapper\">However, a significant limitation of many published approaches lies in their lack of transparency: it is often unclear on what basis a model reaches its conclusions. Using explainable artificial intelligence methods, this study reveals that model decisions can be driven by confounding factors present in the image rather than clinically relevant pathology. Following a systematic analysis of such factors in chest X-ray data \u2014 including artefacts such as ECG leads \u2014 the authors propose a novel method to reduce their influence on model predictions.<\/p>\n<!-- \/wp:paragraph -->\n\n<!-- wp:paragraph {\"epAnimationGeneratedClass\":\"edplus_anim-FcyIzj\",\"epGeneratedClass\":\"eplus-wrapper\"} -->\n<p class=\" eplus-wrapper\">The proposed approach proves more robust against these confounders than previously published solutions, while maintaining performance comparable to state-of-the-art methods. By addressing the gap between predictive accuracy and decision transparency, this work contributes to the development of more trustworthy and clinically reliable deep learning tools. Source code and pre-trained model weights are publicly available.<\/p>\n<!-- \/wp:paragraph -->\n\n<!-- wp:spacer {\"height\":\"10px\",\"epAnimationGeneratedClass\":\"edplus_anim-ypkope\",\"epGeneratedClass\":\"eplus-wrapper\"} -->\n<div style=\"height:10px\" aria-hidden=\"true\" class=\"wp-block-spacer eplus-wrapper\"><\/div>\n<!-- \/wp:spacer -->\n\n<!-- wp:paragraph {\"epAnimationGeneratedClass\":\"edplus_anim-AsClUj\",\"epGeneratedClass\":\"eplus-wrapper\"} -->\n<p class=\" eplus-wrapper\"><strong>Autors:<\/strong> Tomasz Szczepa\u0144ski, Arkadiusz Sitek, Tomasz Trzci\u0144ski, Szymon P\u0142otka<\/p>\n<!-- \/wp:paragraph -->\n\n<!-- wp:paragraph {\"epAnimationGeneratedClass\":\"edplus_anim-Otfb7u\",\"epGeneratedClass\":\"eplus-wrapper\"} -->\n<p class=\" eplus-wrapper\"><strong>Keywords<\/strong>: COVID-19, Deep learning, Explainable AI<\/p>\n<!-- \/wp:paragraph -->\n\n<!-- wp:spacer {\"height\":\"30px\",\"epAnimationGeneratedClass\":\"edplus_anim-ypkope\",\"epGeneratedClass\":\"eplus-wrapper\"} -->\n<div style=\"height:30px\" aria-hidden=\"true\" class=\"wp-block-spacer eplus-wrapper\"><\/div>\n<!-- \/wp:spacer -->\n\n<!-- wp:acf\/button {\"id\":\"block_64c02cf3f5e7b\",\"name\":\"acf\/button\",\"data\":{\"title\":\"Read the article\",\"_title\":\"field_61d40397c2f0a\",\"button_type\":\"link\",\"_button_type\":\"field_63bbde3b8f0d0\",\"url\":\"https:\/\/arxiv.org\/pdf\/2201.09360.pdf\",\"_url\":\"field_61d4039bc2f0b\",\"button_style\":\"primary\",\"_button_style\":\"field_63872d045d0f0\",\"target\":\"_blank\",\"_target\":\"field_63872c705d0ef\",\"button_extra_classes\":\"\",\"_button_extra_classes\":\"field_642beab6a97de\"},\"align\":\"\",\"mode\":\"edit\"} \/-->","post_title":"POTHER: Patch-Voted Deep Learning-based Chest X-ray Bias Analysis for COVID-19 Detection\u00a0","post_excerpt":"In: 22nd International Conference on Computational Science, 2022.","post_status":"publish","comment_status":"closed","ping_status":"closed","post_password":"","post_name":"pother-patch-voted-deep-learning-based-chest-x-ray-bias-analysis-for-covid-19-detection-2","to_ping":"","pinged":"","post_modified":"2026-07-16 10:57:29","post_modified_gmt":"2026-07-16 08:57:29","post_content_filtered":"","post_parent":0,"guid":"https:\/\/new.sano.science\/?post_type=research&p=12676","menu_order":63,"post_type":"research","post_mime_type":"","comment_count":"0","filter":"raw"}]},"_links":{"self":[{"href":"https:\/\/sano.science\/index.php\/wp-json\/wp\/v2\/people\/12056","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/sano.science\/index.php\/wp-json\/wp\/v2\/people"}],"about":[{"href":"https:\/\/sano.science\/index.php\/wp-json\/wp\/v2\/types\/people"}],"version-history":[{"count":12,"href":"https:\/\/sano.science\/index.php\/wp-json\/wp\/v2\/people\/12056\/revisions"}],"predecessor-version":[{"id":31980,"href":"https:\/\/sano.science\/index.php\/wp-json\/wp\/v2\/people\/12056\/revisions\/31980"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/sano.science\/index.php\/wp-json\/wp\/v2\/media\/31801"}],"wp:attachment":[{"href":"https:\/\/sano.science\/index.php\/wp-json\/wp\/v2\/media?parent=12056"}],"wp:term":[{"taxonomy":"people_teams","embeddable":true,"href":"https:\/\/sano.science\/index.php\/wp-json\/wp\/v2\/people_teams?post=12056"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}