HistoMSC: Density and topology analysis for AI-based visual annotation of histopathology whole slide images

<p>We introduce an end-to-end framework for the automated visual annotation of histopathology whole slide images. Our method integrates deep learning models to achieve precise localization and classification of cell nuclei with spatial data aggregation to extend classes of sparsely distributed...

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: Zahoor Ahmad (358103) (author)
مؤلفون آخرون: Khaled Al-Thelaya (17302711) (author), Mahmood Alzubaidi (15740693) (author), Faaiz Joad (21015119) (author), Nauman Ullah Gilal (17302714) (author), William Mifsud (1394) (author), Sabri Boughorbel (846228) (author), Giovanni Pintore (17302717) (author), Enrico Gobbetti (17302720) (author), Jens Schneider (16885948) (author), Marco Agus (8032898) (author)
منشور في: 2025
الموضوعات:
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
_version_ 1864513550738784256
author Zahoor Ahmad (358103)
author2 Khaled Al-Thelaya (17302711)
Mahmood Alzubaidi (15740693)
Faaiz Joad (21015119)
Nauman Ullah Gilal (17302714)
William Mifsud (1394)
Sabri Boughorbel (846228)
Giovanni Pintore (17302717)
Enrico Gobbetti (17302720)
Jens Schneider (16885948)
Marco Agus (8032898)
author2_role author
author
author
author
author
author
author
author
author
author
author_facet Zahoor Ahmad (358103)
Khaled Al-Thelaya (17302711)
Mahmood Alzubaidi (15740693)
Faaiz Joad (21015119)
Nauman Ullah Gilal (17302714)
William Mifsud (1394)
Sabri Boughorbel (846228)
Giovanni Pintore (17302717)
Enrico Gobbetti (17302720)
Jens Schneider (16885948)
Marco Agus (8032898)
author_role author
dc.creator.none.fl_str_mv Zahoor Ahmad (358103)
Khaled Al-Thelaya (17302711)
Mahmood Alzubaidi (15740693)
Faaiz Joad (21015119)
Nauman Ullah Gilal (17302714)
William Mifsud (1394)
Sabri Boughorbel (846228)
Giovanni Pintore (17302717)
Enrico Gobbetti (17302720)
Jens Schneider (16885948)
Marco Agus (8032898)
dc.date.none.fl_str_mv 2025-03-21T09:00:00Z
dc.identifier.none.fl_str_mv 10.1016/j.compbiomed.2025.109991
dc.relation.none.fl_str_mv https://figshare.com/articles/journal_contribution/HistoMSC_Density_and_topology_analysis_for_AI-based_visual_annotation_of_histopathology_whole_slide_images/28748321
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Engineering
Biomedical engineering
Health sciences
Health services and systems
Information and computing sciences
Artificial intelligence
Computer vision and multimedia computation
Histopathology
AI-based annotation
Nuclei localization
Kernel density estimation
Morse–Smale complex
dc.title.none.fl_str_mv HistoMSC: Density and topology analysis for AI-based visual annotation of histopathology whole slide images
dc.type.none.fl_str_mv Text
Journal contribution
info:eu-repo/semantics/publishedVersion
text
contribution to journal
description <p>We introduce an end-to-end framework for the automated visual annotation of histopathology whole slide images. Our method integrates deep learning models to achieve precise localization and classification of cell nuclei with spatial data aggregation to extend classes of sparsely distributed nuclei across the entire slide. We introduce a novel and cost-effective approach to localization, leveraging a U-Net architecture and a ResNet-50 backbone. The performance is boosted through color normalization techniques, helping achieve robustness under color variations resulting from diverse scanners and staining reagents. The framework is complemented by a YOLO detection architecture, augmented with generative methods. For classification, we use context patches around each nucleus, fed to various deep architectures. Sparse nuclei-level annotations are then aggregated using kernel density estimation, followed by color-coding and isocontouring. This reduces visual clutter and provides per-pixel probabilities with respect to pathology taxonomies. Finally, we use Morse–Smale theory to generate abstract annotations, highlighting extrema in the density functions and potential spatial interactions in the form of abstract graphs. Thus, our visualization allows for exploration at scales ranging from individual nuclei to the macro-scale. We tested the effectiveness of our framework in an assessment by six pathologists using various neoplastic cases. Our results demonstrate the robustness and usefulness of the proposed framework in aiding histopathologists in their analysis and interpretation of whole slide images.</p><h2>Other Information</h2> <p> Published in: Computers in Biology and Medicine<br> License: <a href="http://creativecommons.org/licenses/by/4.0/" target="_blank">http://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1016/j.compbiomed.2025.109991" target="_blank">https://dx.doi.org/10.1016/j.compbiomed.2025.109991</a></p>
eu_rights_str_mv openAccess
id Manara2_127fb2df4c09073e1a7e1b50cd0998af
identifier_str_mv 10.1016/j.compbiomed.2025.109991
network_acronym_str Manara2
network_name_str Manara2
oai_identifier_str oai:figshare.com:article/28748321
publishDate 2025
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling HistoMSC: Density and topology analysis for AI-based visual annotation of histopathology whole slide imagesZahoor Ahmad (358103)Khaled Al-Thelaya (17302711)Mahmood Alzubaidi (15740693)Faaiz Joad (21015119)Nauman Ullah Gilal (17302714)William Mifsud (1394)Sabri Boughorbel (846228)Giovanni Pintore (17302717)Enrico Gobbetti (17302720)Jens Schneider (16885948)Marco Agus (8032898)EngineeringBiomedical engineeringHealth sciencesHealth services and systemsInformation and computing sciencesArtificial intelligenceComputer vision and multimedia computationHistopathologyAI-based annotationNuclei localizationKernel density estimationMorse–Smale complex<p>We introduce an end-to-end framework for the automated visual annotation of histopathology whole slide images. Our method integrates deep learning models to achieve precise localization and classification of cell nuclei with spatial data aggregation to extend classes of sparsely distributed nuclei across the entire slide. We introduce a novel and cost-effective approach to localization, leveraging a U-Net architecture and a ResNet-50 backbone. The performance is boosted through color normalization techniques, helping achieve robustness under color variations resulting from diverse scanners and staining reagents. The framework is complemented by a YOLO detection architecture, augmented with generative methods. For classification, we use context patches around each nucleus, fed to various deep architectures. Sparse nuclei-level annotations are then aggregated using kernel density estimation, followed by color-coding and isocontouring. This reduces visual clutter and provides per-pixel probabilities with respect to pathology taxonomies. Finally, we use Morse–Smale theory to generate abstract annotations, highlighting extrema in the density functions and potential spatial interactions in the form of abstract graphs. Thus, our visualization allows for exploration at scales ranging from individual nuclei to the macro-scale. We tested the effectiveness of our framework in an assessment by six pathologists using various neoplastic cases. Our results demonstrate the robustness and usefulness of the proposed framework in aiding histopathologists in their analysis and interpretation of whole slide images.</p><h2>Other Information</h2> <p> Published in: Computers in Biology and Medicine<br> License: <a href="http://creativecommons.org/licenses/by/4.0/" target="_blank">http://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1016/j.compbiomed.2025.109991" target="_blank">https://dx.doi.org/10.1016/j.compbiomed.2025.109991</a></p>2025-03-21T09:00:00ZTextJournal contributioninfo:eu-repo/semantics/publishedVersiontextcontribution to journal10.1016/j.compbiomed.2025.109991https://figshare.com/articles/journal_contribution/HistoMSC_Density_and_topology_analysis_for_AI-based_visual_annotation_of_histopathology_whole_slide_images/28748321CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/287483212025-03-21T09:00:00Z
spellingShingle HistoMSC: Density and topology analysis for AI-based visual annotation of histopathology whole slide images
Zahoor Ahmad (358103)
Engineering
Biomedical engineering
Health sciences
Health services and systems
Information and computing sciences
Artificial intelligence
Computer vision and multimedia computation
Histopathology
AI-based annotation
Nuclei localization
Kernel density estimation
Morse–Smale complex
status_str publishedVersion
title HistoMSC: Density and topology analysis for AI-based visual annotation of histopathology whole slide images
title_full HistoMSC: Density and topology analysis for AI-based visual annotation of histopathology whole slide images
title_fullStr HistoMSC: Density and topology analysis for AI-based visual annotation of histopathology whole slide images
title_full_unstemmed HistoMSC: Density and topology analysis for AI-based visual annotation of histopathology whole slide images
title_short HistoMSC: Density and topology analysis for AI-based visual annotation of histopathology whole slide images
title_sort HistoMSC: Density and topology analysis for AI-based visual annotation of histopathology whole slide images
topic Engineering
Biomedical engineering
Health sciences
Health services and systems
Information and computing sciences
Artificial intelligence
Computer vision and multimedia computation
Histopathology
AI-based annotation
Nuclei localization
Kernel density estimation
Morse–Smale complex