{"id":{"repo_id":"qu-belfast","oai_identifier":"oai:pure.qub.ac.uk/portal:studenttheses/af5f2ab4-858c-4ace-88d0-008e0bee67cc"},"canonical_url":"https://search.dev.ndltd.org/etd/qu-belfast/oai:pure.qub.ac.uk/portal:studenttheses/af5f2ab4-858c-4ace-88d0-008e0bee67cc","repository":{"repo_id":"qu-belfast","name":"Queen's University Belfast","base_url":"https://pureadmin.qub.ac.uk/ws/oai"},"display":{"title":"Deep learning for processing histopathology images","abstract":"Histopathology is the study and diagnosis of disease via tissue microscopy and it is currently the ‘gold-standard‘ in formally diagnosing many types of disease including cancers.<br/>Due to increasing workloads on pathologists, there is a growing need for automated image analysis pipelines that are able to filter out obviously benign samples. However, these algorithms are sensitive to factors of variation such as the staining and scanning conditions with which a tissue specimen is processed that differ significantly across institutions.<br/>In this thesis, novel machine learning algorithms are developed using state-of-the-art deep learning techniques that enable the creation of automated histopathology image<br/>analysis pipelines that are more robust to frequently occurring artifacts and variation in appearance.<br/><br/>A novel neural network architecture called the Dual-Channel Auto-Encoder (DCAE) is devised that learns representations of histopathology images that are invariant to the effects of differing digital slide scanners whilst holding enough discriminative power to delineate various anatomical structures within tissue. This method achieves a 50%<br/>improvement in SSIM score on tissue masks derived from the DCAE features compared to related methods. Next, a novel unsupervised approach to detect and remove artifacts using techniques from generative adversarial networks is presented. This approach allows artifacts to be removed prior to the application of stain separation which is demonstrated experimentally to improve the stain colour estimation performance. Finally, a more sophisticated model of stain separation called Tissue-Dependent Stain Separation (TDSS) is developed which incorporates contextual information such as texture and colour to make more informed estimates of stain colour conditioned on tissue<br/>sub-types and thus producing better separations of stains compared to state-of-the-art methods. The TDSS model achieves an 8.81% reduction in mean-squared error in a stain separation task compared to existing state-of-the-art-methods. These contributions represent a significant step forward towards robust, fully automated histopathology image analysis pipelines.","abstract_html":"Histopathology is the study and diagnosis of disease via tissue microscopy and it is currently the ‘gold-standard‘ in formally diagnosing many types of disease including cancers.&lt;br/&gt;Due to increasing workloads on pathologists, there is a growing need for automated image analysis pipelines that are able to filter out obviously benign samples. However, these algorithms are sensitive to factors of variation such as the staining and scanning conditions with which a tissue specimen is processed that differ significantly across institutions.&lt;br/&gt;In this thesis, novel machine learning algorithms are developed using state-of-the-art deep learning techniques that enable the creation of automated histopathology image&lt;br/&gt;analysis pipelines that are more robust to frequently occurring artifacts and variation in appearance.&lt;br/&gt;&lt;br/&gt;A novel neural network architecture called the Dual-Channel Auto-Encoder (DCAE) is devised that learns representations of histopathology images that are invariant to the effects of differing digital slide scanners whilst holding enough discriminative power to delineate various anatomical structures within tissue. This method achieves a 50%&lt;br/&gt;improvement in SSIM score on tissue masks derived from the DCAE features compared to related methods. Next, a novel unsupervised approach to detect and remove artifacts using techniques from generative adversarial networks is presented. This approach allows artifacts to be removed prior to the application of stain separation which is demonstrated experimentally to improve the stain colour estimation performance. Finally, a more sophisticated model of stain separation called Tissue-Dependent Stain Separation (TDSS) is developed which incorporates contextual information such as texture and colour to make more informed estimates of stain colour conditioned on tissue&lt;br/&gt;sub-types and thus producing better separations of stains compared to state-of-the-art methods. The TDSS model achieves an 8.81% reduction in mean-squared error in a stain separation task compared to existing state-of-the-art-methods. These contributions represent a significant step forward towards robust, fully automated histopathology image analysis pipelines.","abstract_has_math":false,"creators":["Moyes, Andrew"],"institution":"Queen's University Belfast","degree_name":"Doctor of Philosophy","degree_level":"Doctoral Thesis","degree_discipline":null,"degree_department":null,"school":null,"contributors":[],"advisors":["Ji, Ming","Gault, Richard"],"committee_chairs":[],"committee_members":[],"year":2021,"date_issued":"2021-7","date_published":"2021-7","updated_at":"2026-07-24T03:55:58Z","subjects":["Deep learning","computer vision","histopathology"],"languages":["eng"],"rights":[],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier","label":"Identifier","values":["oai:pure.qub.ac.uk/portal:studenttheses/af5f2ab4-858c-4ace-88d0-008e0bee67cc"],"render_values":[{"text":"oai:pure.qub.ac.uk/portal:studenttheses/af5f2ab4-858c-4ace-88d0-008e0bee67cc","href":null,"code":true}]}]},"links":{"outbound_url":"https://pure.qub.ac.uk/en/studentTheses/af5f2ab4-858c-4ace-88d0-008e0bee67cc","outbound_label":"Repository record","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Ji, Ming","Gault, Richard"]},{"key":"dc:contributor.sponsor","label":"Sponsor","values":["Invest Northern Ireland","Northern Ireland Department for the Economy"]},{"key":"dc:creator","label":"Author","values":["Moyes, Andrew"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2021-7"]},{"key":"dc:date.issued","label":"Date","values":["2021-7"]},{"key":"dc:publisher.department","label":"Dc Publisher Department","values":["School of Electronics, Electrical Engineering and Computer Science"]},{"key":"dc:publisher.institution","label":"Dc Publisher Institution","values":["Queen's University Belfast"]},{"key":"dc:relation.isreferencedby","label":"Dc Relation Isreferencedby","values":["https://pure.qub.ac.uk/en/studentTheses/af5f2ab4-858c-4ace-88d0-008e0bee67cc"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]},{"key":"dc:type.qualificationlevel","label":"Dc Type Qualificationlevel","values":["Doctoral Thesis"]},{"key":"dc:type.qualificationname","label":"Dc Type Qualificationname","values":["Doctor of Philosophy"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Deep learning","computer vision","histopathology"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["eng"]},{"key":"dc:rights.embargodate","label":"Dc Rights Embargodate","values":["2022-07-31"]},{"key":"dc:rights.embargoreason","label":"Dc Rights Embargoreason","values":["/dk/atira/pure/core/document/studentthesisembargoreason/publicationissues"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["oai:pure.qub.ac.uk/portal:studenttheses/af5f2ab4-858c-4ace-88d0-008e0bee67cc","https://pure.qub.ac.uk/en/studentTheses/af5f2ab4-858c-4ace-88d0-008e0bee67cc"]},{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://pure.qub.ac.uk/files/238764526/thesis.pdf"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Histopathology is the study and diagnosis of disease via tissue microscopy and it is currently the ‘gold-standard‘ in formally diagnosing many types of disease including cancers.<br/>Due to increasing workloads on pathologists, there is a growing need for automated image analysis pipelines that are able to filter out obviously benign samples. However, these algorithms are sensitive to factors of variation such as the staining and scanning conditions with which a tissue specimen is processed that differ significantly across institutions.<br/>In this thesis, novel machine learning algorithms are developed using state-of-the-art deep learning techniques that enable the creation of automated histopathology image<br/>analysis pipelines that are more robust to frequently occurring artifacts and variation in appearance.<br/><br/>A novel neural network architecture called the Dual-Channel Auto-Encoder (DCAE) is devised that learns representations of histopathology images that are invariant to the effects of differing digital slide scanners whilst holding enough discriminative power to delineate various anatomical structures within tissue. This method achieves a 50%<br/>improvement in SSIM score on tissue masks derived from the DCAE features compared to related methods. Next, a novel unsupervised approach to detect and remove artifacts using techniques from generative adversarial networks is presented. This approach allows artifacts to be removed prior to the application of stain separation which is demonstrated experimentally to improve the stain colour estimation performance. Finally, a more sophisticated model of stain separation called Tissue-Dependent Stain Separation (TDSS) is developed which incorporates contextual information such as texture and colour to make more informed estimates of stain colour conditioned on tissue<br/>sub-types and thus producing better separations of stains compared to state-of-the-art methods. The TDSS model achieves an 8.81% reduction in mean-squared error in a stain separation task compared to existing state-of-the-art-methods. These contributions represent a significant step forward towards robust, fully automated histopathology image analysis pipelines."]},{"key":"dc:title","label":"Title","values":["Deep learning for processing histopathology images"]}]}],"canonical_facts":{"dc:contributor.advisor":["Ji, Ming","Gault, Richard"],"dc:contributor.sponsor":["Invest Northern Ireland","Northern Ireland Department for the Economy"],"dc:creator":["Moyes, Andrew"],"dc:date":["2021-7"],"dc:date.issued":["2021-7"],"dc:description.abstract":["Histopathology is the study and diagnosis of disease via tissue microscopy and it is currently the ‘gold-standard‘ in formally diagnosing many types of disease including cancers.<br/>Due to increasing workloads on pathologists, there is a growing need for automated image analysis pipelines that are able to filter out obviously benign samples. However, these algorithms are sensitive to factors of variation such as the staining and scanning conditions with which a tissue specimen is processed that differ significantly across institutions.<br/>In this thesis, novel machine learning algorithms are developed using state-of-the-art deep learning techniques that enable the creation of automated histopathology image<br/>analysis pipelines that are more robust to frequently occurring artifacts and variation in appearance.<br/><br/>A novel neural network architecture called the Dual-Channel Auto-Encoder (DCAE) is devised that learns representations of histopathology images that are invariant to the effects of differing digital slide scanners whilst holding enough discriminative power to delineate various anatomical structures within tissue. This method achieves a 50%<br/>improvement in SSIM score on tissue masks derived from the DCAE features compared to related methods. Next, a novel unsupervised approach to detect and remove artifacts using techniques from generative adversarial networks is presented. This approach allows artifacts to be removed prior to the application of stain separation which is demonstrated experimentally to improve the stain colour estimation performance. Finally, a more sophisticated model of stain separation called Tissue-Dependent Stain Separation (TDSS) is developed which incorporates contextual information such as texture and colour to make more informed estimates of stain colour conditioned on tissue<br/>sub-types and thus producing better separations of stains compared to state-of-the-art methods. The TDSS model achieves an 8.81% reduction in mean-squared error in a stain separation task compared to existing state-of-the-art-methods. These contributions represent a significant step forward towards robust, fully automated histopathology image analysis pipelines."],"dc:identifier":["oai:pure.qub.ac.uk/portal:studenttheses/af5f2ab4-858c-4ace-88d0-008e0bee67cc","https://pure.qub.ac.uk/en/studentTheses/af5f2ab4-858c-4ace-88d0-008e0bee67cc"],"dc:identifier.uri":["https://pure.qub.ac.uk/files/238764526/thesis.pdf"],"dc:language":["eng"],"dc:publisher.department":["School of Electronics, Electrical Engineering and Computer Science"],"dc:publisher.institution":["Queen's University Belfast"],"dc:relation.isreferencedby":["https://pure.qub.ac.uk/en/studentTheses/af5f2ab4-858c-4ace-88d0-008e0bee67cc"],"dc:rights.embargodate":["2022-07-31"],"dc:rights.embargoreason":["/dk/atira/pure/core/document/studentthesisembargoreason/publicationissues"],"dc:subject":["Deep learning","computer vision","histopathology"],"dc:title":["Deep learning for processing histopathology images"],"dc:type":["Thesis"],"dc:type.qualificationlevel":["Doctoral Thesis"],"dc:type.qualificationname":["Doctor of Philosophy"]},"updated_at":"2026-07-24T03:55:58Z"}