{"id":{"repo_id":"utswmed","oai_identifier":"oai:utswmed-ir.tdl.org:2152.5/10444"},"canonical_url":"https://search.dev.ndltd.org/etd/utswmed/oai:utswmed-ir.tdl.org:2152.5/10444","repository":{"repo_id":"utswmed","name":"University of Texas Southwestern Medical Center","base_url":"https://utswmed-ir.tdl.org/server/oai/request"},"display":{"title":"Deep Learning-Based Comprehensive Pathology Image Analysis","abstract":"The advances in deep learning during the past decade have provided great tools for the analysis of histopathology images. Deep learning algorithms can aid in the routine diagnostics and have the potential to extract hidden information directly from slide images, providing valuable information for healthcare professionals. This dissertation applied deep learning on the diseases of rhabdomyosarcoma and oral potentially malignant disorders. Convolutional neural network models were developed, one of which was to predict the risk of oral cancer development from slide images in patient with oral leukoplakia (a type of oral potentially malignant disorders), another to classify rhabdomyosarcoma histology subtypes and predict survival outcomes of embryonal rhabdomyosarcoma patients. Furthermore, U-Net and Mask R-CNN based HD-Staining models were used to identify cell nuclei of different tissue layers in oral epithelium, and novel Onion Peeling algorithm was developed to count the cell layer numbers. Overall, the deep learning tools in this dissertation serve as aids to pathology evaluation process and can provide valuable information for risk stratification of patients.","abstract_html":"The advances in deep learning during the past decade have provided great tools for the analysis of histopathology images. Deep learning algorithms can aid in the routine diagnostics and have the potential to extract hidden information directly from slide images, providing valuable information for healthcare professionals. This dissertation applied deep learning on the diseases of rhabdomyosarcoma and oral potentially malignant disorders. Convolutional neural network models were developed, one of which was to predict the risk of oral cancer development from slide images in patient with oral leukoplakia (a type of oral potentially malignant disorders), another to classify rhabdomyosarcoma histology subtypes and predict survival outcomes of embryonal rhabdomyosarcoma patients. Furthermore, U-Net and Mask R-CNN based HD-Staining models were used to identify cell nuclei of different tissue layers in oral epithelium, and novel Onion Peeling algorithm was developed to count the cell layer numbers. Overall, the deep learning tools in this dissertation serve as aids to pathology evaluation process and can provide valuable information for risk stratification of patients.","abstract_has_math":false,"creators":["Zhang, Xinyi"],"institution":null,"degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":["Wang, Tao","Xiao, Guanghua","Xie, Yang","Bishop, Justin","Jia, Xun","Zhan, Xiaowei"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2025,"date_issued":"2025-01-02T21:57:45Z","date_published":"2025-01-02T21:57:45Z","updated_at":"2026-07-24T05:52:17Z","subjects":["Deep Learning","Image Processing, Computer-Assisted","Neural Networks, Computer","Pathology, Clinical"],"languages":["en"],"rights":[],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier","label":"Identifier","values":["1482732373"],"render_values":[{"text":"1482732373","href":null,"code":true}]}]},"links":{"outbound_url":"https://hdl.handle.net/2152.5/10444","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Wang, Tao","Xiao, Guanghua","Xie, Yang","Bishop, Justin","Jia, Xun","Zhan, Xiaowei"]},{"key":"dc:creator","label":"Author","values":["Zhang, Xinyi"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2025-01-02T21:57:45Z","2022-12","December 2022"]},{"key":"dc:type","label":"Dc Type","values":["Thesis","text"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Deep Learning","Image Processing, Computer-Assisted","Neural Networks, Computer","Pathology, Clinical"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://hdl.handle.net/2152.5/10444","1482732373"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["The advances in deep learning during the past decade have provided great tools for the analysis of histopathology images. Deep learning algorithms can aid in the routine diagnostics and have the potential to extract hidden information directly from slide images, providing valuable information for healthcare professionals. This dissertation applied deep learning on the diseases of rhabdomyosarcoma and oral potentially malignant disorders. Convolutional neural network models were developed, one of which was to predict the risk of oral cancer development from slide images in patient with oral leukoplakia (a type of oral potentially malignant disorders), another to classify rhabdomyosarcoma histology subtypes and predict survival outcomes of embryonal rhabdomyosarcoma patients. Furthermore, U-Net and Mask R-CNN based HD-Staining models were used to identify cell nuclei of different tissue layers in oral epithelium, and novel Onion Peeling algorithm was developed to count the cell layer numbers. Overall, the deep learning tools in this dissertation serve as aids to pathology evaluation process and can provide valuable information for risk stratification of patients."]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Deep Learning-Based Comprehensive Pathology Image Analysis"]}]}],"canonical_facts":{"dc:contributor":["Wang, Tao","Xiao, Guanghua","Xie, Yang","Bishop, Justin","Jia, Xun","Zhan, Xiaowei"],"dc:creator":["Zhang, Xinyi"],"dc:date":["2025-01-02T21:57:45Z","2022-12","December 2022"],"dc:description":["The advances in deep learning during the past decade have provided great tools for the analysis of histopathology images. Deep learning algorithms can aid in the routine diagnostics and have the potential to extract hidden information directly from slide images, providing valuable information for healthcare professionals. This dissertation applied deep learning on the diseases of rhabdomyosarcoma and oral potentially malignant disorders. Convolutional neural network models were developed, one of which was to predict the risk of oral cancer development from slide images in patient with oral leukoplakia (a type of oral potentially malignant disorders), another to classify rhabdomyosarcoma histology subtypes and predict survival outcomes of embryonal rhabdomyosarcoma patients. Furthermore, U-Net and Mask R-CNN based HD-Staining models were used to identify cell nuclei of different tissue layers in oral epithelium, and novel Onion Peeling algorithm was developed to count the cell layer numbers. Overall, the deep learning tools in this dissertation serve as aids to pathology evaluation process and can provide valuable information for risk stratification of patients."],"dc:format":["application/pdf"],"dc:identifier":["https://hdl.handle.net/2152.5/10444","1482732373"],"dc:language":["en"],"dc:subject":["Deep Learning","Image Processing, Computer-Assisted","Neural Networks, Computer","Pathology, Clinical"],"dc:title":["Deep Learning-Based Comprehensive Pathology Image Analysis"],"dc:type":["Thesis","text"]},"updated_at":"2026-07-24T05:52:17Z"}