{"id":{"repo_id":"mit","oai_identifier":"oai:dspace.mit.edu:1721.1/158957"},"canonical_url":"https://search.dev.ndltd.org/etd/mit/oai:dspace.mit.edu:1721.1/158957","repository":{"repo_id":"mit","name":"MIT","base_url":"https://dspace.mit.edu/oai/request"},"display":{"title":"Data-Driven General Purpose Foundation Models for Computational Pathology","abstract":"The field of computational pathology has undergone a remarkable transformation in recent years. Researchers have leveraged supervised and weakly-supervised deep learning with varying degrees of success to address a wide range of tasks, including cancer subtyping and grading, metastasis detection, survival and treatment response prediction, tumor site-of-origin identification, mutation prediction, biomarker screening, and more. However, traditional task-specific models often require extensive labeled data and struggle to generalize across diverse pathology tasks. This limitation motivates the exploration of foundation models, which promise a more scalable, versatile solution by learning broad representations that can be adapted to various downstream applications. In this thesis, I will investigate the capabilities and limitations of data-driven foundation models in computational pathology. Specifically, I will explore two frameworks for developing general-purpose encoder models for pathology images: one using paired image-text data, and another leveraging self-supervised learning on large-scale unlabeled images. Additionally, I will examine downstream applications of these foundation models, including zero-shot transfer to gigapixel whole slide images and the development of an interactive multimodal AI assistant for pathologists.","abstract_html":"The field of computational pathology has undergone a remarkable transformation in recent years. Researchers have leveraged supervised and weakly-supervised deep learning with varying degrees of success to address a wide range of tasks, including cancer subtyping and grading, metastasis detection, survival and treatment response prediction, tumor site-of-origin identification, mutation prediction, biomarker screening, and more. However, traditional task-specific models often require extensive labeled data and struggle to generalize across diverse pathology tasks. This limitation motivates the exploration of foundation models, which promise a more scalable, versatile solution by learning broad representations that can be adapted to various downstream applications. In this thesis, I will investigate the capabilities and limitations of data-driven foundation models in computational pathology. Specifically, I will explore two frameworks for developing general-purpose encoder models for pathology images: one using paired image-text data, and another leveraging self-supervised learning on large-scale unlabeled images. Additionally, I will examine downstream applications of these foundation models, including zero-shot transfer to gigapixel whole slide images and the development of an interactive multimodal AI assistant for pathologists.","abstract_has_math":false,"creators":["Lu, Ming Yang (Max)"],"institution":"Massachusetts Institute of Technology","degree_name":"Doctoral","degree_level":null,"degree_discipline":null,"degree_department":"Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science","school":null,"contributors":[],"advisors":["Mahmood, Faisal"],"committee_chairs":[],"committee_members":[],"year":2025,"date_issued":"2025-02","date_published":"2025-02","updated_at":"2026-07-22T22:22:29Z","subjects":[],"languages":[],"rights":["In Copyright - Educational Use Permitted","Copyright retained by author(s)"],"rights_urls":["https://rightsstatements.org/page/InC-EDU/1.0/"],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/1721.1/158957","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Mahmood, Faisal"]},{"key":"dc:contributor.department","label":"Department","values":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science"]},{"key":"dc:creator","label":"Author","values":["Lu, Ming Yang (Max)"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2025-03-27T17:00:29Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2025-03-27T17:00:29Z"]},{"key":"dc:date.issued","label":"Date","values":["2025-02"]},{"key":"dc:publisher","label":"Institution","values":["Massachusetts Institute of Technology"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Doctoral","Doctor of Philosophy"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:rights","label":"Dc Rights","values":["In Copyright - Educational Use Permitted","Copyright retained by author(s)"]},{"key":"dc:rights.uri","label":"Rights URI","values":["https://rightsstatements.org/page/InC-EDU/1.0/"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/1721.1/158957"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["The field of computational pathology has undergone a remarkable transformation in recent years. Researchers have leveraged supervised and weakly-supervised deep learning with varying degrees of success to address a wide range of tasks, including cancer subtyping and grading, metastasis detection, survival and treatment response prediction, tumor site-of-origin identification, mutation prediction, biomarker screening, and more. However, traditional task-specific models often require extensive labeled data and struggle to generalize across diverse pathology tasks. This limitation motivates the exploration of foundation models, which promise a more scalable, versatile solution by learning broad representations that can be adapted to various downstream applications. In this thesis, I will investigate the capabilities and limitations of data-driven foundation models in computational pathology. Specifically, I will explore two frameworks for developing general-purpose encoder models for pathology images: one using paired image-text data, and another leveraging self-supervised learning on large-scale unlabeled images. Additionally, I will examine downstream applications of these foundation models, including zero-shot transfer to gigapixel whole slide images and the development of an interactive multimodal AI assistant for pathologists."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["Ph.D."]},{"key":"dc:title","label":"Title","values":["Data-Driven General Purpose Foundation Models for Computational Pathology"]}]}],"canonical_facts":{"dc:contributor.advisor":["Mahmood, Faisal"],"dc:contributor.department":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science"],"dc:creator":["Lu, Ming Yang (Max)"],"dc:date.accessioned":["2025-03-27T17:00:29Z"],"dc:date.available":["2025-03-27T17:00:29Z"],"dc:date.issued":["2025-02"],"dc:description.abstract":["The field of computational pathology has undergone a remarkable transformation in recent years. Researchers have leveraged supervised and weakly-supervised deep learning with varying degrees of success to address a wide range of tasks, including cancer subtyping and grading, metastasis detection, survival and treatment response prediction, tumor site-of-origin identification, mutation prediction, biomarker screening, and more. However, traditional task-specific models often require extensive labeled data and struggle to generalize across diverse pathology tasks. This limitation motivates the exploration of foundation models, which promise a more scalable, versatile solution by learning broad representations that can be adapted to various downstream applications. In this thesis, I will investigate the capabilities and limitations of data-driven foundation models in computational pathology. Specifically, I will explore two frameworks for developing general-purpose encoder models for pathology images: one using paired image-text data, and another leveraging self-supervised learning on large-scale unlabeled images. Additionally, I will examine downstream applications of these foundation models, including zero-shot transfer to gigapixel whole slide images and the development of an interactive multimodal AI assistant for pathologists."],"dc:description.degree":["Ph.D."],"dc:identifier.uri":["https://hdl.handle.net/1721.1/158957"],"dc:publisher":["Massachusetts Institute of Technology"],"dc:rights":["In Copyright - Educational Use Permitted","Copyright retained by author(s)"],"dc:rights.uri":["https://rightsstatements.org/page/InC-EDU/1.0/"],"dc:title":["Data-Driven General Purpose Foundation Models for Computational Pathology"],"dc:type":["Thesis"],"thesis:degree_name":["Doctoral","Doctor of Philosophy"]},"updated_at":"2026-07-22T22:22:29Z"}