Show simple item record

dc.contributor.advisorJayashree Kalpathy-Cramer and Bruce R. Rosen.en_US
dc.contributor.authorChang, Ken,Ph. D.Massachusetts Institute of Technology.en_US
dc.contributor.otherHarvard--MIT Program in Health Sciences and Technology.en_US
dc.date.accessioned2020-09-15T22:01:25Z
dc.date.available2020-09-15T22:01:25Z
dc.date.copyright2020en_US
dc.date.issued2020en_US
dc.identifier.urihttps://hdl.handle.net/1721.1/127506
dc.descriptionThesis: Ph. D. in Medical Engineering and Medical Physics, Harvard-MIT Program in Health Sciences and Technology, May, 2020en_US
dc.descriptionCataloged from the official PDF of thesis.en_US
dc.descriptionIncludes bibliographical references (pages 212-232).en_US
dc.description.abstractThe last few years mark a significant leap in the capability of algorithms with the advent of deep learning. While conventional machine learning has existed for decades, their utility has been rather limited, requiring considerable engineering and domain expertise to design pertinent data features that can be extracted from raw data. In contrast, deep learning methods have yielded state-of-the-art results in a wide range of computer vision tasks without the need for hand-crafted imaging features. At the same time, we are collecting ever-increasing quantities of medical imaging. Together, deep learning models and big data yield a powerful combination. Integrated in the data workflow, the clinic, or at the bedside, these models have the potential to aid with clinical decision-making, improving efficiency, accuracy, and reliability of patient care.en_US
dc.description.abstractHowever, at present, there is a critical gap between the researchers who develop deep learning algorithms and the clinicians who could utilize the technology to improve patient care. In this thesis, I focus on several challenges that prevent clinical translation of algorithms. First, vast quantities of data needed to train effective models are often dispersed across institutions and cannot be shared due to ethical, infrastructure, and patient privacy concerns. As such, we developed distributed methods of training robust deep learning models that do not require sharing patient data in multi-institutional collaborative settings. Second, it is not clearly understood how decisions in algorithm design can affect model performance. To this end, I showcase how various training, data, and model parameters can impact algorithm prediction and performance.en_US
dc.description.abstractLastly, while many algorithms are designed to perform a single task, there are few pipelines that have multi-faceted functionality needed in patient care. I demonstrate an integrated and deployable clinical decision support pipeline for glioma and ischemic stroke that is extensible to other diseases.en_US
dc.description.statementofresponsibilityby Ken Chang.en_US
dc.format.extent232 pagesen_US
dc.language.isoengen_US
dc.publisherMassachusetts Institute of Technologyen_US
dc.rightsMIT theses may be protected by copyright. Please reuse MIT thesis content according to the MIT Libraries Permissions Policy, which is available through the URL provided.en_US
dc.rights.urihttp://dspace.mit.edu/handle/1721.1/7582en_US
dc.subjectHarvard--MIT Program in Health Sciences and Technology.en_US
dc.titleEnhancing medical imaging workflows with deep learningen_US
dc.typeThesisen_US
dc.description.degreePh. D. in Medical Engineering and Medical Physicsen_US
dc.contributor.departmentHarvard--MIT Program in Health Sciences and Technologyen_US
dc.identifier.oclc1193027449en_US
dc.description.collectionPh.D.inMedicalEngineeringandMedicalPhysics Harvard-MIT Program in Health Sciences and Technologyen_US
dspace.imported2020-09-15T22:01:24Zen_US
mit.thesis.degreeDoctoralen_US
mit.thesis.departmentHSTen_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record