Reducing Bias in Tuberculosis Screening with Deep Domain Adaptation
dc.contributor.advisor | Chapman, David | |
dc.contributor.author | Ravin, Nishanjan | |
dc.contributor.department | Computer Science and Electrical Engineering | |
dc.contributor.program | Computer Science | |
dc.date.accessioned | 2022-09-29T15:37:51Z | |
dc.date.available | 2022-09-29T15:37:51Z | |
dc.date.issued | 2021-01-01 | |
dc.description.abstract | We demonstrate that Domain Invariant Feature Learning (DIFL) can improve the out-of-domain generalizability of a deep Tuberculosis screening algorithm. It is well known that state of the art deep learning algorithms often have difficulty generalizing to unseen data distributions due to "domain shift". In the context of medical imaging, this could lead to unintended biases such as the inability to generalize from one patient population to another. We analyze the performance of a ResNet-50 classifier for the purposes of Tuberculosis screening using the four most popular public datasets with geographically diverse sources of imagery. We show that without domain adaptation, ResNet-50 has difficulty in generalizing between imaging distributions from a number of public Tuberculosis screening datasets with imagery from geographically distributed regions. However, with the incorporation of DIFL, the out-of-domain performance is greatly enhanced. Analysis criteria includes a comparison of accuracy, sensitivity, specificity and AUC over both the baseline, as well as the DIFL enhanced algorithms. We conclude that DIFL improves generalizability of Tuberculosis screening while maintaining acceptable accuracy over the source domain imagery when applied across a variety of public datasets. | |
dc.format | application:pdf | |
dc.genre | theses | |
dc.identifier | doi:10.13016/m2e2nl-nbvg | |
dc.identifier.other | 12431 | |
dc.identifier.uri | http://hdl.handle.net/11603/25973 | |
dc.language | en | |
dc.relation.isAvailableAt | The University of Maryland, Baltimore County (UMBC) | |
dc.relation.ispartof | UMBC Computer Science and Electrical Engineering Department Collection | |
dc.relation.ispartof | UMBC Theses and Dissertations Collection | |
dc.relation.ispartof | UMBC Graduate School Collection | |
dc.relation.ispartof | UMBC Student Collection | |
dc.rights | This item may be protected under Title 17 of the U.S. Copyright Law. It is made available by UMBC for non-commercial research and education. For permission to publish or reproduce, please see http://aok.lib.umbc.edu/specoll/repro.php or contact Special Collections at speccoll(at)umbc.edu | |
dc.source | Original File Name: Ravin_umbc_0434M_12431.pdf | |
dc.subject | Domain Invariant Feature Learning | |
dc.subject | Generative Adversarial Networks | |
dc.subject | TB Screening | |
dc.subject | Unsupervised Domain Adaptation | |
dc.title | Reducing Bias in Tuberculosis Screening with Deep Domain Adaptation | |
dc.type | Text | |
dcterms.accessRights | Distribution Rights granted to UMBC by the author. | |
dcterms.accessRights | Access limited to the UMBC community. Item may possibly be obtained via Interlibrary Loan thorugh a local library, pending author/copyright holder's permission. |