INSTITUTIONAL DIGITAL REPOSITORY

Domain specific, Semi-Supervised transfer learning for medical imaging

Show simple item record

dc.contributor.author Virk, J. S.
dc.contributor.author Bathula, D. R.
dc.date.accessioned 2021-07-04T09:42:37Z
dc.date.available 2021-07-04T09:42:37Z
dc.date.issued 2021-07-04
dc.identifier.uri http://localhost:8080/xmlui/handle/123456789/2000
dc.description.abstract Limited availability of annotated medical imaging data poses a challenge for deep learning algorithms. Although transfer learning minimizes this hurdle in general, knowledge transfer across disparate domains is shown to be less effective. On the other hand, smaller architectures were found to be more compelling in learning better features. Consequently, we propose a lightweight architecture that uses mixed asymmetric kernels (MAKNet) to reduce the number of parameters significantly. Additionally, we train the proposed architecture using semi-supervised learning to provide pseudo-labels for a large medical dataset to assist with transfer learning. The proposed MAKNet provides better classification performance with 60 − 70% less parameters than popular architectures. Experimental results also highlight the importance of domainspecific knowledge for effective transfer learning. en_US
dc.language.iso en_US en_US
dc.title Domain specific, Semi-Supervised transfer learning for medical imaging en_US
dc.type Article en_US


Files in this item

This item appears in the following Collection(s)

Show simple item record

Search DSpace


Advanced Search

Browse

My Account