no code implementations • 29 Apr 2024 • Halid Ziya Yerebakan, Yoshihisa Shinagawa, Gerardo Hermosillo Valadez
Organ segmentation is a fundamental task in medical imaging, and it is useful for many clinical automation pipelines.
no code implementations • 11 Aug 2023 • Halid Ziya Yerebakan, Yoshihisa Shinagawa, Mahesh Ranganath, Simon Allen-Raffl, Gerardo Hermosillo Valadez
We propose a method to match anatomical locations between pairs of medical images in longitudinal comparisons.
no code implementations • 25 Jan 2023 • Halid Ziya Yerebakan, Gerardo Hermosillo Valadez
We propose a visualization technique that utilizes neural network embeddings and a generative network to reconstruct original data.
no code implementations • 23 Jun 2020 • Halid Ziya Yerebakan, Parmeet Bhatia, Yoshihisa Shinagawa
We have shown that the method creates interpretable projections of original embedding dimensions.
no code implementations • COLING 2018 • Halid Ziya Yerebakan, Yoshihisa Shinagawa, Parmeet Bhatia, Yiqiang Zhan
To facilitate this, we have used a representation learning algorithm that creates a semantic representation space for documents where the clinically related documents lie close to each other.
no code implementations • 20 Jan 2016 • Halid Ziya Yerebakan, Fitsum Reda, Yiqiang Zhan, Yoshihisa Shinagawa
This paper presents a new Bayesian non-parametric model by extending the usage of Hierarchical Dirichlet Allocation to extract tree structured word clusters from text data.