5 papers
Seamless Whole Slide Label-Free Virtual Staining
Dou Hoon Kwark, Kianoush Falahkheirkhah, Ji-hun Oh +3
Label-free virtual staining offers a compelling, non-destructive alternative to standard histopathology; however, its clinical adoption is hindered by the computational bottlenecks…
Anatomy of a failure: When, how, and why deep vision fails in scientific domains
Ji-Hun Oh, Dou Hoon Kwark, Kianoush Falahkheirkhah +4
Mirroring its ubiquity in popular media and all human activities, the use of deep learning (DL) is rapidly growing in scientific imaging modalities. However, unlike everyday RGB pi…
Exploring the Equivalence of Closed-Set Generative and Real Data Augmentation in Image Classification
Haowen Wang, Guowei Zhang, Xiang Zhang +4
In this paper, we address a key scientific problem in machine learning: Given a training set for an image classification task, can we train a generative model on this dataset to en…
Hierarchical Diffusion Framework for Pseudo-Healthy Brain MRI Inpainting with Enhanced 3D Consistency
Dou Hoon Kwark, Shirui Luo, Xiyue Zhu +3
Pseudo-healthy image inpainting is an essential preprocessing step for analyzing pathological brain MRI scans. Most current inpainting methods favor slice-wise 2D models for their…
Introducing 3D Representation for Medical Image Volume-to-Volume Translation via Score Fusion
Xiyue Zhu, Dou Hoon Kwark, Ruike Zhu +6
In volume-to-volume translations in medical images, existing models often struggle to capture the inherent volumetric distribution using 3D voxelspace representations, due to high…