Search Results for author:
Found 6 papers, 2 papers with code
Self-supervised Physics-based Denoising for Computed Tomography
Computed Tomography (CT) imposes risk on the patients due to its inherent X-ray radiation, stimulating the development of low-dose CT (LDCT) imaging methods.
Medical image segmentation with imperfect 3D bounding boxes
While current weakly-supervised approaches that use 2D bounding boxes as weak labels can be applied to medical image segmentation, we show that their success is limited in cases when the assumption about the tightness of the bounding boxes breaks.
Anatomy of Domain Shift Impact on U-Net Layers in MRI Segmentation
Domain Adaptation (DA) methods are widely used in medical image segmentation tasks to tackle the problem of differently distributed train (source) and test (target) data.
Uncertainty-based method for improving poorly labeled segmentation datasets
The success of modern deep learning algorithms for image segmentation heavily depends on the availability of large datasets with clean pixel-level annotations (masks), where the objects of interest are accurately delineated.
No-reference denoising of low-dose CT projections
Low-dose computed tomography (LDCT) became a clear trend in radiology with an aspiration to refrain from delivering excessive X-ray radiation to the patients.
First U-Net Layers Contain More Domain Specific Information Than The Last Ones
Our results demonstrate that 1) domain-shift may deteriorate the quality even for a simple brain extraction segmentation task (surface Dice Score drops from 0. 85-0. 89 even to 0. 09); 2) fine-tuning of the first layers significantly outperforms fine-tuning of the last layers in almost all supervised domain adaptation setups.
