6 papers
Pulse-Echo Ultrasound Methods for Speed-of-Sound Estimation: A Review
Can Deniz Bezek, Orcun Goksel
Speed of sound (SoS) is fundamental to ultrasound beamforming and a promising quantitative biomarker for tissue characterization. Although transmission- and reflector-based methods…
An Accessible Solution for Deformable Image Registration Compared with Learning-Based Approaches
Onur Ali Zeybekoglu, David Tilly, Orcun Goksel
Deformable image registration (DIR) is a core problem in medical image analysis; but, unlike labeling decision problems such as classification and segmentation, registration is a p…
Needle in a Haystack: One-Class Representation Learning for Detecting Rare Malignant Cells in Computational Cytology
Swarnadip Chatterjee, Vladimir Basic, Arrigo Capitanio +2
In computational cytology, detecting malignancy on whole-slide images is difficult because malignant cells are morphologically diverse yet vanishingly rare amid a vast background o…
DenOiS: Dual-Domain Denoising of Observation and Solution in Ultrasound Image Reconstruction
Can Deniz Bezek, Orcun Goksel
Medical imaging aims to recover underlying tissue properties, using inexact (simplified/linearized) imaging models and often from inaccurate and incomplete measurements. Analytical…
Lean Unet: A Compact Model for Image Segmentation
Ture Hassler, Ida à kerholm, Marcus Nordström +2
Unet and its variations have been standard in semantic image segmentation, especially for computer assisted radiology. Current Unet architectures iteratively downsample spatial res…
Joint semi-supervised and contrastive learning enables domain generalization and multi-domain segmentation
Alvaro Gomariz, Yusuke Kikuchi, Yun Yvonna Li +5
Despite their effectiveness, current deep learning models face challenges with images coming from different domains with varying appearance and content. We introduce SegCLR, a vers…