Biomedical Image Segmentation
Biomedical image segmentation aims to automatically delineate specific structures or regions of interest within medical images, facilitating accurate diagnosis and treatment planning. Current research emphasizes improving segmentation accuracy and robustness across diverse image modalities and datasets, focusing on architectures like U-Net and its variants, transformers, and novel hybrid models incorporating long-range dependency mechanisms and uncertainty quantification. These advancements are crucial for improving the efficiency and reliability of medical image analysis, impacting various clinical applications from cancer detection to cardiovascular disease management.
Papers
MorphoSeg: An Uncertainty-Aware Deep Learning Method for Biomedical Segmentation of Complex Cellular Morphologies
Tianhao Zhang, Heather J. McCourty, Berardo M. Sanchez-Tafolla, Anton Nikolaev, Lyudmila S. Mihaylova
Going Beyond U-Net: Assessing Vision Transformers for Semantic Segmentation in Microscopy Image Analysis
Illia Tsiporenko, Pavel Chizhov, Dmytro Fishman