Comprehensive Attention Networks for Cell Segmentation Using Numerical Integration

Logo poskytovatele

Varování

Publikace nespadá pod Filozofickou fakultu, ale pod Fakultu informatiky. Oficiální stránka publikace je na webu muni.cz.
Autoři

EFTIMIU Nikomidisz Jorgosz KOZUBEK Michal

Rok publikování 2026
Druh Článek ve sborníku
Konference 2026 IEEE International Symposium on Biomedical Imaging (ISBI)
Fakulta / Pracoviště MU

Fakulta informatiky

Citace
Klíčová slova Image processing; Biomedical image analysis
Přiložené soubory
Popis The emergence of neural networks has greatly improved segmentation accuracy in the domain of biomedical imaging, but the majority of existing solutions all employ the same general methodology. Attempting to generate entire masks at once naturally makes it difficult for a network to perform consistently well in every boundary region, especially when the objects to be segmented are complex. We describe a novel approach which combines attention-based neural networks with numerical integration methods to segment detected objects in a piecewise manner by tracing boundary pixels. This algorithm allows datasets with only a small number of annotated instances to be used for training and for behaviour analysis at the inference stage. We demonstrate our results on two datasets of the Cell Tracking Challenge, including simulated and real recordings of cells. The source code is available at https://gitlab.fi.muni.cz/xeftimiu/limit-cycle-seg.
Související projekty:

Používáte starou verzi internetového prohlížeče. Doporučujeme aktualizovat Váš prohlížeč na nejnovější verzi.