Segmentation and Tracking of Mammary Epithelial Organoids in Brightfield Microscopy

Logo poskytovatele

Varování

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

HRADECKÁ Lucia WIESNER David SUMBAL Jakub SUMBALOVÁ KOLEDOVÁ Zuzana MAŠKA Martin

Rok publikování 2023
Druh Článek v odborném periodiku
Časopis / Zdroj IEEE Transactions on Medical Imaging
Fakulta / Pracoviště MU

Fakulta informatiky

Citace
www https://doi.org/10.1109/TMI.2022.3210714
Doi http://dx.doi.org/10.1109/TMI.2022.3210714
Klíčová slova organoid segmentation; organoid tracking; brightfield microscopy; deep learning; image synthesis
Popis We present an automated and deep-learningbased workflow to quantitatively analyze the spatiotemporal development of mammary epithelial organoids in twodimensional time-lapse (2D+t) sequences acquired using a brightfield microscope at high resolution. It involves a convolutional neural network (U-Net), purposely trained using computer-generated bioimage data created by a conditional generative adversarial network (pix2pixHD), to infer semantic segmentation, adaptive morphological filtering to identify organoid instances, and a shape-similarity-constrained, instance-segmentation-correcting tracking procedure to reliably cherry-pick the organoid instances of interest in time. By validating it using real 2D+t sequences of mouse mammary epithelial organoids of morphologically different phenotypes, we clearly demonstrate that the workflow achieves reliable segmentation and tracking performance, providing a reproducible and laborless alternative to manual analyses of the acquired bioimage data.
Související projekty:

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