RESUMEN
On 8 December 2022 the organizing committee of the European Network for Breast Development and Cancer labs (ENBDC) held its fifth annual Think Tank meeting in Amsterdam, the Netherlands. Here, we embraced the opportunity to look back to identify the most prominent breakthroughs of the past ten years and to reflect on the main challenges that lie ahead for our field in the years to come. The outcomes of these discussions are presented in this position paper, in the hope that it will serve as a summary of the current state of affairs in mammary gland biology and breast cancer research for early career researchers and other newcomers in the field, and as inspiration for scientists and clinicians to move the field forward.
Asunto(s)
Neoplasias de la Mama , Glándulas Mamarias Humanas , Humanos , Femenino , Mama , BiologíaRESUMEN
We present an automated and deep-learning-based workflow to quantitatively analyze the spatiotemporal development of mammary epithelial organoids in two-dimensional 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.