Towards FAIR and high-quality AI-ready data for bioimage analysis
Deep learning (DL) has transformed biomedical and microscopy image analysis. However, the development, validation and benchmarking of DL algorithms rely heavily on high-quality annotated datasets that are often scarce and difficult to reuse. Furthermore, the complexity of such data presents significant challenges for accurate algorithm implementation. In the first part of this seminar, we will discuss how the BioImage Archive is working to increase the availability of annotated biological image datasets by making them FAIR (Findable, Accessible, Interoperable, and Reusable). The second part of the seminar will address the critical aspects of data quality and result validation in DL applications for biomedical imaging. The seminar will provide practical standards for sharing high-quality data while leveraging the power of deep learning in biomedical research.
Speakers: Teresa Zulueta-Coarasa, Estibaliz Gómez de Mariscal