Arrate Muñoz-Barrutia

Abstract Image-based machine learning tools are powerful resources for analyzing medical images, with deep learning-based semantic segmentation commonly utilized to enable the spatial quantification of structures visible in images. However, dataset generation and training of segmentation algorithms requires advanced programming skills and intricate workflows, limiting their accessibility to scientists without prior coding expertise.

Abstract Artificial intelligence (AI) methods are powerful tools for biological image analysis and processing. High-quality annotated images are key to training and developing new algorithms, but access to such data is often hindered by the lack of standards for sharing datasets. We discuss the barriers to sharing annotated image datasets and suggest specific guidelines to improve the reuse of bioimages and annotations for AI applications.

Bioimage analysis is a cornerstone of modern life sciences, powering discoveries and insights derived from biological image data. Deep learning has become an invaluable tool for analyzing microscopy datasets, and its application is increasingly widespread in biomedical research1. However, its prerequisite for high-level programming skills has often acted as a barrier, limiting accessibility for researchers without a specific computational background2.