Thanks to recent promising advances in AI, automated segmentation of imaging datasets has made significant progress. However, evaluating and preserving 3D and 3D+t datasets remains extremely challenging and resource-intensive. A study recently published in eLife introduces MorphoNet 2.0, a major conceptual and technical evolution designed to facilitate the segmentation, self-evaluation, and correction of 3D images. The application is accessible to non-programmer biologists thanks to user-friendly graphical interfaces and runs on all major operating systems. Its power is demonstrated by the improvement in accuracy and interpretability of five previously published segmented datasets. This approach is crucial for producing scientific-quality reference datasets, which are essential for training and benchmarking advanced AI-based segmentation tools.
Link to the eLife article : https://elifesciences.org/
Contact : Emmanuel FAURE
