ISCO: Intelligent Framework for Accurate Segmentation and Comparative Analysis of Organoids
ZHOU, J.; Fu, Z.; Ni, X.; Luo, Q.; Yang, G.
Show abstract
Organoids are self-organizing 3D cell clusters that closely mimic the structure and function of in vivo tissues and organs. Quantifying organoid morphology is critical for advancing our understanding of organ development, drug discovery, and toxicity assessment. Recent advances in microscopy have provided powerful tools to capture detailed morphological features of organoids, yet manual image analysis remains labor-intensive and time-consuming. In response, we present a comprehensive microscopy-based analysis pipeline that utilizes SegmentAnything 2.1 to accurately segment individual organoids. Additionally, we introduce a suite of morphological features--including perimeter, area, radius, non-smoothness, and non-circularity--that enable researchers to quantitatively and automatically analyze organoid structures. To further standardize organoid analysis across the field, Intelligent segmentation and comparison of organoids(ISCO), an intelligent AI-driven open-source algorithm, is developed with the aim of establishing a comprehensive toolset for organoid characterization.
Matching journals
The top 10 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- A deep learning workflow for quantification of Micronuclei in DNA damage studies in cultured cancer cell lines: a proof of principle investigation 94%
- Tumor spheroid elasticity estimation using mechano-microscopy combined with a conditional generative adversarial network 91%
- Intra-clustering analysis reveals tissue-specific mutational patterns 90%
Similar papers in this journal
- ConfluentFUCCI for fully-automated analysis of cell-cycle progression in a highly dense collective of migrating cells 95%
- Caveolae and scaffold detection from single molecule localization microscopy data using deep learning 94%
- The Image Data Explorer: interactive exploration of image-derived data 94%
Similar papers in this journal
Similar papers in this journal
Similar papers in this journal
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.