m3DinAI MDC demo dataset (BT549; 3D spheroids; dose–response plate; DMSO/MMS + drugs)
Abstract
This archive provides a lightweight demo dataset for the m3DinAI MDC (Morphological Disruption Concentration) workflow on BT-549 3D spheroids. To keep the download size manageable for reviewers, the dataset contains one maximum-intensity projection (MIP) per well (384 images) instead of the full z-stacks. The archive already includes the precomputed projections expected by the pipeline: 1. projections/ with {rXXcXXfYY}_MIP.tiff It also includes plate_map.csv (compound/dose/control annotations and intra-plate replicate IDs) in the same folder level as Images/. After extraction, run:python scripts/0_mdc_pipeline.py --z-stack-dir /BT549_MDC/Images --skip-if-exists The pipeline will skip MIP generation/8-bit conversion steps and proceed with segmentation, feature extraction (including radiomics), UMAP + k-means (k=2), a plate heatmap annotated with doses, and an MDC_table reporting the minimum dose at which all three intra-plate replicates are classified as “affected”.
Fields of Study & Subjects
Cell Image Analysis Techniques
Radiomics and Machine Learning in Medical Imaging
Computational Drug Discovery Methods
Publication details
- Journal / source
- Zenodo (CERN European Organization for Nuclear Research)
- Publication date
- 5 March 2026
- Language
- EN
- Document type
- Dataset