Interpretable deep concepts of organoid morphology

Image-based classification of organoid morphologies can indicate drug response, viability, or successful differentiation. In recent work, learned representations outperform handcrafted features as the basis for downstream classifiers. However, their black-box nature hides the morphological cues a classifier relies on. Based on the foundation models DINOv3 (general-purpose) and ViTAMIn-O (organoid-specific), we train sparse autoencoders (SAEs) to learn interpretable concepts related to distinct organoid morphologies. We annotate concepts with spatial labels (organoid, organoid wall, background) and compute their dataset specificity and task relevance across five tasks. The spatial labels of DINOv3 concepts yield coarse organoid segmentations on out-of-domain datasets. Filtering concepts by spatial label in the DINOv3-SAE improves downstream AUROC for three of the five tasks. Qualitative analysis of the most relevant concepts further reveals a confounding factor introduced by our preprocessing in one task. Through such insights, interpretable concepts could help improve the reliability of classifiers and guide the future development of organoid representation models. The trained SAEs will be made available upon publication.

Authors

Publication Details

Journal
arXiv (Cornell University)
Published
2026-11-16
DOI
https://doi.org/10.48550/arxiv.2611.20840
Primary Topic
Explainable Artificial Intelligence (XAI)
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

Interpretable deep concepts of organoid morphology

Tingying Peng, Lion Jasper Gleiter
arXiv (Cornell University)
Explainable Artificial Intelligence (XAI)
preprint

Interpretable deep concepts of organoid morphology

Tingying Peng, Lion Jasper Gleiter
preprint en

Abstract

Image-based classification of organoid morphologies can indicate drug response, viability, or successful differentiation. In recent work, learned representations outperform handcrafted features as the basis for downstream classifiers. However, their black-box nature hides the morphological cues a classifier relies on. Based on the foundation models DINOv3 (general-purpose) and ViTAMIn-O (organoid-specific), we train sparse autoencoders (SAEs) to learn interpretable concepts related to distinct organoid morphologies. We annotate concepts with spatial labels (organoid, organoid wall, background) and compute their dataset specificity and task relevance across five tasks. The spatial labels of DINOv3 concepts yield coarse organoid segmentations on out-of-domain datasets. Filtering concepts by spatial label in the DINOv3-SAE improves downstream AUROC for three of the five tasks. Qualitative analysis of the most relevant concepts further reveals a confounding factor introduced by our preprocessing in one task. Through such insights, interpretable concepts could help improve the reliability of classifiers and guide the future development of organoid representation models. The trained SAEs will be made available upon publication.

arXiv (Cornell University)
Explainable Artificial Intelligence (XAI)
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon