AI Science Tracker
EN

Rapid 3D phenotypic analysis of neurons and organoids using data-driven cell segmentation-free machine learning

Sunnybrook Research Institute, University of Toronto · 22 Feb 2021 · biology

Discovery

Rapid 3D phenotypic analysis of neurons and organoids using data-driven cell segmentation-free machine learning

Source check: Source checked. Not independent scientific confirmation.

Finding: Phindr3D combines unsupervised k-means voxel features with hierarchical supervoxel and megavoxel descriptors for segmentation-free 3D image phenotyping. In 8,100 neuronal image stacks across 9 biological replicates, it separated treatment-associated morphologies, including distinct responses to anti-apoptotic inhibitors, and it characterized oncogene-associated morphogenesis in mammary acinar organoids. These assay-bound results do not establish clinical utility.

Technology: Phindr3D shallow-learning pipeline: unsupervised k-means voxel categories, hierarchical supervoxel/megavoxel features, affinity-propagation clustering, and random-forest classification

Publication: Peer-reviewed paper · Test context: direct test. Catalog categories, not an evidence grade.

AI contribution
Phindr3D derives hierarchical voxel-based image features without cell segmentation; unsupervised k-means builds pixel, supervoxel, and megavoxel categories, followed by affinity-propagation clustering or random-forest classification.
Test and result
The tool processed 8,100 three-channel neuronal image stacks from 9 biological replicates on 3 plates; affinity-propagation clustering yielded eight combined phenotype clusters and separated responses to anti-apoptotic inhibitors with similar profiles across replicates. In a reference 3D cell-line assay, concentration-response EC50 values were similar to conventional segmentation-based classification.
Limitation / still unknown
Evidence is limited to the reported microscopy assays and models; generalization to other imaging tasks and clinical utility were not established.
Evidence sources and annotation context

Evidence context (descriptions follow the cited sources; test type is a catalog classification):

Evidence sources: https://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1008630 · https://pmc.ncbi.nlm.nih.gov/articles/PMC7932518/

Source checked · editorial details

The source page was checked against this entry. Independent confirmation is not assessed by this label.

Source type: paper. Paper: not linked in this catalog; this does not mean no paper exists.

Review date: 22 Nov 2026. Review scope: Primary result-bearing material for the stated method, result and evaluation, with bibliographic version information..

No follow-up recorded; this is not a claim that no follow-up exists. Follow-up review scope and date are not recorded. No source-supported relationships recorded.

Editorial assessment: Impact 2/5 · Validation 3/5 · Novelty 2/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.

Open in the full catalog for filters, charts and related discoveries. Browse biology discoveries.