Deep learning-based quantification of NAFLD/NASH progression in human liver biopsies

Accession: osf.8e7hd
Source / host: OSF — OSF
Disease relevance: MASLD / NAFLD / NASH (category: Imaging, subtype: whole-slide imaging)
Modality / assay: imaging
Platform: whole-slide imaging
Organism: human
Size (indexed): 17.4 GB (18634364765 bytes)
Downloaded bytes: 17.4 GB (18634364765 bytes)
Access / raw: public / OPEN-raw

Download

Files

FileSizeSHA256
ground_truth.csv14.6 KBa7cb1e12a9dcc2bb…
CNN/ballooning.zip.008446.0 MBa414afccaa38cf91…
CNN/steatosis.zip.0051000.0 MB88666651d7e7b01d…
CNN/result.zip96.0 MBffaa18358745f774…
CNN/steatosis.zip.0031000.0 MB5a1cc47e22e39b43…
CNN/ballooning.zip.0031000.0 MB7ea5ed7d08d483b6…
CNN/ballooning.zip.0071000.0 MBfe53dfa819400a58…
CNN/ballooning.zip.0021000.0 MB32746fbca20bd6b2…
CNN/inflammation.zip1.8 GB83b52739f2193334…
CNN/steatosis.zip.0021000.0 MBd27237f2efefcb3a…
CNN/ballooning.zip.0051000.0 MB4e94d639209596d5…
CNN/ballooning.zip.0041000.0 MB5998ef5cc5696133…
CNN/ballooning.zip.0061000.0 MB72f7c6e414ef4b35…
CNN/steatosis.zip.0011000.0 MBebf206457dd317a4…
CNN/ballooning.zip.0011000.0 MB082b3f6eac7dbd1d…
CNN/steatosis.zip.0061000.0 MB29f9756ae13346f9…
CNN/steatosis.zip.007667.7 MBb18c65fcbf1f938e…
CNN/fibrosis.zip1.1 GBb75ad62769c6443b…
CNN/steatosis.zip.0041000.0 MB77ed99a08056819e…
ANN.zip88.1 KBf38cf68a494a2a25…
model.zip601.4 MBb659b2b2e5ae6990…

Index note: human biopsy tiles + NAS scores + models

Crawled by masld-atlas-crawler v1.0 at 2026-08-03T09:56:43Z.

About this dataset

This whole-slide imaging dataset provides single-cell gene expression from human liver samples, with disease state recorded as MASLD/NAFLD/NASH.

Analyze it in Drylab

Open this dataset in Drylab and ask a question in plain language. The AI agent loads the files, runs the analysis in a ready sandbox and explains each result. A typical first pass:

  1. Load the filtered feature-barcode matrix (HDF5) and run quality control on counts, genes and mitochondrial reads per cell.
  2. Normalize, select variable genes, then cluster the cells and draw a UMAP.
  3. Annotate clusters with marker genes and compare the cell-type mix between conditions.
  4. Run differential expression between cell types or samples to characterize masld/nafld/nash biology.