HEST-Benchmark LUNG: Gene expression prediction from histology, Lung
Gene expression prediction from histology, Lung. Scored with Pearson correlation on HEST-Benchmark LUNG. Random Forest regression with 70 trees over frozen patch features, averaged over folds or patients.
Overview
Gene expression prediction from histology, Lung. Scored with Pearson correlation on HEST-Benchmark LUNG. Random Forest regression with 70 trees over frozen patch features, averaged over folds or patients.
Consult the linked sources for architecture or protocol details. Missing evidence is not evidence of a missing capability.
Results
Each comparison retains its reviewed evaluation scope, dataset and metric. Results are shown without a pooled ranking.
HEST-Benchmark LUNG: Gene expression prediction from histology, Lung
pearson_r (correlation) · Higher values are better.
HEST-Benchmark LUNG: Gene expression prediction from histology, Lung · HEST-Benchmark LUNG (HEST-Benchmark split)
Evidence origin: Author-reported evaluation.
HEST-1k: A Dataset for Spatial Transcriptomics and Histology Image Analysis · Table 1, row(LUNG)- Every figure comes from the same Random Forest head over frozen features, so it measures the encoder, not a full prediction pipeline.
- Cohorts differ in size and difficulty, so a figure in one cohort is not comparable to a figure in another.
Comparison details and limitations
Every method HEST-Benchmark reports on Gene expression prediction from histology, Lung, scored with Pearson correlation on HEST-Benchmark LUNG.
- Author-reported numbers, source checked but not independently reproduced.
Automated source review: 2026-09-18. Numerical source review does not establish independent reproduction.
Dots show point estimates. Whiskers show only explicitly defined uncertainty (standard deviation, standard error or a labelled interval); their definitions remain in Table. Unresolved uncertainty is not plotted. Differences do not establish statistical significance.
Showing 10 of 10 matching rows.
Methods and evaluation design
Procedure, tasks and evaluated configurations
Evaluation design
Benchmarks bring together tasks and protocols. A task describes the biological question; a protocol defines a particular test.
Benchmarks
These source-backed links do not make different protocols or scores interchangeable.
Recorded evaluations
Each evaluation records what was tested and under which conditions.
- SimCLR histology encoder + random forest (HEST; Ciga et al.) on HEST-Benchmark LUNG: Gene expression prediction from histology, Lung
- CONCH on HEST-Benchmark LUNG: Gene expression prediction from histology, Lung
- CTransPath on HEST-Benchmark LUNG: Gene expression prediction from histology, Lung
- GigaPath on HEST-Benchmark LUNG: Gene expression prediction from histology, Lung
- KimiaNet on HEST-Benchmark LUNG: Gene expression prediction from histology, Lung
- Phikon on HEST-Benchmark LUNG: Gene expression prediction from histology, Lung
- PLIP on HEST-Benchmark LUNG: Gene expression prediction from histology, Lung
- Remedis on HEST-Benchmark LUNG: Gene expression prediction from histology, Lung
- ResNet50 on HEST-Benchmark LUNG: Gene expression prediction from histology, Lung
- UNI on HEST-Benchmark LUNG: Gene expression prediction from histology, Lung
Run instructions
No runnable recipe has been reviewed for this task. Dataset access, model requirements, licences and compute requirements must be checked against its sources before execution.
A task describes a biological question. Choose a linked protocol to obtain concrete split and scoring instructions.
Strengths, limitations and unresolved questions
Evidence
Source checking verifies the cited claim or transcription. It does not establish independent reproduction.
Evidence table
Inspect claims, sources and review details
Trace each statement to its source and review. A context-only reference supports the record generally; it does not verify an individual field. Source checking does not reproduce an experiment.
One row per statement and cited source. Multiple citations are not independent evaluations. Shared locators are labelled explicitly.
1 evidence row matching the loaded filters
| Property and statement | Original source and location | Review and provenance |
|---|---|---|
| Relationship: part of discovery-benchmark-hest-benchmark Individual claims | HEST-1k: A Dataset for Spatial Transcriptomics and Histology Image Analysis Table 1, row(LUNG) Version: Version pinned by URL and artifact SHA256 when available | source checked automated source review · 2026-09-18 Audit detailsPrimary-source transcription with no human sign-off and no independent reproduction. Field: Claim: hest-association-lung Source artifact SHA-256: Hash scope: Exact retrieved primary paper artifact bytes. |
Sources and history
View linked audit checks and correction history
Release 2026-09-29-06401fd5b220 · Record review: source checked
1 source records and release history
- HEST-1k: A Dataset for Spatial Transcriptomics and Histology Image Analysis · Original source · Version pinned by URL and artifact SHA256 when available
Technical metadata and extraction receipts
Stable ID: hest-task-lung
- areas
- cells-tissues
- tasks
- Gene expression prediction from histology, Lung
- metric
- Pearson correlation
- metric direction
- higher
- dataset
- HEST-Benchmark LUNG
- protocol
- Random Forest regression with 70 trees over frozen patch features, averaged over folds or patients.
- source locator
- Table 1, row(LUNG)
- comparison panels
- id: hest-panel-lung; title: HEST-Benchmark LUNG: Gene expression prediction from histology, Lung; protocol id: hest-task-lung; dataset id: hest-dataset-hest-benchmark-lung; metric: pearson_r; unit: correlation; direction: higher; result ids: hest-result-resnet50-lung-pearson-r; hest-result-kimianet-lung-pearson-r; hest-result-ciga-lung-pearson-r; hest-result-ctranspath-lung-pearson-r; hest-result-remedis-lung-pearson-r; hest-result-phikon-lung-pearson-r; hest-result-plip-lung-pearson-r; hest-result-uni-lung-pearson-r; hest-result-conch-lung-pearson-r; hest-result-gigapath-lung-pearson-r; source ids: evidence-expansion-p2-hest-cached-636099a73dee; source locator: Table 1, row(LUNG); context: Every method HEST-Benchmark reports on Gene expression prediction from histology, Lung, scored with Pearson correlation on HEST-Benchmark LUNG.; caveats: Author-reported numbers, source checked but not independently reproduced.; Every figure comes from the same Random Forest head over frozen features, so it measures the encoder, not a full prediction pipeline.; Cohorts differ in size and difficulty, so a figure in one cohort is not comparable to a figure in another.; review: method: automated_source_review; date: 2026-09-18
Related records
- part of: HEST-Benchmark
- subject: HEST-Benchmark LUNG: part of discovery-benchmark-hest-benchmark
- benchmark: SimCLR histology encoder + random forest (HEST; Ciga et al.) on HEST-Benchmark LUNG: Gene expression prediction from histology, Lung
- benchmark: CONCH on HEST-Benchmark LUNG: Gene expression prediction from histology, Lung
- benchmark: CTransPath on HEST-Benchmark LUNG: Gene expression prediction from histology, Lung
- benchmark: GigaPath on HEST-Benchmark LUNG: Gene expression prediction from histology, Lung
- benchmark: KimiaNet on HEST-Benchmark LUNG: Gene expression prediction from histology, Lung
- benchmark: Phikon on HEST-Benchmark LUNG: Gene expression prediction from histology, Lung
- benchmark: PLIP on HEST-Benchmark LUNG: Gene expression prediction from histology, Lung
- benchmark: Remedis on HEST-Benchmark LUNG: Gene expression prediction from histology, Lung
- benchmark: ResNet50 on HEST-Benchmark LUNG: Gene expression prediction from histology, Lung
- benchmark: UNI on HEST-Benchmark LUNG: Gene expression prediction from histology, Lung