ffr
Datasets
All datasets matching “ffr”AMAZON_FFR_TVTffr-anatomy-prediction-discordance-detection-v0.1Goal
Detect discordancebetween coronary anatomy complexityand AI-derived FFR accuracyagainst invasive FFR ground truth.
This targets silent degradationin specific patient subgroups.
Inputs
vessel_tortuosity
calcification_burden
lesion_length_mm
segmentation_confidence
image_artifact_score
ai_ffr_prediction
ai_ffr_run_variance
model_disagreement
invasive_ffr_ground_truth
Required outputs
discordance_flag
discordance_type
subgroup_risk_label
reliability_drop_score
Discordance types
Examples:… See the full description on the dataset page: https://huggingface.co/datasets/ClarusC64/ffr-anatomy-prediction-discordance-detection-v0.1.ffr-subgroup-failure-surface-routing-v0.1Goal
Given a discordance eventroute the correct clinical action.
This dataset treats failureas a subgroup surface.
Not a single bad prediction.
Inputs
anatomy complexity metrics
image artifact signals
AI prediction stability signals
invasive FFR ground truth (for labeling)
Required outputs
failure_subgroup
predicted_error_range
intervention_route
fallback_protocol
confidence_score
Intervention routes
Examples:
continue (safe zone)
tighten QA thresholds
segmentation repair then rerun… See the full description on the dataset page: https://huggingface.co/datasets/ClarusC64/ffr-subgroup-failure-surface-routing-v0.1.FFR
[!NOTE]
Dataset origin: https://github.com/bonaventuredossou/ffr-v1
Description
The authors of the dataset provide a description in the following PDFs: here and here.
Citation
@inproceedings{emezue-dossou-2020-ffr,
title = "{FFR} v1.1: {F}on-{F}rench Neural Machine Translation",
author = "Emezue, Chris Chinenye and
Dossou, Femi Pancrace Bonaventure",
editor = "Cunha, Rossana and
Shaikh, Samira and
Varis, Erika and
Georgi, Ryan… See the full description on the dataset page: https://huggingface.co/datasets/FrancophonIA/FFR.ffr-physiology-prediction-coherence-baseline-mapping-v0.1
Goal
Define the baseline coherencebetween AI-derived FFR predictionsand real physiological signals.
Signals include:
myocardial perfusion
wall motion
stress test results
vital signs
This dataset establisheswhat physiologically plausible alignmentlooks like.
Without this baselineimplausibility cannot be detected.
Required output
The model must provide:
physiological_coherence_score
interpretation of alignment error
baseline_label
Why this matters… See the full description on the dataset page: https://huggingface.co/datasets/ClarusC64/ffr-physiology-prediction-coherence-baseline-mapping-v0.1.ffr-failure-horizon-intervention-routing-v0.1Dataset goal
Forecast when AI-derived FFR reliabilitywill cross a clinical risk threshold.
Then route the correct interventionbefore unsafe output enters workflow.
Inputs
image quality signals
model variance and disagreement
calibration residuals
coherence decay score
drift pattern label
Required outputs
failure_horizon_min
intervention_route
workflow_fallback
expected_safety_gain
confidence_score
Routes
Examples:
re-scan protocol
segmentation repair then rerun
disable output and escalate… See the full description on the dataset page: https://huggingface.co/datasets/ClarusC64/ffr-failure-horizon-intervention-routing-v0.1.