Skip to content
← Back to explorer

Learning to Read Where to Look: Disease-Aware Vision-Language Pretraining for 3D CT

Simon Ging, Philipp Arnold, Sebastian Walter, Hani Alnahas, Hannah Bast, Elmar Kotter, Jiancheng Yang, Behzad Bozorgtabar, Thomas Brox · Mar 2, 2026 · Citations: 0

Open arXiv Find Implementation RSS feed Shortlist (0)

Data freshness

Extraction: Fresh

Check recency before relying on this page for active eval decisions. Use stale pages as context and verify against current hub results.

Metadata refreshed

Mar 2, 2026, 4:10 PM

Recent

Extraction refreshed

Mar 8, 2026, 3:14 AM

Fresh

Extraction source

Persisted extraction

Confidence 0.20

Abstract

Recent 3D CT vision-language models align volumes with reports via contrastive pretraining, but typically rely on limited public data and provide only coarse global supervision. We train a 3D CT vision-language model on 98k report-volume pairs (50k patients) collected at a single hospital, combined with public datasets, using SigLIP-style contrastive pretraining together with prompt-based disease supervision in the shared vision-text embedding space. On CT-RATE, our model achieves state-of-the-art text-to-image retrieval (R@10 31.5 vs. 22.2) and competitive disease classification (AUC 83.8 vs. 83.8), with consistent results on Rad-ChestCT (AUC 77.0 vs. 77.3). We further observe that radiologists routinely reference specific images within their reports (e.g., ``series X, image Y''), linking textual descriptions to precise axial locations. We automatically mine 262k such snippet-slice pairs and introduce the task of intra-scan snippet localization -- predicting the axial depth referred to by a text snippet -- reducing mean absolute error to 36.3 mm at 12 mm feature resolution, compared with 67.0 mm for the best baseline. Adding this localization objective leaves retrieval and classification broadly unchanged within confidence bounds, yielding a single unified model for retrieval, classification, and intra-scan grounding.

Low-signal caution for protocol decisions

Use this page for context, then validate protocol choices against stronger HFEPX references before implementation decisions.

  • Extraction flags indicate low-signal or possible false-positive protocol mapping.
  • Extraction confidence is 0.20 (below strong-reference threshold).
  • No explicit evaluation mode was extracted from available metadata.
Human Eval Hub LLM-as-Judge Hub Pairwise Preference Hub

HFEPX Relevance Assessment

This paper is adjacent to HFEPX scope and is best used for background context, not as a primary protocol reference.

Best use

Background context only

Use if you need

Background context only.

Main weakness

Extraction flags indicate low-signal or possible false-positive protocol mapping.

Trust level

Low

Eval-Fit Score

0/100 • Low

Treat as adjacent context, not a core eval-method reference.

Human Feedback Signal

Not explicit in abstract metadata

Evaluation Signal

Weak / implicit signal

HFEPX Fit

Adjacent candidate

Extraction confidence: Low

If you are doing eval pipeline work, start here:

Human Eval Hub LLM-as-Judge Hub Pairwise Preference Hub Tool-Use Eval Hub

Field Provenance & Confidence

Each key protocol field shows extraction state, confidence band, and data source so you can decide whether to trust it directly or validate from full text.

Human Feedback Types

missing

None explicit

Confidence: Low Source: Persisted extraction missing

No explicit feedback protocol extracted.

Evidence snippet: Recent 3D CT vision-language models align volumes with reports via contrastive pretraining, but typically rely on limited public data and provide only coarse global supervision.

Evaluation Modes

missing

None explicit

Confidence: Low Source: Persisted extraction missing

Validate eval design from full paper text.

Evidence snippet: Recent 3D CT vision-language models align volumes with reports via contrastive pretraining, but typically rely on limited public data and provide only coarse global supervision.

Quality Controls

missing

Not reported

Confidence: Low Source: Persisted extraction missing

No explicit QC controls found.

Evidence snippet: Recent 3D CT vision-language models align volumes with reports via contrastive pretraining, but typically rely on limited public data and provide only coarse global supervision.

Benchmarks / Datasets

missing

Not extracted

Confidence: Low Source: Persisted extraction missing

No benchmark anchors detected.

Evidence snippet: Recent 3D CT vision-language models align volumes with reports via contrastive pretraining, but typically rely on limited public data and provide only coarse global supervision.

Reported Metrics

partial

Mae

Confidence: Low Source: Persisted extraction evidenced

Useful for evaluation criteria comparison.

Evidence snippet: Recent 3D CT vision-language models align volumes with reports via contrastive pretraining, but typically rely on limited public data and provide only coarse global supervision.

Rater Population

missing

Unknown

Confidence: Low Source: Persisted extraction missing

Rater source not explicitly reported.

Evidence snippet: Recent 3D CT vision-language models align volumes with reports via contrastive pretraining, but typically rely on limited public data and provide only coarse global supervision.

Human Data Lens

  • Uses human feedback: No
  • Feedback types: None
  • Rater population: Unknown
  • Unit of annotation: Unknown
  • Expertise required: Medicine
  • Extraction source: Persisted extraction

Evaluation Lens

  • Evaluation modes:
  • Agentic eval: None
  • Quality controls: Not reported
  • Confidence: 0.20
  • Flags: low_signal, possible_false_positive

Protocol And Measurement Signals

Benchmarks / Datasets

No benchmark or dataset names were extracted from the available abstract.

Reported Metrics

mae

Research Brief

Deterministic synthesis

Recent 3D CT vision-language models align volumes with reports via contrastive pretraining, but typically rely on limited public data and provide only coarse global supervision. HFEPX protocol signal is limited in abstract-level metadata, so treat it as adjacent context. Updated from current HFEPX corpus.

Generated Mar 8, 2026, 3:14 AM · Grounded in abstract + metadata only

Key Takeaways

  • Recent 3D CT vision-language models align volumes with reports via contrastive pretraining, but typically rely on limited public data and provide only coarse global supervision.
  • We train a 3D CT vision-language model on 98k report-volume pairs (50k patients) collected at a single hospital, combined with public datasets, using SigLIP-style contrastive…
  • Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.

Researcher Actions

  • Treat this as method context, then pivot to protocol-specific HFEPX hubs.
  • Identify benchmark choices from full text before operationalizing conclusions.
  • Validate metric comparability (mae).

Caveats

  • Generated from title, abstract, and extracted metadata only; full-paper implementation details are not parsed.
  • Low-signal flag detected: protocol relevance may be indirect.

Research Summary

Contribution Summary

  • Recent 3D CT vision-language models align volumes with reports via contrastive pretraining, but typically rely on limited public data and provide only coarse global supervision.
  • We train a 3D CT vision-language model on 98k report-volume pairs (50k patients) collected at a single hospital, combined with public datasets, using SigLIP-style contrastive pretraining together with prompt-based disease supervision in the…
  • On CT-RATE, our model achieves state-of-the-art text-to-image retrieval (R@10 31.5 vs.

Why It Matters For Eval

  • Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.

Researcher Checklist

  • Gap: Human feedback protocol is explicit

    No explicit human feedback protocol detected.

  • Gap: Evaluation mode is explicit

    No clear evaluation mode extracted.

  • Gap: Quality control reporting appears

    No calibration/adjudication/IAA control explicitly detected.

  • Gap: Benchmark or dataset anchors are present

    No benchmark/dataset anchor extracted from abstract.

  • Pass: Metric reporting is present

    Detected: mae

Category-Adjacent Papers (Broader Context)

These papers are nearby in arXiv category and useful for broader context, but not necessarily protocol-matched to this paper.

Need human evaluators for your AI research? Scale annotation with expert AI Trainers.

Post a Job Get a Quote