The reviewed record of science sign in
Pith

arxiv: 2004.09167 · v3 · pith:LYV7NO4E · submitted 2020-04-20 · cs.CL · cs.IR· cs.LG

CheXbert: Combining Automatic Labelers and Expert Annotations for Accurate Radiology Report Labeling Using BERT

Reviewed by Pithpith:LYV7NO4Eopen to challenge →

classification cs.CL cs.IRcs.LG
keywords annotationslabelingreportexpertmedicalbertchexbertlabeler
0
0 comments X
read the original abstract

The extraction of labels from radiology text reports enables large-scale training of medical imaging models. Existing approaches to report labeling typically rely either on sophisticated feature engineering based on medical domain knowledge or manual annotations by experts. In this work, we introduce a BERT-based approach to medical image report labeling that exploits both the scale of available rule-based systems and the quality of expert annotations. We demonstrate superior performance of a biomedically pretrained BERT model first trained on annotations of a rule-based labeler and then finetuned on a small set of expert annotations augmented with automated backtranslation. We find that our final model, CheXbert, is able to outperform the previous best rules-based labeler with statistical significance, setting a new SOTA for report labeling on one of the largest datasets of chest x-rays.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 13 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. CheXTemporal: A Dataset for Temporally-Grounded Reasoning in Chest Radiography

    cs.CV 2026-05 accept novelty 8.0

    CheXTemporal supplies paired chest X-rays with explicit temporal progression taxonomy and spatial grounding to benchmark and improve models on longitudinal reasoning tasks.

  2. BenSyc: Benchmarking Conversational Sycophancy and Human Alignment in LLMs for Bengali Contexts

    cs.CL 2026-06 unverdicted novelty 7.0

    BenSyc is the first benchmark for conversational sycophancy in Bengali, with top LLMs achieving only 61.8 Macro-F1 on binary detection and 61.7 on five-class classification while often generating overly validating responses.

  3. AnchorDiff: Topology-Aware Masked Diffusion with Confidence-based Rewriting for Radiology Report Generation

    cs.AI 2026-05 unverdicted novelty 7.0

    AnchorDiff is a topology-aware masked diffusion framework with RadGraph anchors and confidence-based rewriting that claims state-of-the-art results on MIMIC-CXR and MIMIC-RG4 for radiology report generation.

  4. CT-FineBench: A Diagnostic Fidelity Benchmark for Fine-Grained Evaluation of CT Report Generation

    cs.AI 2026-04 unverdicted novelty 7.0

    CT-FineBench is a QA-based benchmark that evaluates fine-grained factual consistency of generated CT reports by probing specific clinical attributes such as location, size, and margin.

  5. Beyond Classification Accuracy: Neural-MedBench and the Need for Deeper Reasoning Benchmarks

    cs.CV 2025-09 unverdicted novelty 7.0

    Neural-MedBench reveals sharp performance drops in state-of-the-art VLMs on reasoning-intensive neurology tasks compared to conventional classification benchmarks, with reasoning failures dominating errors.

  6. CheXmix: Unified Generative Pretraining for Vision Language Models in Medical Imaging

    cs.CV 2026-04 unverdicted novelty 6.0

    CheXmix combines masked autoencoder pretraining with early-fusion generative modeling to outperform prior models on chest X-ray classification by up to 8.6% AUROC, inpainting by 51%, and report generation by 45% on GREEN.

  7. Enhancing Reinforcement Learning for Radiology Report Generation with Evidence-aware Rewards and Self-correcting Preference Learning

    cs.LG 2026-04 unverdicted novelty 6.0

    ESC-RL improves RL for radiology reports via group-wise evidence-aware rewards (GEAR) and LLM-driven self-correcting preference learning (SPL), reaching state-of-the-art on two chest X-ray datasets.

  8. Gaze2Report: Radiology Report Generation via Visual-Gaze Prompt Tuning of LLMs

    q-bio.TO 2026-04 unverdicted novelty 6.0

    Gaze2Report combines predicted eye-gaze scanpaths and graph neural networks with LoRA-tuned LLMs to generate radiology reports that incorporate human visual attention without requiring gaze data at inference time.

  9. MOSAIC: A Multilingual, Taxonomy-Agnostic, and Computationally Efficient Approach for Radiological Report Classification

    cs.CL 2025-08 unverdicted novelty 6.0

    MOSAIC achieves mean macro F1 of 88 on chest X-ray report classification across five datasets in four languages using a 4B-parameter open model with low GPU memory and few-shot or light fine-tuning options.

  10. Precision Recall Controllable Radiology Report Generation via Hybrid Natural Language and Clinical Reward Learning

    cs.CL 2026-06 unverdicted novelty 5.0

    Reinforcement learning with a tunable control parameter and clinical reward enables precision-recall controllable radiology report generation that outperforms prior methods on MIMIC-CXR.

  11. Precision Recall Controllable Radiology Report Generation via Hybrid Natural Language and Clinical Reward Learning

    cs.CL 2026-06 unverdicted novelty 5.0

    A reinforcement learning framework for radiology report generation introduces a control parameter for precision-recall trade-off plus clinical rewards and group-relative training, claiming better NLG and clinical effi...

  12. RadLite: Multi-Task LoRA Fine-Tuning of Small Language Models for CPU-Deployable Radiology AI

    cs.CL 2026-05 unverdicted novelty 5.0

    LoRA fine-tuning of 3-4B SLMs on 162K multi-task radiology data yields strong performance deployable on consumer CPUs at 4-8 tokens/second.

  13. M4CXR: Exploring Multi-task Potentials of Multi-modal Large Language Models for Chest X-ray Interpretation

    cs.CV 2024-08 unverdicted novelty 5.0

    M4CXR is a multi-modal large language model that performs multiple tasks in chest X-ray analysis including report generation with claimed SOTA clinical accuracy using chain-of-thought prompting.