Beyond Scalar Scores: Exploring LLM-based Metrics for Clinical Significance Evaluation in Radiology Reports

• URL: http://arxiv.org/abs/2606.18797v1
• Date: Wed, 17 Jun 2026 08:10:30 GMT
• Title: Beyond Scalar Scores: Exploring LLM-based Metrics for Clinical Significance Evaluation in Radiology Reports
• Abstract summary: Existing metrics obscure this requirement by reducing report quality to a medically ungrounded scalar.<n>We study this boundary using ReEvalMed benchmark as testbed and evaluate metric-level clinical significance.
• Score: 49.5225801722164
• License: http://creativecommons.org/publicdomain/zero/1.0/
• Abstract: Reliable evaluation of generated radiology reports requires strict clinical accuracy, as omitted critical findings or mischaracterized radiographic observations can directly affect patient care. Existing metrics obscure this requirement by reducing report quality to a medically ungrounded scalar. Although Large Language Models (LLMs) possess rich medical knowledge, they likewise struggle to draw a reliable boundary between clinically significant errors and harmless variation. We study this boundary using ReEvalMed benchmark as testbed and evaluate metric-level clinical significance from detecting true clinical errors ("Discrimination") and tolerating insignificant variations ("Robustness"). Across 8 LLM evaluators under one-pass and two-pass settings, we identify a widespread discrimination bias: models effectively detect errors but also over-penalize harmless rephrasings. To mitigate this, we synthesize 4k report pairs and train lightweight interpretable metrics on Qwen3-8B and MedGemma-4B. Our trained metric sharpens the clinical significance boundary, surpassing 32B-scale medical LLMs and remaining competitive with proprietary models. Crucially, the more costly two-pass setting fails to consistently improve overall performance and mainly trades discrimination for robustness. These findings suggest one-pass trained metrics as the practical choice for cost-sensitive deployment, with two-pass inference reserved for settings where D-R balance is critical. We will release the dataset and metric.

Related papers

• CT-FineBench: A Diagnostic Fidelity Benchmark for Fine-Grained Evaluation of CT Report Generation [51.11942945171396]
  Conventional evaluation metrics offer only coarse measures of lexical overlap or entity matching.<n>We propose CT-FineBench, a benchmark built from CT-RATE and Merlin to evaluate the fine-grained factual consistency of CT reports.<n>Our benchmark is constructed through a meticulous, Question-Answering (QA) based process.
  arXiv  Detail & Related papers  (2026-04-27T03:32:46Z)
• Suppressing Prior-Comparison Hallucinations in Radiology Report Generation via Semantically Decoupled Latent Steering [94.37535002230504]
  We develop a training-free, inference-time control framework termed Semantically Decoupled Latent Steering.<n>Our approach constructs a semantic-free intervention vector via large language model (LLM)-driven semantic decomposition.<n>We show that our approach significantly reduces the probability of historical hallucinations.
  arXiv  Detail & Related papers  (2026-02-27T04:49:01Z)
• CTest-Metric: A Unified Framework to Assess Clinical Validity of Metrics for CT Report Generation [8.08950963137043]
  We present CTest-Metric, a first unified metric assessment framework with three modules determining the clinical feasibility of metrics for CT RRG.<n>The modules test: (i) Writing Style Generalizability (WSG) via LLM-based rephrasing; (ii) Synthetic Error Injection (SEI) at graded severities; and (iii) Metrics-vs-Expert correlation (MvE) using clinician ratings on 175 "disagreement" cases.<n>Eight widely used metrics (BLEU, ROUGE, METEOR, BERTScore-F1, F1-RadGraph, Ra
  arXiv  Detail & Related papers  (2026-01-16T18:09:19Z)
• Toward Reliable Clinical Coding with Language Models: Verification and Lightweight Adaptation [3.952186976672079]
  We show that lightweight interventions, including prompt engineering and small-scale fine-tuning, can improve accuracy without the computational overhead of search-based methods.<n>To address hierarchically near-miss errors, we introduce clinical code verification as both a standalone task and a pipeline component.
  arXiv  Detail & Related papers  (2025-10-08T23:50:58Z)
• ReEvalMed: Rethinking Medical Report Evaluation by Aligning Metrics with Real-World Clinical Judgment [10.958326795130112]
  We propose a clinically grounded Meta-Evaluation framework.<n>We define clinically grounded criteria spanning clinical alignment and key metric capabilities.<n>Our framework offers guidance for building more clinically reliable evaluation methods.
  arXiv  Detail & Related papers  (2025-09-30T21:00:47Z)
• CRG Score: A Distribution-Aware Clinical Metric for Radiology Report Generation [6.930435788495898]
  We propose the CRG Score, a metric that evaluates only clinically relevant abnormalities explicitly described in reference reports.<n>By balancing penalties based on label distribution, it enables fairer, more robust evaluation and serves as a clinically aligned reward function.
  arXiv  Detail & Related papers  (2025-05-22T17:02:28Z)
• GEMA-Score: Granular Explainable Multi-Agent Scoring Framework for Radiology Report Evaluation [7.838068874909676]
  Granular Explainable Multi-Agent Score (GEMA-Score) conducts both objective and subjective evaluation through a large language model-based multi-agent workflow.<n>GEMA-Score achieves the highest correlation with human expert evaluations on a public dataset.
  arXiv  Detail & Related papers  (2025-03-07T11:42:22Z)
• Improving Multiple Sclerosis Lesion Segmentation Across Clinical Sites: A Federated Learning Approach with Noise-Resilient Training [75.40980802817349]
  Deep learning models have shown promise for automatically segmenting MS lesions, but the scarcity of accurately annotated data hinders progress in this area. We introduce a Decoupled Hard Label Correction (DHLC) strategy that considers the imbalanced distribution and fuzzy boundaries of MS lesions. We also introduce a Centrally Enhanced Label Correction (CELC) strategy, which leverages the aggregated central model as a correction teacher for all sites.
  arXiv  Detail & Related papers  (2023-08-31T00:36:10Z)
• Learning to diagnose cirrhosis from radiological and histological labels with joint self and weakly-supervised pretraining strategies [62.840338941861134]
  We propose to leverage transfer learning from large datasets annotated by radiologists, to predict the histological score available on a small annex dataset. We compare different pretraining methods, namely weakly-supervised and self-supervised ones, to improve the prediction of the cirrhosis. This method outperforms the baseline classification of the METAVIR score, reaching an AUC of 0.84 and a balanced accuracy of 0.75.
  arXiv  Detail & Related papers  (2023-02-16T17:06:23Z)
• Towards Reliable Medical Image Segmentation by Modeling Evidential Calibrated Uncertainty [57.023423137202485]
  Concerns regarding the reliability of medical image segmentation persist among clinicians.<n>We introduce DEviS, an easily implementable foundational model that seamlessly integrates into various medical image segmentation networks.<n>By leveraging subjective logic theory, we explicitly model probability and uncertainty for medical image segmentation.
  arXiv  Detail & Related papers  (2023-01-01T05:02:46Z)
• Controlling False Positive/Negative Rates for Deep-Learning-Based Prostate Cancer Detection on Multiparametric MR images [58.85481248101611]
  We propose a novel PCa detection network that incorporates a lesion-level cost-sensitive loss and an additional slice-level loss based on a lesion-to-slice mapping function. Our experiments based on 290 clinical patients concludes that 1) The lesion-level FNR was effectively reduced from 0.19 to 0.10 and the lesion-level FPR was reduced from 1.03 to 0.66 by changing the lesion-level cost.
  arXiv  Detail & Related papers  (2021-06-04T09:51:27Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.