paper-with-me

홈 › Papers

Multi-RADS Synthetic Radiology Report Dataset and Head-to-Head Benchmarking of 41 Open-Weight and Proprietary Language Models

2026-01-06 · Kartik Bose, Abhinandan Kumar, Raghuraman Soundararajan, Priya Mudgil, Samonee Ralmilay, Niharika Dutta, Manphool Singhal, Arun Kumar, Saugata Sen, Anurima Patra, Priya Ghosh, Abanti Das, Amit Gupta, Ashish Verma, Dipin Sudhakaran, Ekta Dhamija, Himangi Unde, Ishan Kumar, Krithika Rangarajan, Prerna Garg, Rachel Sequeira, Sudhin Shylendran, Taruna Yadav, Tej Pal, Pankaj Gupta arxiv

Background: Reporting and Data Systems (RADS) standardize radiology risk communication but automated RADS assignment from narrative reports is challenging because of guideline complexity, output-format constraints, and limited benchmarking across RADS frameworks and model sizes. Purpose: To create RXL-RADSet, a radiologist-verified synthetic multi-RADS benchmark, and compare validity and accuracy of open-weight small language models (SLMs) with a proprietary model for RADS assignment. Materials and Methods: RXL-RADSet contains 1,600 synthetic radiology reports across 10 RADS (BI-RADS, CAD-RADS, GB-RADS, LI-RADS, Lung-RADS, NI-RADS, O-RADS, PI-RADS, TI-RADS, VI-RADS) and multiple modalities. Reports were generated by LLMs using scenario plans and simulated radiologist styles and underwent two-stage radiologist verification. We evaluated 41 quantized SLMs (12 families, 0.135-32B parameters) and GPT-5.2 under a fixed guided prompt. Primary endpoints were validity and accuracy; a secondary analysis compared guided versus zero-shot prompting. Results: Under guided prompting GPT-5.2 achieved 99.8% validity and 81.1% accuracy (1,600 predictions). Pooled SLMs (65,600 predictions) achieved 96.8% validity and 61.1% accuracy; top SLMs in the 20-32B range reached ~99% validity and mid-to-high 70% accuracy. Performance scaled with model size (inflection between <1B and >=10B) and declined with RADS complexity primarily due to classification difficulty rather than invalid outputs. Guided prompting improved validity (99.2% vs 96.7%) and accuracy (78.5% vs 69.6%) compared with zero-shot. Conclusion: RXL-RADSet provides a radiologist-verified multi-RADS benchmark; large SLMs (20-32B) can approach proprietary-model performance under guided prompting, but gaps remain for higher-complexity schemes.

📄 PDF Abstract BibTeX arXiv:2601.03232

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

RadSEM: A Finding-by-Finding Metric for Clinical Consistency in Radiology Reports

2026-06-03 · Zhenhong Yang, Zhuoyun Liu, Jintao Fei, Wen Tang 외 arxiv

Radiology report evaluation must distinguish clinical compatibility from surface similarity, because negation, laterality, or normal-abnormal polarity can reverse a finding. We propose RadSEM (Radiology Sentence-Level Ev…

A Scalable Machine Learning Approach for Inferring Probabilistic US-LI-RADS Categorization

2018-06-15 · Imon Banerjee, Hailey H. Choi, Terry Desser, Daniel L. Rubin

We propose a scalable computerized approach for large-scale inference of Liver Imaging Reporting and Data System (LI-RADS) final assessment categories in narrative ultrasound (US) reports. Although our model was trained …

BIG-bench Machine Learning

FineRadScore: A Radiology Report Line-by-Line Evaluation Technique Generating Corrections with Severity Scores

2024-05-31 · Alyssa Huang, Oishi Banerjee, Kay Wu, Eduardo Pontes Reis 외

The current gold standard for evaluating generated chest x-ray (CXR) reports is through radiologist annotations. However, this process can be extremely time-consuming and costly, especially when evaluating large numbers …

Language ModelingLanguage ModellingLarge Language Model

SCREENet: A Multi-view Deep Convolutional Neural Network for Classification of High-resolution Synthetic Mammographic Screening Scans

2020-09-18 · Saeed Seyyedi, Margaret J. Wong, Debra M. Ikeda, Curtis P. Langlotz

Purpose: To develop and evaluate the accuracy of a multi-view deep learning approach to the analysis of high-resolution synthetic mammograms from digital breast tomosynthesis screening cases, and to assess the effect on …

Supervised Machine Learning Algorithm for Detecting Consistency between Reported Findings and the Conclusions of Mammography Reports

2022-02-28 · Alexander Berdichevsky, Mor Peleg, Daniel L. Rubin

Objective. Mammography reports document the diagnosis of patients' conditions. However, many reports contain non-standard terms (non-BI-RADS descriptors) and incomplete statements, which can lead to conclusions that are …

Semantic SimilaritySemantic Textual Similarity