Related Concept Videos
Uncertainty: Overview
Propagation of Uncertainty from Random Error
Propagation of Uncertainty from Systematic Error
Uncertainty in Measurement: Accuracy and Precision
Uncertainty in Measurement: Reading Instruments
Data Reporting and Recording
You might also read
Related Articles
Articles linked to this work by shared authors, journal, and citation graph.
Mechanochemical upcycling of poly (vinyl chloride) for alcohol halogenation.
Iron-sulfur biogeochemical coupling drives subsurface mobilization of Fe and SO₄ in mining groundwaters: Multi-isotope (Sr, Fe, S, O, H) evidence.
Biomimetic mineralized collagen nanostructures orchestrate osteogenesis and osteoimmunomodulation to improve osseointegration of titanium alloy microporous interfaces.
Clinical Manifestations.
High pump depletion second-harmonic generation using domain engineered thin-film lithium niobate waveguides.
Habitat Diversity Sustains Ecosystem Functioning in Plateau Arid-Region Wetlands.
Tooling or Not Tooling? The Impact of Tools on Language Agents for Chemistry Problem Solving.
LMOD: A Large Multimodal Ophthalmology Dataset and Benchmark for Large Vision-Language Models.
Identifying Self-Disclosures of Use, Misuse and Addiction in Community-based Social Media Posts.
Uncertainty Quantification for Clinical Outcome Predictions with (Large) Language Models.
OSCaR: Object State Captioning and State Change Representation.
Related Experiment Video
Updated: Jan 7, 2026

Guidelines and Experience Using Imaging Biomarker Explorer IBEX for Radiomics
Published on: January 8, 2018
Semantic Consistency-Based Uncertainty Quantification for Factuality in Radiology Report Generation.
Chenyu Wang1, Weichao Zhou2, Shantanu Ghosh1
1Boston University.
This study introduces a new framework to quantify uncertainty in AI-generated radiology reports, improving factual accuracy by detecting and rejecting inaccurate information. The method enhances the reliability of automated radiology report generation (RRG).
More Related Videos
Area of Science:
- Artificial Intelligence
- Medical Imaging
- Natural Language Processing
Background:
- Automated radiology report generation (RRG) shows promise in assisting radiologists.
- Current generative models, including Vision Large Language Models (VLLMs), struggle with factual accuracy and hallucinations.
- Ensuring the factual correctness of AI-generated reports is a critical challenge.
Purpose of the Study:
- To introduce a novel Semantic Consistency-Based Uncertainty Quantification (SCUQ) framework for RRG.
- To provide both report-level and sentence-level uncertainty measures.
- To develop a plug-and-play module that enhances factual accuracy without altering existing models.
Main Methods:
- Developed a Semantic Consistency-Based Uncertainty Quantification (SCUQ) framework.
- Implemented a method that quantifies uncertainty without model modification or access to inner states.
- Integrated the SCUQ framework as a plug-and-play module with state-of-the-art RRG models.
Main Results:
- The SCUQ framework effectively detects hallucinations and improves the factual accuracy of generated reports.
- Rejecting high-uncertainty reports improved factuality scores by 10% on the MIMIC-CXR dataset using the Radialog model.
- Sentence-level uncertainty successfully flagged low-precision sentences with an 82.9% success rate.
Conclusions:
- The SCUQ framework significantly enhances the factual accuracy of AI-generated radiology reports.
- This plug-and-play approach offers a practical solution for improving the reliability of RRG systems.
- The open-source implementation facilitates further research and adoption in medical AI.

