Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Encoding

Encoding

Information enters the brain through encoding, which is the input of information into the memory system. Once sensory information is received from the environment, the brain labels or codes it. The information is then organized with similar information and connected to existing concepts. Encoding occurs through automatic processing and effortful processing.
Automatic processing involves the encoding of details like time, space, frequency, and the meaning of words, usually done without conscious...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Large Language Models for Multidisciplinary Tumor Board Decision-Making in Primary Liver Tumors: A Retrospective Single-Center Study.

Cancers·2026

Same author

Generalizable and explainable deep learning for brain MRI: a multi-cohort evaluation of 3D architectures for age and sex prediction.

Brain informatics·2026

Same author

Erratum for: Associations of MRI-derived Paraspinal IMAT and LMM with Cardiometabolic Risk Factors: Results from a German Cohort.

Radiology·2026

Same author

Longitudinal five-year follow-up by muscle MRI and high-resolution nerve ultrasound in hereditary neuropathies.

Neurological research and practice·2026

Same author

Counterfactual Diffusion Models Provide Interpretable Explanations of Artificial Intelligence Models in Pathology.

Cancer research·2026

Same author

Towards autonomous medical artificial intelligence agents.

Nature·2026

Search research articles

Related Experiment Video

Updated: May 5, 2026

Interaction between Phonological and Semantic Processes in Visual Word Recognition using Electrophysiology

Interaction between Phonological and Semantic Processes in Visual Word Recognition using Electrophysiology

Published on: June 29, 2021

Hallucination filtering in radiology vision-language models using discrete semantic entropy.

Patrick Wienholt^1,2, Sophie Caselitz^3,4, Robert Siepmann^3,4

¹Lab for Artificial Intelligence in Medicine, Department of Diagnostic and Interventional Radiology, University Hospital RWTH Aachen, Aachen, Germany. pwienholt@ukaachen.de.

European Radiology

|February 20, 2026

Summary

Discrete semantic entropy (DSE) effectively detects hallucination-prone questions for vision-language models (VLMs). This method significantly improves accuracy in radiologic image analysis, enhancing VLM reliability for clinical applications.

Keywords:

Data accuracy Diagnostic imaging Entropy Generative artificial intelligence Image interpretation (Computer-assisted)

More Related Videos

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

Related Experiment Videos

Last Updated: May 5, 2026

Interaction between Phonological and Semantic Processes in Visual Word Recognition using Electrophysiology

Interaction between Phonological and Semantic Processes in Visual Word Recognition using Electrophysiology

Published on: June 29, 2021

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

Area of Science:

Artificial Intelligence
Medical Imaging
Natural Language Processing

Background:

Black-box vision-language models (VLMs) are increasingly used for radiologic image analysis.
Hallucinations, or inaccurate information generation, pose a significant challenge to VLM reliability in clinical settings.
Current methods for detecting VLM hallucinations are limited, especially in black-box scenarios.

Purpose of the Study:

To evaluate the efficacy of discrete semantic entropy (DSE) in identifying questions that may lead to hallucinations in VLMs.
To determine if DSE-based filtering can improve the accuracy of VLMs in radiologic image-based visual question answering (VQA).

Main Methods:

A retrospective study utilized two public datasets (VQA-Med 2019 and a diagnostic radiology dataset).
GPT-4o and GPT-4.1 models answered questions, with DSE computed from semantic response clusters.
Accuracy was assessed before and after filtering questions with DSE > 0.3.

Main Results:

Baseline accuracy for GPT-4o was 51.7% and for GPT-4.1 was 54.8%.
After DSE filtering (DSE > 0.3), accuracy increased to 76.3% for GPT-4o and 63.8% for GPT-4.1.
Accuracy gains were statistically significant across datasets, even after Bonferroni correction.

Conclusions:

DSE reliably detects hallucinations in black-box VLMs by quantifying semantic inconsistency.
This method significantly enhances diagnostic answer accuracy in radiologic VQA.
DSE provides a practical filtering strategy to improve the safety and trustworthiness of clinical VLM applications.