Correction: Confidence Measurement Metrics in Multimodal Large Language Models for Ultrasound-Based Radiology Cases: Comparative Evaluation Study of Self-Reported, Consistency-Based, and Hybrid Methods - Takeaways - MDSpire

Correction: Confidence Measurement Metrics in Multimodal Large Language Models for Ultrasound-Based Radiology Cases: Comparative Evaluation Study of Self-Reported, Consistency-Based, and Hybrid Methods

  • By

  • Taewon Han

  • Jaeseung Shin

  • Jeong Hyun Lee

  • Kyowon Gu

  • July 6, 2026

  • 0 min

Share

  • 1

    The article discusses corrections made to a study on confidence measurement metrics in multimodal large language models for ultrasound radiology.

  • 2

    A footnote from Table 2 has been removed as part of the corrections to the original article.

  • 3

    The Shannon entropy formula in the Confidence Measurement Metrics section has been updated.

  • 4

    The values for 'GPT-5' and 'Majority vote (5), n (%)' in Table 1 have been replaced with new data.

  • 5

    The corrected article will be published online and resubmitted to PubMed and other repositories.

Original Source(s)

Correction: Confidence Measurement Metrics in Multimodal Large Language Models for Ultrasound-Based Radiology Cases: Comparative Evaluation Study of Self-Reported, Consistency-Based, and Hybrid Methods

  • by Taewon Han, Jaeseung Shin, Jeong Hyun Lee, Kyowon Gu

  • July 6, 2026

Related Content

The grand piano ratio: an adjunctive intraoperative screening tool for detecting excessive femoral component external rotation in total knee arthroplasty

Early endocrine, bone, and inflammatory responses to microwave ablation for hyperparathyroidism: preliminary study

The role of 18F-FDG PET/CT in identifying risk factors for ground-glass nodules in invasive lung adenocarcinoma