Retrieval from Dynamic Phrases: Generating Radiograph Reports with Phrase-Level Template and Dynamic Memory Bank

  • Haoquan Chen
  • , Bin Yan
  • , Hongyu Shen
  • , Mingtao Pei*
  • *Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Most retrieval-based report generation methods rely on sentence-level templates, which often introduce ambiguities due to similar semantics across different sentences. To overcome this, we propose a phrase-level framework, comprising automatic phrase template extraction and report generation based on retrieval. In the first stage, we introduce a phrase scoring mechanism to evaluate the semantics and importance of phrases, enabling efficient template extraction. In the second stage, we retrieve relevant templates and fuse their features with visual features from the radiograph through a Retrieval-Aggregation strategy. The dynamic update of the template bank during training improves template representations. Experiments on IU X-Ray and MIMIC-CXR datasets demonstrate the effectiveness of our method in generating accurate radiology reports.

Original languageEnglish
Title of host publicationInternational Joint Conference on Neural Networks, IJCNN 2025 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9798331510428
DOIs
Publication statusPublished - 2025
Externally publishedYes
Event2025 International Joint Conference on Neural Networks, IJCNN 2025 - Rome, Italy
Duration: 30 Jun 20255 Jul 2025

Publication series

NameProceedings of the International Joint Conference on Neural Networks
ISSN (Print)2161-4393
ISSN (Electronic)2161-4407

Conference

Conference2025 International Joint Conference on Neural Networks, IJCNN 2025
Country/TerritoryItaly
CityRome
Period30/06/255/07/25

Keywords

  • Dynamic Bank
  • Phrase Templates
  • Radiograph Report Generation
  • Vision-Language Retrieval

Fingerprint

Dive into the research topics of 'Retrieval from Dynamic Phrases: Generating Radiograph Reports with Phrase-Level Template and Dynamic Memory Bank'. Together they form a unique fingerprint.

Cite this