EUVIMEDEUVIMED entdecken
Crossref

AERMNet: Attention-enhanced relational memory network for medical image report generation

Xianhua Zeng, Tianxing Liao, Liming Xu, Zhiqiang Wang

Computer Methods and Programs in Biomedicine · 2024-02 · 244 · 107979

DOI: 10.1016/j.cmpb.2023.107979 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Computer Methods and Programs in Biomedicine, 2024-02. Verfasst von Xianhua Zeng und 3 weiteren Autor:innen. Beteiligte Einrichtung: College of Computer Science and Technology, Chongqing University of Posts and Telecommunications, Chongqing 400065, China. Electronic address: zengxh…. Hauptthemen laut MEDLINE: Benchmarking, Physicians. Die Arbeit wurde bisher 25-mal zitiert (Crossref) und nennt 53 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

BACKGROUND AND OBJECTIVES: The automatic generation of medical image diagnostic reports can assist doctors in reducing their workload and improving the efficiency and accuracy of diagnosis. However, among the most existing report generation models, there are problems that the weak correlation between generated words and the lack of contextual information in the report generation process. METHODS: To address the above problems, we propose an Attention-Enhanced Relational Memory Network (AERMNet) model, where the relational memory module is continuously updated by the words generated in the previous time step to strengthen the correlation between words in generated medical image report. And the double LSTM with interaction module reduces the loss of context information and makes full use of feature information. Thus, more accurate disease information can be generated by AERMNet for medical image reports. RESULTS: Experimental results on four medical datasets Fetal heart (FH), Ultrasound, IU X-Ray and MIMIC-CXR, show that our proposed method outperforms some of the previous models with respect to language generation metrics (Cider improving by 2.4% on FH, Bleu1 improving by 2.4% on Ultrasound, Cider improving by 16.4% on IU X-Ray, Bleu2 improving by 9.7% on MIMIC-CXR). CONCLUSIONS: This work promotes the development of medical image report generation and expands the prospects of computer-aided diagnosis applications. Our code is released at https://github.com/llttxx/AERMNET.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

BenchmarkingPhysiciansHumansDiagnosis, Computer-AssistedLanguageMedical RecordsImage Processing, Computer-Assisted

Stichwörter der Autor:innen

Context informationDouble LSTMInteractionMedical image report generationRelational memory

Autor:innen und Institutionen

  • College of Computer Science and Technology, Chongqing University of Posts and Telecommunications, Chongqing 400065, China. Electronic address: zengxh@cqupt.edu.cn.
  • College of Computer Science and Technology, Chongqing University of Posts and Telecommunications, Chongqing 400065, China.
  • College of Computer Science, China West Normal University, Nanchong, Sichuan, 637000, China.

Zitieren

APA

Zeng, X., Liao, T., Xu, L., & Wang, Z. (2024). AERMNet: Attention-enhanced relational memory network for medical image report generation. Computer Methods and Programs in Biomedicine, 244, 107979. https://doi.org/10.1016/j.cmpb.2023.107979

Vancouver

Zeng X, Liao T, Xu L, Wang Z. AERMNet: Attention-enhanced relational memory network for medical image report generation. Computer Methods and Programs in Biomedicine. 2024;244:107979. doi:10.1016/j.cmpb.2023.107979

BibTeX
@article{Zeng2024,
  author = {Zeng, Xianhua and Liao, Tianxing and Xu, Liming and Wang, Zhiqiang},
  title = {AERMNet: Attention-enhanced relational memory network for medical image report generation},
  journal = {Computer Methods and Programs in Biomedicine},
  year = {2024},
  volume = {244},
  pages = {107979},
  doi = {10.1016/j.cmpb.2023.107979}
}
Kostenlos starten →