EUVIMEDEUVIMED entdecken
Übersichtsarbeit

Automatic medical report generation based on deep learning: A state of the art survey

Xinyao Liu, Junchang Xin, Qi Shen, Zhihong Huang, Zhiqiong Wang

Computerized Medical Imaging and Graphics · 2025-03 · 120 · 102486

DOI: 10.1016/j.compmedimag.2024.102486 ↗

Kurz gefasst

Übersichtsarbeit in der Zeitschrift Computerized Medical Imaging and Graphics, 2025-03. Verfasst von Xinyao Liu und 4 weiteren Autor:innen. Beteiligte Einrichtung: College of Medicine and Biological Information Engineering, Northeastern University, 110819, China. Hauptthemen laut MEDLINE: Deep Learning, Radiology Information Systems, Diagnostic Imaging. Die Arbeit wurde bisher 18-mal zitiert (Crossref) und nennt 139 Literaturangaben. Gefördert von: National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

With the increasing popularity of medical imaging and its expanding applications, posing significant challenges for radiologists. Radiologists need to spend substantial time and effort to review images and manually writing reports every day. To address these challenges and speed up the process of patient care, researchers have employed deep learning methods to automatically generate medical reports. In recent years, researchers have been increasingly focusing on this task and a large amount of related work has emerged. Although there have been some review articles summarizing the state of the art in this field, their discussions remain relatively limited. Therefore, this paper provides a comprehensive review of the latest advancements in automatic medical report generation, focusing on four key aspects: (1) describing the problem of automatic medical report generation, (2) introducing datasets of different modalities, (3) thoroughly analyzing existing evaluation metrics, (4) classifying existing studies into five categories: retrieval-based, domain knowledge-based, attention-based, reinforcement learning-based, large language models-based, and merged model. In addition, we point out the problems in this field and discuss the directions of future challenges. We hope that this review provides a thorough understanding of automatic medical report generation and encourages the continued development in this area.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningRadiology Information SystemsDiagnostic ImagingHumans

Stichwörter der Autor:innen

Automatic medical report generationDeep learningEncoder–decoder frameworkMedical imageNatural language process

Autor:innen und Institutionen

  • College of Medicine and Biological Information Engineering, Northeastern University, 110819, China.
  • College of Computer Science and Engineering, Northeastern University, 110819, China.
  • School of Science and Engineering, University of Dundee, DD1 4HN, UK.
  • College of Medicine and Biological Information Engineering, Northeastern University, 110819, China. Electronic address: wangzq@bmie.neu.edu.cn.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Liu, X., Xin, J., Shen, Q., Huang, Z., & Wang, Z. (2025). Automatic medical report generation based on deep learning: A state of the art survey. Computerized Medical Imaging and Graphics, 120, 102486. https://doi.org/10.1016/j.compmedimag.2024.102486

Vancouver

Liu X, Xin J, Shen Q, Huang Z, Wang Z. Automatic medical report generation based on deep learning: A state of the art survey. Computerized Medical Imaging and Graphics. 2025;120:102486. doi:10.1016/j.compmedimag.2024.102486

BibTeX
@article{Liu2025,
  author = {Liu, Xinyao and Xin, Junchang and Shen, Qi and Huang, Zhihong and Wang, Zhiqiong},
  title = {Automatic medical report generation based on deep learning: A state of the art survey},
  journal = {Computerized Medical Imaging and Graphics},
  year = {2025},
  volume = {120},
  pages = {102486},
  doi = {10.1016/j.compmedimag.2024.102486}
}
Kostenlos starten →