EUVIMEDEUVIMED entdecken
Crossref

Automatic Radiology Reports Generation via Memory Alignment Network

Hongyu Shen, Mingtao Pei, Juncai Liu, Zhaoxing Tian

Proceedings of the AAAI Conference on Artificial Intelligence · 24.03.2024 · 38 (5) · 4776-4783

DOI: 10.1609/aaai.v38i5.28279 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 24.03.2024. Verfasst von Hongyu Shen und 3 weiteren Autor:innen. Die Arbeit wurde bisher 39-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The automatic generation of radiology reports is of great significance, which can reduce the workload of doctors and improve the accuracy and reliability of medical diagnosis and treatment, and has attracted wide attention in recent years. Cross-modal mapping between images and text, a key component of generating high-quality reports, is challenging due to the lack of corresponding annotations. Despite its importance, previous studies have often overlooked it or lacked adequate designs for this crucial component. In this paper, we propose a method with memory alignment embedding to assist the model in aligning visual and textual features to generate a coherent and informative report. Specifically, we first get the memory alignment embedding by querying the memory matrix, where the query is derived from a combination of the visual features and their corresponding positional embeddings. Then the alignment between the visual and textual features can be guided by the memory alignment embedding during the generation process. The comparison experiments with other alignment methods show that the proposed alignment method is less costly and more effective. The proposed approach achieves better performance than state-of-the-art approaches on two public datasets IU X-Ray and MIMIC-CXR, which further demonstrates the effectiveness of the proposed alignment method.

Zitieren

APA

Shen, H., Pei, M., Liu, J., & Tian, Z. (2024). Automatic Radiology Reports Generation via Memory Alignment Network. Proceedings of the AAAI Conference on Artificial Intelligence, 38(5), 4776-4783. https://doi.org/10.1609/aaai.v38i5.28279

Vancouver

Shen H, Pei M, Liu J, Tian Z. Automatic Radiology Reports Generation via Memory Alignment Network. Proceedings of the AAAI Conference on Artificial Intelligence. 2024;38(5):4776-4783. doi:10.1609/aaai.v38i5.28279

BibTeX
@article{Shen2024,
  author = {Shen, Hongyu and Pei, Mingtao and Liu, Juncai and Tian, Zhaoxing},
  title = {Automatic Radiology Reports Generation via Memory Alignment Network},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2024},
  volume = {38},
  number = {5},
  pages = {4776--4783},
  doi = {10.1609/aaai.v38i5.28279}
}
Kostenlos starten →