CSAMDT: Conditional Self Attention Memory-Driven Transformers for Radiology Report Generation from Chest X-Ray
Journal of Imaging Informatics in Medicine · 03.06.2024 · 37 (6) · 2825-2837
DOI: 10.1007/s10278-024-01126-6 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Imaging Informatics in Medicine, online erschienen am 03.06.2024. Verfasst von Iqra Shahzadi und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science, COMSATS University Islamabad, Islamabad, Pakistan. Hauptthemen laut MEDLINE: Radiography, Thoracic. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 66 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: Higher Education Commision, Pakistan.
Abstract (Originalsprache)
A radiology report plays a crucial role in guiding patient treatment, but writing these reports is a time-consuming task that demands a radiologist's expertise. In response to this challenge, researchers in the subfields of artificial intelligence for healthcare have explored techniques for automatically interpreting radiographic images and generating free-text reports, while much of the research on medical report creation has focused on image captioning methods without adequately addressing particular report aspects. This study introduces a Conditional Self Attention Memory-Driven Transformer model for generating radiological reports. The model operates in two phases: initially, a multi-label classification model, utilizing ResNet152 v2 as an encoder, is employed for feature extraction and multiple disease diagnosis. In the second phase, the Conditional Self Attention Memory-Driven Transformer serves as a decoder, utilizing self-attention memory-driven transformers to generate text reports. Comprehensive experimentation was conducted to compare existing and proposed techniques based on Bilingual Evaluation Understudy (BLEU) scores ranging from 1 to 4. The model outperforms the other state-of-the-art techniques by increasing the BLEU 1 (0.475), BLEU 2 (0.358), BLEU 3 (0.229), and BLEU 4 (0.165) respectively. This study's findings can alleviate radiologists' workloads and enhance clinical workflows by introducing an autonomous radiological report generation system.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Computer Science, COMSATS University Islamabad, Islamabad, Pakistan.
- Department of Computer Science, COMSATS University Islamabad, Islamabad, Pakistan. tahir_mustafa@comsats.edu.pk.
- Rehabilitation Department, Yusra Medical and Dental College, Rawalpindi, Pakistan.
ORCID-Profile: Tahir Mustafa Madni
Förderung
- Higher Education Commision, Pakistan
Zitieren
APA
Shahzadi, I., Madni, T. M., Janjua, U. I., Batool, G., Naz, B., & Ali, M. Q. (2024). CSAMDT: Conditional Self Attention Memory-Driven Transformers for Radiology Report Generation from Chest X-Ray. Journal of Imaging Informatics in Medicine, 37(6), 2825-2837. https://doi.org/10.1007/s10278-024-01126-6
Vancouver
Shahzadi I, Madni TM, Janjua UI, Batool G, Naz B, Ali MQ. CSAMDT: Conditional Self Attention Memory-Driven Transformers for Radiology Report Generation from Chest X-Ray. Journal of Imaging Informatics in Medicine. 2024;37(6):2825-2837. doi:10.1007/s10278-024-01126-6
BibTeX
@article{Shahzadi2024,
author = {Shahzadi, Iqra and Madni, Tahir Mustafa and Janjua, Uzair Iqbal and Batool, Ghanwa and Naz, Bushra and Ali, Muhammad Qasim},
title = {CSAMDT: Conditional Self Attention Memory-Driven Transformers for Radiology Report Generation from Chest X-Ray},
journal = {Journal of Imaging Informatics in Medicine},
year = {2024},
volume = {37},
number = {6},
pages = {2825--2837},
doi = {10.1007/s10278-024-01126-6}
}
EUVIMED