COMFormer: Classification of Maternal–Fetal and Brain Anatomy Using a Residual Cross-Covariance Attention Guided Transformer in Ultrasound
IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control · 2023-11 · 70 (11) · 1417-1427
DOI: 10.1109/tuffc.2023.3311879 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control, 2023-11. Verfasst von Md Mostafa Kamal Sarker und 5 weiteren Autor:innen. Hauptthemen laut MEDLINE: Brain, Ultrasonography, Prenatal. Die Arbeit wurde bisher 23-mal zitiert (Crossref) und nennt 42 Literaturangaben. Gefördert von: InnoHK-Funded Hong Kong Center for Cerebro-Cardiovascular Health Engineering (COCHE) Project 2.1.
Abstract (Originalsprache)
Monitoring the healthy development of a fetus requires accurate and timely identification of different maternal-fetal structures as they grow. To facilitate this objective in an automated fashion, we propose a deep-learning-based image classification architecture called the COMFormer to classify maternal-fetal and brain anatomical structures present in 2-D fetal ultrasound (US) images. The proposed architecture classifies the two subcategories separately: maternal-fetal (abdomen, brain, femur, thorax, mother's cervix (MC), and others) and brain anatomical structures [trans-thalamic (TT), trans-cerebellum (TC), trans-ventricular (TV), and non-brain (NB)]. Our proposed architecture relies on a transformer-based approach that leverages spatial and global features using a newly designed residual cross-variance attention block. This block introduces an advanced cross-covariance attention (XCA) mechanism to capture a long-range representation from the input using spatial (e.g., shape, texture, intensity) and global features. To build COMFormer, we used a large publicly available dataset (BCNatal) consisting of 12 400 images from 1792 subjects. Experimental results prove that COMFormer outperforms the recent CNN and transformer-based models by achieving 95.64% and 96.33% classification accuracy on maternal-fetal and brain anatomy, respectively.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Förderung
- InnoHK-Funded Hong Kong Center for Cerebro-Cardiovascular Health Engineering (COCHE) Project 2.1
Zitieren
APA
Sarker, M. M. K., Singh, V. K., Alsharid, M., Hernandez-Cruz, N., Papageorghiou, A. T., & Noble, J. A. (2023). COMFormer: Classification of Maternal–Fetal and Brain Anatomy Using a Residual Cross-Covariance Attention Guided Transformer in Ultrasound. IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control, 70(11), 1417-1427. https://doi.org/10.1109/tuffc.2023.3311879
Vancouver
Sarker MMK, Singh VK, Alsharid M, Hernandez-Cruz N, Papageorghiou AT, Noble JA. COMFormer: Classification of Maternal–Fetal and Brain Anatomy Using a Residual Cross-Covariance Attention Guided Transformer in Ultrasound. IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control. 2023;70(11):1417-1427. doi:10.1109/tuffc.2023.3311879
BibTeX
@article{Sarker2023,
author = {Sarker, Md Mostafa Kamal and Singh, Vivek Kumar and Alsharid, Mohammad and Hernandez-Cruz, Netzahualcoyotl and Papageorghiou, Aris T and Noble, J Alison},
title = {COMFormer: Classification of Maternal–Fetal and Brain Anatomy Using a Residual Cross-Covariance Attention Guided Transformer in Ultrasound},
journal = {IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control},
year = {2023},
volume = {70},
number = {11},
pages = {1417--1427},
doi = {10.1109/tuffc.2023.3311879}
}
EUVIMED