EUVIMEDEUVIMED entdecken
Crossref

Improved breast ultrasound tumor classification using dual-input CNN with GAP-guided attention loss

Xiao Zou, Jintao Zhai, Shengyou Qian, Ang Li, Feng Tian, Xiaofei Cao, Runmin Wang

Mathematical Biosciences and Engineering · 2023

DOI: 10.3934/mbe.2023682 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Mathematical Biosciences and Engineering, 2023. Verfasst von Xiao Zou und 6 weiteren Autor:innen. Beteiligte Einrichtung: School of Physics and Electronics, Hunan Normal University, Changsha 410081, China. Hauptthemen laut MEDLINE: Ultrasonography, Mammary, Neoplasms. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 59 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Ultrasonography is a widely used medical imaging technique for detecting breast cancer. While manual diagnostic methods are subject to variability and time-consuming, computer-aided diagnostic (CAD) methods have proven to be more efficient. However, current CAD approaches neglect the impact of noise and artifacts on the accuracy of image analysis. To enhance the precision of breast ultrasound image analysis for identifying tissues, organs and lesions, we propose a novel approach for improved tumor classification through a dual-input model and global average pooling (GAP)-guided attention loss function. Our approach leverages a convolutional neural network with transformer architecture and modifies the single-input model for dual-input. This technique employs a fusion module and GAP operation-guided attention loss function simultaneously to supervise the extraction of effective features from the target region and mitigate the effect of information loss or redundancy on misclassification. Our proposed method has three key features: (i) ResNet and MobileViT are combined to enhance local and global information extraction. In addition, a dual-input channel is designed to include both attention images and original breast ultrasound images, mitigating the impact of noise and artifacts in ultrasound images. (ii) A fusion module and GAP operation-guided attention loss function are proposed to improve the fusion of dual-channel feature information, as well as supervise and constrain the weight of the attention mechanism on the fused focus region. (iii) Using the collected uterine fibroid ultrasound dataset to train ResNet18 and load the pre-trained weights, our experiments on the BUSI and BUSC public datasets demonstrate that the proposed method outperforms some state-of-the-art methods. The code will be publicly released at https://github.com/425877/Improved-Breast-Ultrasound-Tumor-Classification.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Ultrasonography, MammaryNeoplasmsFemaleHumansArtifactsElectric Power SuppliesImage Processing, Computer-Assisted

Stichwörter der Autor:innen

breast ultrasound tumorclassificationconvolutional neural networkfeature fusionultrasound image

Autor:innen und Institutionen

  • School of Physics and Electronics, Hunan Normal University, Changsha 410081, China.
  • College of Information Science and Engineering, Hunan Normal University, Changsha 410081, China.

Zitieren

APA

Zou, X., Zhai, J., Qian, S., Li, A., Tian, F., Cao, X., & Wang, R. (2023). Improved breast ultrasound tumor classification using dual-input CNN with GAP-guided attention loss. Mathematical Biosciences and Engineering. https://doi.org/10.3934/mbe.2023682

Vancouver

Zou X, Zhai J, Qian S, Li A, Tian F, Cao X, et al. Improved breast ultrasound tumor classification using dual-input CNN with GAP-guided attention loss. Mathematical Biosciences and Engineering. 2023. doi:10.3934/mbe.2023682

BibTeX
@article{Zou2023,
  author = {Zou, Xiao and Zhai, Jintao and Qian, Shengyou and Li, Ang and Tian, Feng and Cao, Xiaofei and Wang, Runmin},
  title = {Improved breast ultrasound tumor classification using dual-input CNN with GAP-guided attention loss},
  journal = {Mathematical Biosciences and Engineering},
  year = {2023},
  doi = {10.3934/mbe.2023682}
}
Kostenlos starten →