EUVIMEDEUVIMED entdecken
Crossref

A deep learning framework for accurate mammographic mass classification using local context attention module

Ibrahim Abdelhalim, Yassir Almalki, Abdelrahman Abdallah, Rasha Karam, Sharifa Alduraibi, Mohammad Basha, Hassan Mohamed, Mohammed Ghazal, Ali Mahmoud, Norah Saleh Alghamdi, Sohail Contractor, Ayman El-Baz

Medical Physics · 2025

DOI: 10.1002/mp.18119 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Medical Physics, 2025. Verfasst von Ibrahim Abdelhalim und 11 weiteren Autor:innen. Beteiligte Einrichtung: Department of Bioengineering, University of Louisville, Louisville, USA. Hauptthemen laut MEDLINE: Deep Learning, Mammography, Breast Neoplasms, Image Interpretation, Computer-Assisted. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 43 Literaturangaben. Gefördert von: Qassim Health Cluster, Princess Nourah Bint Abdulrahman University.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Dense breast tissue significantly increases breast cancer (BC) risk. However, current mammographic methods for classifying BC are often subjective and unreliable, which complicates the task of accurate evaluation.

Purpose

This study introduces a deep learning method with a local context attention module (LCAM), using dual mammogram views aligned with BI‐RADS to enhance grading consistency and accuracy in BC classification across four groups by leveraging local context around masses.

Methods

Specific regions of interest (ROIs) containing dense tissue around breast masses are identified from dual mammogram views, providing additional insights for predicting BC BI‐RADS categories. These ROIs are then input into a convolutional neural network (CNN)‐based model, which is crucial for selecting and differentiating radiomic features associated with BI‐RADS. To enhance our model's ability to distinguish salient radiomic features associated with mass malignancy, the LCAM sequentially infers attention maps along two separate dimensions: channel and spatial. These attention maps are subsequently multiplied with the input feature map for adaptive feature refinement.

Results

Examining 3020 patients across four BI‐RADS categories while leveraging dual mammogram views demonstrates the robust performance of the proposed framework, achieving a sensitivity of 82.46% and a specificity of 91.42% in identifying BI‐RADS grading relevant to breast masses.

Conclusions

We introduced a novel CNN‐based framework that utilizes dual mammogram views for the BC classification. It utilizes LCAM, which further understands the local characteristics surrounding breast masses, aiming to enhance the accuracy and consistency of classification outcomes.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningMammographyBreast NeoplasmsImage Interpretation, Computer-AssistedBreast DensityHumansFemaleConvolutional Neural NetworksRadiomicsSensitivity and SpecificityAdultMiddle Aged

Stichwörter der Autor:innen

BI‐RADSbreast cancerdeep learningmammogrammass malignancy

Autor:innen und Institutionen

  • Department of Bioengineering, University of Louisville, Louisville, USA.
  • Department of Internal Medicine, Najran University, Najran, Saudi Arabia.
  • Department of Medical Imaging, McMaster University, Hamilton, Canada.
  • Department of Information Technology, Assiut University, Assiut, Egypt.
  • Department of Radiology, Mansoura University, Mansoura, Egypt.
  • Department of Radiology, Qassim University, Buraidah, Saudi Arabia.

Förderung

  • Qassim Health Cluster
  • Princess Nourah Bint Abdulrahman University

Zitieren

APA

Abdelhalim, I., Almalki, Y., Abdallah, A., Karam, R., Alduraibi, S., Basha, M., Mohamed, H., Ghazal, M., Mahmoud, A., Alghamdi, N. S., Contractor, S., & El-Baz, A. (2025). A deep learning framework for accurate mammographic mass classification using local context attention module. Medical Physics. https://doi.org/10.1002/mp.18119

Vancouver

Abdelhalim I, Almalki Y, Abdallah A, Karam R, Alduraibi S, Basha M, et al. A deep learning framework for accurate mammographic mass classification using local context attention module. Medical Physics. 2025. doi:10.1002/mp.18119

BibTeX
@article{Abdelhalim2025,
  author = {Abdelhalim, Ibrahim and Almalki, Yassir and Abdallah, Abdelrahman and Karam, Rasha and Alduraibi, Sharifa and Basha, Mohammad and Mohamed, Hassan and Ghazal, Mohammed and Mahmoud, Ali and Alghamdi, Norah Saleh and Contractor, Sohail and El-Baz, Ayman},
  title = {A deep learning framework for accurate mammographic mass classification using local context attention module},
  journal = {Medical Physics},
  year = {2025},
  doi = {10.1002/mp.18119}
}
Kostenlos starten →