EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

MammoViT: A Custom Vision Transformer Architecture for Accurate BIRADS Classification in Mammogram Analysis

Abdullah G M Al Mansour iD, Faisal Alshomrani iD, Abdullah Alfahaid iD, Abdulaziz T M Almutairi iD

Diagnostics · 25.01.2025 · 15 (3) · 285

DOI: 10.3390/diagnostics15030285 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Diagnostics, online erschienen am 25.01.2025. Verfasst von Abdullah G M Al Mansour und 3 weiteren Autor:innen. Beteiligte Einrichtung: Radiology and Medical Imaging Department, College of Applied Medical Sciences, Prince Sattam Bin Abdulaziz University, Alkharj 11942, Saudi Arabia. Die Arbeit wurde bisher 28-mal zitiert (Crossref) und nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Prince Sattam bin Abdulaziz University.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Breast cancer screening through mammography interpretation is crucial for early detection and improved patient outcomes. However, the manual classification of mammograms using the BIRADS (Breast Imaging-Reporting and Data System) remains challenging due to subtle imaging features, inter-reader variability, and increasing radiologist workload. Traditional computer-aided detection systems often struggle with complex feature extraction and contextual understanding of mammographic abnormalities. To address these limitations, this study proposes MammoViT, a novel hybrid deep learning framework that leverages both ResNet50’s hierarchical feature extraction capabilities and Vision Transformer’s ability to capture long-range dependencies in images.

Methods

We implemented a multi-stage approach utilizing a pre-trained ResNet50 model for initial feature extraction from mammogram images. To address the significant class imbalance in our four-class BIRADS dataset, we applied SMOTE (Synthetic Minority Over-sampling Technique) to generate synthetic samples for minority classes. The extracted feature arrays were transformed into non-overlapping patches with positional encodings for Vision Transformer processing. The Vision Transformer employs multi-head self-attention mechanisms to capture both local and global relationships between image patches, with each attention head learning different aspects of spatial dependencies. The model was optimized using Keras Tuner and trained using 5-fold cross-validation with early stopping to prevent overfitting.

Results

MammoViT achieved 97.4% accuracy in classifying mammogram images across different BIRADS categories. The model’s effectiveness was validated through comprehensive evaluation metrics, including a classification report, confusion matrix, probability distribution, and comparison with existing studies.

Conclusions

MammoViT effectively combines ResNet50 and Vision Transformer architectures while addressing the challenge of imbalanced medical imaging datasets. The high accuracy and robust performance demonstrate its potential as a reliable tool for supporting clinical decision-making in breast cancer screening.

Schlagwörter

Stichwörter der Autor:innen

BIRADS classificationResNet50SMOTEVision Transformerbreast cancer detectiondeep learningmammogram analysismedical imaging

Autor:innen und Institutionen

  • Radiology and Medical Imaging Department, College of Applied Medical Sciences, Prince Sattam Bin Abdulaziz University, Alkharj 11942, Saudi Arabia.
  • Department of Diagnostic Radiology Technology, College of Applied Medical Science, Taibah University, Medinah 42353, Saudi Arabia.
  • College of Computer Science and Engineering, Taibah University, Yanbu 46421, Saudi Arabia.
  • Department of Computer, College of Science and Humanities, Shaqra University, Shaqra 11961, Saudi Arabia.

ORCID-Profile: Abdullah G M Al Mansour, Faisal Alshomrani, Abdullah Alfahaid, Abdulaziz T M Almutairi

Förderung

  • Prince Sattam bin Abdulaziz University

Zitieren

APA

Al Mansour, A. G. M., Alshomrani, F., Alfahaid, A., & Almutairi, A. T. M. (2025). MammoViT: A Custom Vision Transformer Architecture for Accurate BIRADS Classification in Mammogram Analysis. Diagnostics, 15(3), 285. https://doi.org/10.3390/diagnostics15030285

Vancouver

Al Mansour AGM, Alshomrani F, Alfahaid A, Almutairi ATM. MammoViT: A Custom Vision Transformer Architecture for Accurate BIRADS Classification in Mammogram Analysis. Diagnostics. 2025;15(3):285. doi:10.3390/diagnostics15030285

BibTeX
@article{AlMansour2025,
  author = {Al Mansour, Abdullah G M and Alshomrani, Faisal and Alfahaid, Abdullah and Almutairi, Abdulaziz T M},
  title = {MammoViT: A Custom Vision Transformer Architecture for Accurate BIRADS Classification in Mammogram Analysis},
  journal = {Diagnostics},
  year = {2025},
  volume = {15},
  number = {3},
  pages = {285},
  doi = {10.3390/diagnostics15030285}
}
Kostenlos starten →