Enhancing Mammography Models: The Impact of Radiologist Recommendations on Algorithmic Precision

  • Youssef Lahdoudi MPA, ENSA Khouribga, Sultan Moulay Slimane University, BP 77,Beni Amir, Morocco
  • Abdelghani Ghazdali MPA, ENSA Khouribga, Sultan Moulay Slimane University, BP 77,Beni Amir, Morocco
  • Hamza Khalfi MPA, ENSA Khouribga, Sultan Moulay Slimane University, BP 77,Beni Amir, Morocco
  • Nidal Lamghari MPA, ENSA Khouribga, Sultan Moulay Slimane University, BP 77,Beni Amir, Morocco
DOI: https://doi.org/10.19139/soic-2310-5070-2014
Keywords: Breast Cancer, Machine learning in radiology, Medical image classification, Mammography, Radiology image classification

Abstract

This study highlights the benefits of advanced image classification in breast cancer diagnosis and treatment. We utilize deep learning algorithms like YOLOv5 for image segmentation and Densenet121 for feature extraction from segmented regions. Our dataset includes 54,706 mammography images for comprehensive analysis. We evaluate 100 challenging cases, ensuring a balanced representation of benign and malignant instances. Validation involves 50 consensus cases. To address the class imbalance, we employ Upsampling/Downsampling. We fine-tune 14 algorithms and compare outcomes with and without radiologists' recommendations. Results show a 99.8\% AUC during testing and 59.5\% during validation without radiologists' input, which improves to 99.9\% and 93.5\% respectively with their insights. Expert guidance significantly enhances diagnostic accuracy. The study explores the interplay between algorithmic precision, dataset characteristics, and expert recommendations in breast cancer diagnosis. It provides valuable insights for leveraging technology and expert knowledge for improved medical outcomes.
Published
2024-08-12
How to Cite
Lahdoudi, Y., Ghazdali, A., Khalfi, H., & Lamghari, N. (2024). Enhancing Mammography Models: The Impact of Radiologist Recommendations on Algorithmic Precision. Statistics, Optimization & Information Computing, 13(1), 434-449. https://doi.org/10.19139/soic-2310-5070-2014
Issue
Vol 13 No 1 (2025)
Section
Research Articles
Authors who publish with this journal agree to the following terms:

    1. Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
    2. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
    3. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).