• Home
  • Search
  • Improving Performance of Breast Lesion Classification Using a ResNet50 Model Optimized with a Novel Attention Mechanism
  • Cite Icon54
  • https://doi.org/10.3390/tomography8050200Copy DOI Icon

Improving Performance of Breast Lesion Classification Using a ResNet50 Model Optimized with a Novel Attention Mechanism

Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Background: The accurate classification between malignant and benign breast lesions detected on mammograms is a crucial but difficult challenge for reducing false-positive recall rates and improving the efficacy of breast cancer screening. Objective: This study aims to optimize a new deep transfer learning model by implementing a novel attention mechanism in order to improve the accuracy of breast lesion classification. Methods: ResNet50 is selected as the base model to develop a new deep transfer learning model. To enhance the accuracy of breast lesion classification, we propose adding a convolutional block attention module (CBAM) to the standard ResNet50 model and optimizing a new model for this task. We assembled a large dataset with 4280 mammograms depicting suspicious soft-tissue mass-type lesions. A region of interest (ROI) is extracted from each image based on lesion center. Among them, 2480 and 1800 ROIs depict verified benign and malignant lesions, respectively. The image dataset is randomly split into two subsets with a ratio of 9:1 five times to train and test two ResNet50 models with and without using CBAM. Results: Using the area under ROC curve (AUC) as an evaluation index, the new CBAM-based ResNet50 model yields AUC = 0.866 ± 0.015, which is significantly higher than that obtained by the standard ResNet50 model (AUC = 0.772 ± 0.008) (p < 0.01). Conclusion: This study demonstrates that although deep transfer learning technology attracted broad research interest in medical-imaging informatic fields, adding a new attention mechanism to optimize deep transfer learning models for specific application tasks can play an important role in further improving model performances.

Similar Papers
  • Research Article
  • Citations1

Discrimination of benign and malignant breast lesions on dynamic contrast-enhanced magnetic resonance imaging using deep learning.

  • Dec 01, 2023
  • Journal of cancer research and therapeutics
  • Ming Zhang +5
  • Research Article

Enhancing Early Tuberculosis Detection Using CGAN Augmentation and Deep Transfer Learning Models

  • Nov 28, 2025
  • International Journal of Data Science and Analysis
  • Teresia Kamau +3
  • Research Article
  • Citations11

Multimodal deep transfer learning to predict retinal vein occlusion macular edema recurrence after anti-VEGF therapy

  • Apr 01, 2024
  • Heliyon
  • Laihe Zhang +5
  • Research Article

Brain-tumor Classification Using ResNet50 Enhanced with SE and CBAM Attention Mechanisms

  • Jan 01, 2026
  • Jordanian Journal of Computers and Information Technology
  • Nadia Shamsulddin Abdulsattar +1
  • Research Article
  • Citations43

Attention-based deep learning for breast lesions classification on contrast enhanced spectral mammography: a multicentre study.

  • Dec 15, 2022
  • British Journal of Cancer
  • Ning Mao +10
  • PDF
  • Research Article
  • Citations3

Deep Learning-Assisted Efficient Staging of SARS-CoV-2 Lesions Using Lung CT Slices

  • Oct 19, 2022
  • Mathematical Problems in Engineering
  • S Arockia Sukanya +1
  • Research Article
  • Citations46

A Study of the Neutrosophic Set Significance on Deep Transfer Learning Models: an Experimental Case on a Limited COVID-19 Chest X-ray Dataset

  • Jan 04, 2021
  • Cognitive Computation
  • Nour Eldeen M Khalifa +3
  • PDF
  • Research Article
  • Citations19

A hybrid CNN and ensemble model for COVID-19 lung infection detection on chest CT scans.

  • Mar 09, 2023
  • PLOS ONE
  • Ahmed A Akl +3
  • PDF
  • Research Article

Variational quantum enhanced deep transfer learning for small underwater aqua species image classification

  • Nov 04, 2025
  • Scientific Reports
  • Sugunapriya A +1
  • Research Article

Retrospective Development of an AI Model Combining Ultrasound and Clinical Data for Pediatric Appendicitis Differentiation

  • Jan 01, 2025
  • Emergency Medicine International
  • Rongying Tan +9
  • PDF
  • Research Article
  • Citations4

ONDL: An optimized Neutrosophic Deep Learning model for classifying waste for sustainability

  • Nov 08, 2024
  • PLOS ONE
  • Nour Eldeen Mahmoud Khalifa +3
  • PDF
  • Research Article
  • Citations2

Enhanced Sequence-to-Sequence Deep Transfer Learning for Day-Ahead Electricity Load Forecasting

  • May 20, 2024
  • Electronics
  • Vasileios Laitsos +4
  • Research Article
  • Citations9

Analysis of Deep Transfer Learning Methods for Early Diagnosis of the Covid-19 Disease with Chest X-ray Images

  • Apr 30, 2022
  • Düzce Üniversitesi Bilim ve Teknoloji Dergisi
  • Durmuş Özdemi̇r +1
  • PDF
  • Research Article
  • Citations3

A lightweight Deeplab V3+ network integrating deep transitive transfer learning and attention mechanism for burned area identification

  • May 07, 2025
  • Scientific Reports
  • Lizhi Liu +7
  • Research Article
  • Citations12

Early diagnosis of COVID-19 patients using deep learning-based deep forest model

  • Jan 07, 2022
  • Journal of Experimental &amp; Theoretical Artificial Intelligence
  • Dilbag Singh +3
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.