Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Pulmonary embolism mortality in the United States: a nationwide analysis.

Journal of thrombosis and thrombolysis·2026
Same author

Pulse Steroid Therapy in a Patient With Refractory Rhabdomyolysis of Unknown Etiology: A Case Report.

Clinical case reports·2026
Same author

Ventricular Tachycardia Ablation Outcomes in Patients With Previous Implantable Cardioverter-Defibrillator Insertion: A Multicenter Cohort Study.

Journal of cardiovascular electrophysiology·2026
Same author

Nationwide patterns of cardiac-related mortality in amyloidosis cases: an epidemiologic study.

BMC cardiovascular disorders·2025
Same author

Aortic dissection mortality in the United States, 1968-2023: Trends, disparities, and deep learning forecasts.

International journal of cardiology. Cardiovascular risk and prevention·2025
Same author

Efficient Vision Transformers for Ophthalmic Images Classification: A Comparative Study of Supervised, Semi-Supervised, and Unsupervised Learning Approaches.

Journal of medical systems·2025

Related Experiment Video

Updated: Aug 9, 2025

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

1.9K

Transfer learning with different modified convolutional neural network models for classifying digital mammograms

Mohammed Tareq Mutar1, Mustafa Majid1, Mazin Judy Ibrahim2

  • 1Medical doctors, lectures at College of Medicine, University of Baghdad.

The Gulf Journal of Oncology
|February 21, 2023
PubMed
Summary

Artificial intelligence (AI) models show promise in breast cancer detection from mammograms. The NASNetLarge model achieved high accuracy, offering a fast and efficient screening tool to aid radiologists.

Keywords:
Artificial intelligenceBreast CancerTransfer learning Mammogram.

More Related Videos

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

6.9K
Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns
13:44

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Published on: August 30, 2013

43.0K

Related Experiment Videos

Last Updated: Aug 9, 2025

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

1.9K
Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

6.9K
Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns
13:44

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Published on: August 30, 2013

43.0K

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Oncology

Background:

  • Breast cancer remains a leading cause of cancer mortality globally.
  • Artificial intelligence (AI) is increasingly explored for enhancing breast cancer detection in radiological and cytological analyses.
  • AI demonstrates potential in classifying breast cancer, either independently or in conjunction with radiologist assessments.

Purpose of the Study:

  • To evaluate the performance and accuracy of various machine learning algorithms for diagnostic mammogram interpretation.
  • To assess AI models using a local four-field digital mammogram dataset.

Main Methods:

  • Utilized a dataset of 383 full-field digital mammograms from an oncology hospital, with images labeled by an experienced radiologist.
  • Applied image processing techniques including contrast enhancement (CLAHE) and data augmentation (flipping, rotation).
  • Employed transfer learning with fine-tuning on models pre-trained on the ImageNet dataset, using Python and the Keras library for analysis.

Main Results:

  • The NASNetLarge model achieved the highest performance with an accuracy of 0.8475 and an Area Under the Curve (AUC) of 0.8956.
  • DenseNet169 and InceptionResNetV2 models showed the lowest performance, with an accuracy of 0.72.
  • The analysis demonstrated a rapid processing time, with the longest duration for analyzing one hundred images being seven seconds.

Conclusions:

  • This study introduces a novel strategy for AI-assisted diagnostic and screening mammography through transfer learning and fine-tuning.
  • The implemented AI models offer acceptable performance and high speed, potentially alleviating workload in screening units.