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 Experiment Video

Updated: Dec 25, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

3.3K

Segmentation of Masses on Mammograms Using Data Augmentation and Deep Learning.

Felipe André Zeiser1, Cristiano André da Costa2, Tiago Zonta1,3

  • 1Software Innovation Laboratory - SOFTWARELAB, Applied Computing Graduate Program, Universidade do Vale do Rio dos Sinos - Unisinos, Av. Unisinos 950, São Leopoldo, 93022-000, Brazil.

Journal of Digital Imaging
|March 25, 2020
PubMed
Summary

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

FTDRL-HGSO: an efficient terrain-adaptive DRL-driven gait and path control framework for hexapod robots.

Scientific reports·2026
Same author

Higher Levels of <i>BRCA1</i> Gene Methylation in Sporadic Breast Cancer Patients with a Lower Incidence of Recurrence.

Medical sciences (Basel, Switzerland)·2026
Same author

MRNet: A Multi-Resolution Dual-Task Framework for Micrometastases Detection in Breast Cancer Sentinel Lymph Nodes.

Journal of imaging informatics in medicine·2026
Same author

Breast cancer patients present pro-tumor biomarkers related to purinergic signaling and oxidative stress.

Purinergic signalling·2025
Same author

Refining HER2-Negative breast cancer: distinct survival profiles of HER2-Low and HER2-Ultralow tumors.

Pathology, research and practice·2025
Same author

Clinical, histopathological and immunohistochemical analysis of vulvar squamous cell carcinoma.

Revista brasileira de ginecologia e obstetricia : revista da Federacao Brasileira das Sociedades de Ginecologia e Obstetricia·2024

This study introduces a U-Net based computer-aided detection (CAD) system for early breast cancer diagnosis from mammograms. The system achieved high accuracy, aiding specialists in identifying malignant lesions more effectively.

Area of Science:

  • Medical Imaging
  • Artificial Intelligence in Healthcare
  • Oncology

Background:

  • Early breast cancer diagnosis is crucial for effective treatment.
  • Mammography is a primary detection method, but breast density can obscure malignant lesions.
  • Computer-aided detection (CAD) systems can assist radiologists in mass identification.

Purpose of the Study:

  • To develop and evaluate a U-Net based CAD system for detecting masses in digitized mammograms.
  • To utilize a comprehensive dataset including normal, benign, and malignant cases for robust model training.
  • To enable specialists to monitor lesions over time with improved diagnostic support.

Main Methods:

  • A four-stage process involving pre-processing, data augmentation, U-Net model training, and performance testing.
Keywords:
Breast cancerComputer-aided detectionDeep learningFully convolutional networkSegmentationU-Net

Related Experiment Videos

Last Updated: Dec 25, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

3.3K
  • Utilized 7989 images from the Digital Database for Screening Mammography (DDSM).
  • Evaluated six U-Net model variations using metrics like accuracy, sensitivity, specificity, and Dice Index.

    • Main Results:

    • The best performing U-Net model achieved 92.32% sensitivity, 80.47% specificity, 85.95% accuracy, and a 79.39% Dice Index.
    • The system demonstrated effectiveness even when trained on a complete, unbiased dataset.
    • Area Under the Curve (AUC) reached 86.40%.

    Conclusions:

    • The developed CAD system shows significant potential in aiding the early diagnosis of breast cancer.
    • Using a complete mammogram database enhances the knowledge base for CAD systems.
    • The U-Net model provides a valuable tool for specialists in lesion monitoring and diagnosis.