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

Best practices and challenges in executing large scale pilots for eHealth deployment and managing innovation: the GATEKEEPER experience.

Frontiers in digital health·2026
Same author

The effect of dietetic counseling combined with digital tools intervention on hemodynamic markers in Greek adults: The GATEKEEPER Study.

Nutrition, metabolism, and cardiovascular diseases : NMCD·2026
Same author

A telemetry dataset on resource utilisation and power consumption in the edge-cloud continuum.

Data in brief·2026
Same author

Large Language Models for Cardiovascular Disease, Cancer, and Mental Disorders: A Review of Systematic Reviews.

Healthcare (Basel, Switzerland)·2026
Same author

Services for Connected, Cooperated, and Automated Mobility based on Big Data and Artificial Intelligence: The SHOW project paradigm.

Open research Europe·2025
Same author

Linguistic Markers in Spontaneous Speech: Insights into Subjective Cognitive Decline (Review).

Healthcare (Basel, Switzerland)·2025

Related Experiment Video

Updated: May 22, 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

2.6K

A Two-Stage Lightweight Deep Learning Framework for Mass Detection and Segmentation in Mammograms Using YOLOv5 and

Dimitris Manolakis1, Paschalis Bizopoulos2, Antonios Lalas2

  • 1Information Technologies Institute, Centre for Research & Technology- Hellas, 6th km Harilaou - Thermis, Thermi, 57001, Greece. manolakisd@iti.gr.

Journal of Imaging Informatics in Medicine
|March 15, 2025
PubMed
Summary
This summary is machine-generated.

This study introduces a novel, lightweight AI model for breast cancer segmentation that runs in a web browser, protecting patient privacy. The efficient two-stage model achieves high accuracy for mass detection and segmentation without data leaving the user's device.

Keywords:
Breast cancerDeep learningMedical imagingSegmentation

More Related Videos

Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

8.4K
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

449

Related Experiment Videos

Last Updated: May 22, 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

2.6K
Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

8.4K
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

449

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Computer Science

Background:

  • Medical data privacy is paramount in diagnostic imaging.
  • Accurate and efficient breast cancer segmentation is crucial for diagnosis and treatment planning.
  • Existing solutions often require data transfer, posing privacy risks.

Purpose of the Study:

  • To develop a privacy-preserving, lightweight AI solution for breast cancer segmentation.
  • To enable accurate medical image analysis directly within a user's browser.
  • To address the challenge of balancing computational efficiency with diagnostic performance.

Main Methods:

  • A two-stage AI model was developed, combining nano YoloV5 for mass detection and a lightweight neural network for segmentation.
  • The segmentation model utilizes SegNet architecture and depthwise separable convolutions for efficiency.
  • The solution is designed to operate entirely within the user's web browser, ensuring data privacy.

Main Results:

  • The detection model achieved mAP@50 scores of 50.3% on CBIS-DDSM and 68.2% on INbreast datasets.
  • The segmentation model demonstrated high performance with IoU scores of 81.0% (CBIS-DDSM) and 77.3% (INbreast).
  • The segmentation model achieved Dice scores of 89.4% (CBIS-DDSM) and 87.0% (INbreast) with an inference time of 21 ms per image.

Conclusions:

  • The proposed lightweight, browser-based AI model effectively performs breast cancer segmentation while ensuring strict medical data privacy.
  • The solution offers a significant advancement in efficient and secure medical image analysis.
  • This approach facilitates accurate breast cancer detection and segmentation without compromising patient confidentiality.