Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: Apr 24, 2026

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

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

Published on: November 30, 2022

A Novel Deep Learning Framework for Nipple Segmentation in Digital Mammography.

Marcos Rogozinski¹, Jan Hurtado^2,3, Cesar A Sierra-Franco^2,3

¹Department of Informatics, Pontifical Catholic University of Rio de Janeiro, Rio de Janeiro, RJ, Brazil. mrogozinski@inf.puc-rio.br.

Journal of Imaging Informatics in Medicine

|June 3, 2025

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

Deep Learning-Based Automated Reports for Breast Density Assessment in Mammography Images.

Journal of imaging informatics in medicine·2026

Same author

Enabling Autonomous Data Annotation in Mammography Image: A Human-in-the-Loop Reinforcement Learning Approach.

Journal of imaging informatics in medicine·2026

Same author

Is virtual reality always better than 2D videos? A head-to-head randomized controlled trial for fear of flying with long-term follow-up.

Psychiatry research·2025

Same author

Towards Automated Semantic Segmentation in Mammography Images for Enhanced Clinical Applications.

Journal of imaging informatics in medicine·2024

Same author

Segmentation of four-chamber view images in fetal ultrasound exams using a novel deep learning model ensemble method.

Computers in biology and medicine·2024

Same author

Real-time data analysis in health monitoring systems: A comprehensive systematic literature review.

Journal of biomedical informatics·2022

A new method significantly improves nipple segmentation in mammography, outperforming existing techniques, especially in difficult cases. This enhances medical image analysis and computer-aided detection systems.

Area of Science:

Medical Imaging
Computer Vision
Biomedical Engineering

Background:

Accurate nipple segmentation is crucial for medical analysis and computer-aided detection in digital mammography.
The nipple serves as a key anatomical landmark for multi-view and multi-modality breast image registration.
Precise nipple localization is vital for ensuring image quality and accurate anomaly registration across different mammographic views.

Purpose of the Study:

To introduce a novel methodology for enhancing nipple segmentation in digital mammography.
To improve the accuracy and robustness of nipple localization compared to existing methods.
To address challenges in segmentation posed by class imbalance and high object variability.

Main Methods:

Development of a novel segmentation methodology for digital mammography.

Keywords:

Deep learning Ensemble learning Image segmentation Mammography image Object detection

More Related Videos

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

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

Published on: August 30, 2013

Related Experiment Videos

Last Updated: Apr 24, 2026

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

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

Published on: November 30, 2022

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

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

Published on: August 30, 2013

Evaluation of the proposed approach against baseline methods on challenging cases.

Quantitative assessment using metrics such as mean Intersection over Union (mIoU) and Hausdorff distance.

Main Results:

The novel approach achieved successful nipple detection in all tested cases.
A mean Intersection over Union (mIoU) of 0.63 was reached in cases where baseline methods failed.
Significant improvements were observed, including a tenfold increase in Hausdorff distance and enhanced mIoU in both craniocaudal (CC) and mediolateral oblique (MLO) views.

Conclusions:

The proposed methodology offers a substantial advancement in nipple segmentation for digital mammography.
The technique demonstrates superior performance, particularly in challenging segmentation scenarios.
The generalizability of the approach suggests potential applications in other breast imaging modalities and related fields.