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

Correction: Rehman et al. Fabrication, In Vitro and In Vivo Assessment of Eucalyptol-Loaded Nanoemulgel as a Novel Paradigm for Wound Healing. <i>Pharmaceutics</i> 2022, <i>14,</i> 1971.

Pharmaceutics·2025
Same author

Extracellular Vesicular miRNA in Pancreatic Cancer: From Lab to Therapy.

Cancers·2024
Same author

Fabrication, Characterization and Biomedical Evaluation of a Statistically Optimized Gelatin Scaffold Enriched with Co-Drugs Loaded into Controlled-Release Silica Nanoparticles.

Molecules (Basel, Switzerland)·2023
Same author

Deep Transfer Learning Technique for Multimodal Disease Classification in Plant Images.

Contrast media & molecular imaging·2023
Same author

Glaucoma Detection and Classification Using Improved U-Net Deep Learning Model.

Healthcare (Basel, Switzerland)·2022
Same author

Response Surface Methodology (RSM) Powered Formulation Development, Optimization and Evaluation of Thiolated Based Mucoadhesive Nanocrystals for Local Delivery of Simvastatin.

Polymers·2022

Related Experiment Video

Updated: Sep 4, 2025

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

Breast Cancer Detection on Histopathological Images Using a Composite Dilated Backbone Network.

Vinodkumar Mohanakurup1, Syam Machinathu Parambil Gangadharan2, Pallavi Goel3

  • 1Bell, Montreal, Canada.

Computational Intelligence and Neuroscience
|July 18, 2022
PubMed
Summary
This summary is machine-generated.

A novel Composite Dilated Backbone Network (CDBN) enhances breast cancer detection in histopathological images. This machine learning approach improves diagnostic accuracy by integrating multiple backbones for more robust feature identification.

More Related Videos

Tracking the Mammary Architectural Features and Detecting Breast Cancer with Magnetic Resonance Diffusion Tensor Imaging
15:48

Tracking the Mammary Architectural Features and Detecting Breast Cancer with Magnetic Resonance Diffusion Tensor Imaging

Published on: December 15, 2014

22.6K
Reconstruction of 3-Dimensional Histology Volume and its Application to Study Mouse Mammary Glands
10:59

Reconstruction of 3-Dimensional Histology Volume and its Application to Study Mouse Mammary Glands

Published on: July 26, 2014

14.5K

Related Experiment Videos

Last Updated: Sep 4, 2025

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
Tracking the Mammary Architectural Features and Detecting Breast Cancer with Magnetic Resonance Diffusion Tensor Imaging
15:48

Tracking the Mammary Architectural Features and Detecting Breast Cancer with Magnetic Resonance Diffusion Tensor Imaging

Published on: December 15, 2014

22.6K
Reconstruction of 3-Dimensional Histology Volume and its Application to Study Mouse Mammary Glands
10:59

Reconstruction of 3-Dimensional Histology Volume and its Application to Study Mouse Mammary Glands

Published on: July 26, 2014

14.5K

Area of Science:

  • Medical Imaging
  • Computer Vision
  • Machine Learning

Background:

  • Breast cancer diagnosis accuracy is critical due to high mortality rates.
  • Machine learning and deep learning show promise in improving diagnostic tools.
  • Current Convolutional Neural Network (CNN) detectors rely heavily on backbone network performance.

Purpose of the Study:

  • To introduce an innovative Composite Dilated Backbone Network (CDBN) for enhanced breast cancer detection.
  • To improve the performance of existing CNN-based object detectors.
  • To validate the effectiveness of CDBN on breast cancer histopathological images.

Main Methods:

  • Developed a Composite Dilated Backbone Network (CDBN) by integrating multiple identical backbones.
  • Employed a stepwise approach, feeding high-level features from previous backbones to subsequent ones.
  • Incorporated dilated convolution, ResNet, and Alexnet within the CDBN architecture.
  • Tested CDBN's integration with contemporary detectors, including cascade mask R-CNN.

Main Results:

  • Achieved mean Average Precision (mAP) improvements of 1.5% to 3.0% on the BreakHis dataset.
  • Demonstrated enhanced instance segmentation capabilities.
  • The baseline cascade mask R-CNN detector performance improved to mAP = 53.3 with CDBN integration.
  • CDBN does not require pretraining, creating high-level features from low-level elements.

Conclusions:

  • CDBN is an effective method for enhancing object detection and instance segmentation in medical images.
  • The proposed network offers a significant performance boost for CNN-based detectors without pretraining.
  • CDBN integration is a versatile approach to improve diagnostic accuracy in breast cancer analysis.