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 Videos

Automatic intraductal breast carcinoma classification using a neural network-based recognition system.

A Reigosa¹, L Hernández, V Torrealba

¹Image Processing Center, University of Carabobo, Venezuela Anatomic Pathology Department, Oncological Institute "Dr. Miguel Perez Carreño;" Venezuela System Department, Technological Institute of Valencia, Venezuela Department of Pathology, Red Cross Hospital of Valencia, Valencia, Venezuela.

The Breast Journal

|January 13, 2011

Summary

This summary is machine-generated.

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

[Hip prostheses as a treatment for acetabular fractures in the elderly].

Acta ortopedica mexicana·2025

Same author

[Effectiveness of peripheral nerve blockade in pain management for patients undergoing anterior cruciate ligament reconstruction: a retrospective observational study].

Acta ortopedica mexicana·2025

Same author

Combined additive effects of neuronal membrane glycoprotein GPM6a and the intercellular cell adhesion molecule ICAM5 on neuronal morphogenesis.

Journal of neurochemistry·2024

Same author

Clinical evaluation of a new chemically-cured bulk-fill composite in posterior restorations: 6-month multicenter double-blind randomized clinical trial.

Journal of dentistry·2024

Same author

Tuning the conductance of carbon rings with impurities and electric fields.

RSC advances·2023

Same author

Recommendations for the coordination of Neurology and Neuroradiology Departments in the management of patients with multiple sclerosis.

Neurologia·2023

An automated system accurately classifies breast cancer grades from histologic images using cellular contours. This tool achieved 97.5% agreement with pathologists, aiding in cancer diagnosis.

Area of Science:

Digital pathology
Computational biology
Oncology

Background:

Accurate grading of intraductal breast carcinoma is crucial for treatment decisions.
Histologic image analysis presents challenges in objectivity and reproducibility.

Purpose of the Study:

To develop and validate an automated contour-based system for classifying intraductal breast carcinoma into high and low nuclear grades.
To assess the system's agreement with expert pathologist consensus.

Main Methods:

A contour-based automatic recognition system was developed using digitized histologic images.
Image features invariant to rotation and translation were extracted from cellular contours.
A multilayer perceptron network trained with error back propagation was employed for classification.

Related Experiment Videos

The system analyzed 40 cases and results were compared to pathologist consensus.

Main Results:

The system demonstrated high accuracy in classifying breast carcinoma nuclear grades.
Achieved 97.5% agreement with pathologist consensus (p < .00001).
Selected image discriminating characteristics were invariant to rotation and translation.

Conclusions:

The contour-based automatic recognition system is a reliable tool for classifying intraductal breast carcinoma nuclear grades.
This automated system shows potential to assist pathologists in definitive cancer diagnosis.
The system's high accuracy and agreement suggest its utility in digital pathology workflows.