Jove
Visualize
Contact Us

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

A methodology for developing dermatological datasets: lessons from retrospective data collection for AI-based applications.

BMC medical research methodology·2025
Same author

TECRR: a benchmark dataset of radiological reports for BI-RADS classification with machine learning, deep learning, and large language model baselines.

BMC medical informatics and decision making·2024
Same author

Exploring the intersection of obesity and gender in COVID-19 outcomes in hospitalized Mexican patients: a comparative analysis of risk profiles using unsupervised machine learning.

Frontiers in public health·2024
Same author

Breast cancer risk prediction using machine learning: a systematic review.

Frontiers in oncology·2024
Same author

Deep learning, radiomics and radiogenomics applications in the digital breast tomosynthesis: a systematic review.

BMC bioinformatics·2023
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: Jul 15, 2025

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

1.9K

Hybrid morphological-convolutional neural networks for computer-aided diagnosis.

Martha Rebeca Canales-Fiscal1, José Gerardo Tamez-Peña2

  • 1Tecnológico de Monterrey, Escuela de Ingeniería y Ciencias, Monterrey, NL, Mexico.

Frontiers in Artificial Intelligence
|October 5, 2023
PubMed
Summary

A novel Morphological and Convolutional Neural Network (MCNN) with Random Forest classification effectively handles limited medical image data. This hybrid approach shows promise for accurate classification in datasets with few samples.

Keywords:
computer-aided diagnosisdeep learningmathematical morphologymedical image classificationmedical image datasets

More Related Videos

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
08:20

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

1.5K
Digital Hybrid Model Preparation for Virtual Planning of Reconstructive Dentoalveolar Surgical Procedures
09:10

Digital Hybrid Model Preparation for Virtual Planning of Reconstructive Dentoalveolar Surgical Procedures

Published on: August 5, 2021

1.8K

Related Experiment Videos

Last Updated: Jul 15, 2025

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

1.9K
Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
08:20

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

1.5K
Digital Hybrid Model Preparation for Virtual Planning of Reconstructive Dentoalveolar Surgical Procedures
09:10

Digital Hybrid Model Preparation for Virtual Planning of Reconstructive Dentoalveolar Surgical Procedures

Published on: August 5, 2021

1.8K

Area of Science:

  • Computer Science
  • Medical Imaging
  • Machine Learning

Background:

  • Deep Convolutional Neural Networks (CNNs) face memory and computational challenges, requiring extensive data.
  • Medical image datasets are often scarce due to acquisition and curation complexities.
  • Overfitting and poor generalization are common issues with deep learning on limited medical data.

Purpose of the Study:

  • To propose a compact, hybrid machine learning architecture (MCNN + Random Forest) for medical image classification with limited data.
  • To evaluate the MCNN's performance against popular deep CNNs (ResNet-18, ShuffleNet-V2, MobileNet-V2) using full training and transfer learning.
  • To assess the potential of mathematical morphology in shallow neural networks for medical image analysis.

Main Methods:

  • Developed a Morphological and Convolutional Neural Network (MCNN) integrating morphological operations and independent channel processing.
  • Utilized a Random Forest classifier on the MCNN's output for final classification.
  • Compared MCNN performance with ResNet-18, ShuffleNet-V2, and MobileNet-V2 on ISIC (melanoma) and ORIGA (glaucoma) datasets.

Main Results:

  • MCNN achieved an AUC of 0.94 for melanoma classification, outperforming deep CNNs.
  • MCNN performance on glaucoma classification (AUC 0.65) was comparable to deep CNNs.
  • The MCNN demonstrated reliable performance with limited medical image samples.

Conclusions:

  • Hybrid MCNN architectures show potential for effective learning from small medical image datasets.
  • Mathematical morphology integrated into shallow neural networks can enhance medical image classification.
  • The proposed MCNN offers a viable alternative to deep learning for data-scarce medical imaging applications.