Related Experiment Video
Updated: Jun 5, 2025
07:15
Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
Published on: August 16, 2020
6.7K
An approach for classification of breast cancer using lightweight deep convolution neural network
Ahmed Elaraby1, Aymen Saad2, Hela Elmannai3
1Department of Computer Science, Faculty of Computers and Information, South Valley University, Qena, 83523, Egypt.
Heliyon
|December 6, 2024
Summary
Deep learning algorithms can now precisely identify breast cancers on mammograms. This automated feature extraction method shows promise for improving diagnostic accuracy and reducing errors in breast cancer screening.
Area of Science:
- Medical Imaging
- Artificial Intelligence
- Oncology
Background:
- Machine learning (ML) aids radiologists in breast cancer (BC) diagnosis, but traditional methods require time-consuming feature extraction.
- Deep learning (DL) offers automated feature extraction for improved efficiency and accuracy in medical imaging analysis.
Purpose of the Study:
- To develop and evaluate a deep learning algorithm for precise breast cancer identification on screening mammograms.
- To assess the effectiveness of a Lightweight Convolutional Neural Network (LWCNN) for end-to-end feature extraction and classification.
Main Methods:
- Utilized a Lightweight Convolutional Neural Network (LWCNN) for automatic feature extraction in an end-to-end manner.
- Trained and tested the LWCNN model on mammography datasets with full clinical annotation and image-level cancer status.
- Conducted two experiments using original and enhanced datasets to evaluate model performance.
Main Results:
- The LWCNN model achieved high training and testing accuracies, reaching up to 99% in both experiments.
- Experiment 1: 95% training, 93% testing accuracy (Dataset 1).
- Experiment 2: 95% training, 91% testing accuracy (Dataset 2).
Conclusions:
- Deep learning techniques, specifically LWCNN, can be effectively trained for remarkable accuracy in mammography datasets.
- The proposed automated approach shows significant promise for enhancing clinical tools in breast cancer screening.
- This method has the potential to reduce both false positive and false negative outcomes in mammography interpretation.
