Related Experiment Video
Updated: May 29, 2025
07:15
Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
Published on: August 16, 2020
6.7K
Breast cancer classification based on hybrid CNN with LSTM model.
Mourad Kaddes1, Yasser M Ayid2, Ahmed M Elshewey3
1Department of Information Systems, College of Computing & Information Technology at Khulais, University of Jeddah, Jeddah, Saudi Arabia.
Scientific Reports
|February 5, 2025
Summary
This study introduces a hybrid deep learning model (CNN-LSTM) for faster and more accurate breast cancer detection. The model significantly improves classification performance, aiding early diagnosis and treatment.
Area of Science:
- Medical Imaging
- Artificial Intelligence
- Oncology
Background:
- Breast cancer (BC) poses a global health challenge, exacerbated by limitations in early detection and knowledge dissemination.
- Medical image analysis and computer-aided diagnosis, particularly using deep learning (DL), are vital for enhancing cancer detection and classification accuracy.
- Accurate and rapid breast cancer diagnosis is critical for effective treatment planning and improved patient outcomes.
Purpose of the Study:
- To develop and evaluate a novel hybrid deep learning model for binary breast cancer classification.
- To enhance the accuracy and resilience of breast cancer detection by combining Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) architectures.
- To compare the performance of the proposed hybrid model against established DL models for breast cancer classification.
Main Methods:
- A hybrid deep learning model integrating CNN for feature extraction and LSTM for sequential analysis was developed.
- The model was trained and validated on two publicly available breast cancer datasets from Kaggle.
- Performance was evaluated using metrics including accuracy, sensitivity, specificity, F-score, and Area Under the Curve (AUC), and compared against CNN, LSTM, GRUs, VGG-16, and RESNET-50.
Main Results:
- The proposed CNN-LSTM hybrid model achieved high classification accuracies of 99.17% and 99.90% on the two datasets.
- The model demonstrated superior performance compared to individual DL models (CNN, LSTM, GRUs) and established architectures (VGG-16, RESNET-50).
- Key performance metrics confirmed the model's effectiveness in accurately classifying breast cancer.
Conclusions:
- The hybrid CNN-LSTM model offers a significant advancement in automated breast cancer detection and classification.
- This approach enhances diagnostic accuracy and efficiency, supporting clinicians in early cancer identification.
- The findings highlight the potential of integrated deep learning architectures for improving breast cancer screening and management.
