Related Experiment Video
Updated: Sep 5, 2025
15:48
Tracking the Mammary Architectural Features and Detecting Breast Cancer with Magnetic Resonance Diffusion Tensor Imaging
Published on: December 15, 2014
22.6K
Intelligent breast cancer diagnostic system empowered by deep extreme gradient descent optimization
Muhammad Bilal Shoaib Khan1, Atta-Ur Rahman2, Muhammad Saqib Nawaz3
1Department of Information Technology, Akhuwat College University, Lahore 54000, Pakistan.
Mathematical Biosciences and Engineering : MBE
|July 8, 2022
Summary
This study introduces a novel deep learning model using deep extreme gradient descent optimization (DEGDO) for accurate breast cancer prediction. The model achieved high accuracy, demonstrating its potential for improved early detection and diagnosis.
Area of Science:
- Oncology
- Computer Science
- Artificial Intelligence
Background:
- Breast cancer is a prevalent global health concern, necessitating advanced diagnostic tools.
- Machine learning (ML) offers powerful methods for pattern recognition in medical datasets.
- Early and accurate detection significantly improves patient outcomes.
Purpose of the Study:
- To develop and evaluate a deep learning model for enhanced breast cancer prediction accuracy.
- To introduce a novel deep extreme gradient descent optimization (DEGDO) technique for breast cancer detection.
Main Methods:
- A two-stage model comprising training and validation phases was implemented.
- The training phase involved data acquisition, preprocessing (noise/missing value handling), and application layers.
- The model was trained using the Wisconsin Breast Cancer Diagnostic dataset and DEGDO.
Main Results:
- The proposed DEGDO-based deep learning model achieved 98.73% accuracy.
- Exceptional performance metrics include 99.60% specificity, 99.43% sensitivity, and 99.48% precision.
- The model demonstrated superior performance compared to existing approaches.
Conclusions:
- The developed deep learning model with DEGDO shows significant promise for accurate breast cancer detection.
- The high accuracy and performance metrics suggest its utility in clinical settings for improved diagnostics.
- Further validation and implementation could enhance breast cancer screening and patient care.
