This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
Open AccessFeature PaperArticle
Automated Classification and Segmentation and Feature Extraction from Breast Imaging Data
by
Yiran Sun
Yiran Sun 1,2,
Zede Zhu
Zede Zhu 1,2 and
Barmak Honarvar Shakibaei Asli
Barmak Honarvar Shakibaei Asli 2,*
1
College of Mechanical and Electrical Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, China
2
Centre for Life-Cycle Engineering and Management, Faculty of Engineering and Applied Sciences,
Cranfield University, Cranfield, Bedfordshire MK43 0AL, UK
*
Author to whom correspondence should be addressed.
Electronics 2024, 13(19), 3814; https://doi.org/10.3390/electronics13193814 (registering DOI)
Submission received: 9 August 2024
/
Revised: 23 September 2024
/
Accepted: 24 September 2024
/
Published: 26 September 2024
Abstract
Breast cancer is the most common type of cancer in women and poses a significant health risk to women globally. Developments in computer-aided diagnosis (CAD) systems are focused on specific tasks of classification and segmentation, but few studies involve a completely integrated system. In this study, a comprehensive CAD system was proposed to screen ultrasound, mammograms and magnetic resonance imaging (MRI) of breast cancer, including image preprocessing, breast cancer classification, and tumour segmentation. First, the total variation filter was used for image denoising. Second, an optimised XGBoost machine learning model using EfficicnetB0 as feature extraction was proposed to classify breast images into normal and tumour. Third, after classifying the tumour images, a hybrid CNN deep learning model integrating the strengths of MobileNet and InceptionV3 was proposed to categorise tumour images into benign and malignant. Finally, Attention U-Net was used to segment tumours in annotated datasets while classical image segmentation methods were used for the others. The proposed models in the designed CAD system achieved an accuracy of 96.14% on the abnormal classification and 94.81% on tumour classification on the BUSI dataset, improving the effectiveness of automatic breast cancer diagnosis.
Share and Cite
MDPI and ACS Style
Sun, Y.; Zhu, Z.; Honarvar Shakibaei Asli, B.
Automated Classification and Segmentation and Feature Extraction from Breast Imaging Data. Electronics 2024, 13, 3814.
https://doi.org/10.3390/electronics13193814
AMA Style
Sun Y, Zhu Z, Honarvar Shakibaei Asli B.
Automated Classification and Segmentation and Feature Extraction from Breast Imaging Data. Electronics. 2024; 13(19):3814.
https://doi.org/10.3390/electronics13193814
Chicago/Turabian Style
Sun, Yiran, Zede Zhu, and Barmak Honarvar Shakibaei Asli.
2024. "Automated Classification and Segmentation and Feature Extraction from Breast Imaging Data" Electronics 13, no. 19: 3814.
https://doi.org/10.3390/electronics13193814
Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details
here.
Article Metrics
Article Access Statistics
For more information on the journal statistics, click
here.
Multiple requests from the same IP address are counted as one view.