A Novel Artificial Intelligence Techniques for Women Breast Cancer Classification Using Ultrasound Images
Background: Females benefit from ultrasound screening and diagnosis of breast cancer, and artificial intelligence has enabled the automatic identification of medical conditions on medical imaging. Methods: This study aimed to develop machine learning (ML) and deep learning (DL) models for the detect...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IMR Press
2023-12-01
|
| Series: | Clinical and Experimental Obstetrics & Gynecology |
| Subjects: | |
| Online Access: | https://www.imrpress.com/journal/CEOG/50/12/10.31083/j.ceog5012271 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850167814020661248 |
|---|---|
| author | Stephen Afrifa Vijayakumar Varadarajan Peter Appiahene Tao Zhang |
| author_facet | Stephen Afrifa Vijayakumar Varadarajan Peter Appiahene Tao Zhang |
| author_sort | Stephen Afrifa |
| collection | DOAJ |
| description | Background: Females benefit from ultrasound screening and diagnosis of breast cancer, and artificial intelligence has enabled the automatic identification of medical conditions on medical imaging. Methods: This study aimed to develop machine learning (ML) and deep learning (DL) models for the detection and classification of breast cancer in a breast ultrasound image (BUSI) and United States (US) ultrasound images datasets and to compare the models’ performance to previous studies. The ultrasound scans were collected from women between the ages of 25 and 75. The dataset contains 780 images with a resolution of 500 × 500 pixels. There were 133 normal images with no cancerous masses, 437 images with cancerous masses, and 210 images with benign masses among the 780 cancerous images in the BUSI dataset whiles the US ultrasound images includes 123 and 109 ultrasound images of malignant and benign breast tumors. Two traditional ML models, random forest (RF) and K-Nearest Neighbor (KNN), as well as a deep learning (DL) model using convolutional neural networks (CNN), were trained to classify breast masses as benign, malignant, or normal. Results: The CNN obtained an accuracy of 96.10%, the RF an accuracy of 61.46%, and the KNN an accuracy of 64.39% with the BUSI dataset. Standard evaluation measures were employed to assess the performance for benignancy, malignancy, and normality classification. Furthermore, the models’ area under the curve-receiver operating characteristics (AUC-ROC) are 0.99 by the CNN, 0.85 by the RF, and 0.65 by the KNN. Conclusions: The study’s findings revealed that DL surpasses conventional ML when it comes to training image datasets; hence, DL is suggested for breast cancer detection and classification. Furthermore, the resilience of the models used in this study overcomes data imbalance by allowing them to train both binary and multiclass datasets. |
| format | Article |
| id | doaj-art-df6a897c4fc44f099f319f14d69aa856 |
| institution | OA Journals |
| issn | 0390-6663 |
| language | English |
| publishDate | 2023-12-01 |
| publisher | IMR Press |
| record_format | Article |
| series | Clinical and Experimental Obstetrics & Gynecology |
| spelling | doaj-art-df6a897c4fc44f099f319f14d69aa8562025-08-20T02:21:07ZengIMR PressClinical and Experimental Obstetrics & Gynecology0390-66632023-12-01501227110.31083/j.ceog5012271S0390-6663(23)02192-9A Novel Artificial Intelligence Techniques for Women Breast Cancer Classification Using Ultrasound ImagesStephen Afrifa0Vijayakumar Varadarajan1Peter Appiahene2Tao Zhang3Department of Information and Communication Engineering, Tianjin University, 300072 Tianjin, ChinaDepartment of Computer Science and Engineering, University of New South Wales, Sydney, NSW 2052, AustraliaDepartment of Information Technology and Decision Sciences, University of Energy and Natural Resources, 00233 Sunyani, GhanaDepartment of Information and Communication Engineering, Tianjin University, 300072 Tianjin, ChinaBackground: Females benefit from ultrasound screening and diagnosis of breast cancer, and artificial intelligence has enabled the automatic identification of medical conditions on medical imaging. Methods: This study aimed to develop machine learning (ML) and deep learning (DL) models for the detection and classification of breast cancer in a breast ultrasound image (BUSI) and United States (US) ultrasound images datasets and to compare the models’ performance to previous studies. The ultrasound scans were collected from women between the ages of 25 and 75. The dataset contains 780 images with a resolution of 500 × 500 pixels. There were 133 normal images with no cancerous masses, 437 images with cancerous masses, and 210 images with benign masses among the 780 cancerous images in the BUSI dataset whiles the US ultrasound images includes 123 and 109 ultrasound images of malignant and benign breast tumors. Two traditional ML models, random forest (RF) and K-Nearest Neighbor (KNN), as well as a deep learning (DL) model using convolutional neural networks (CNN), were trained to classify breast masses as benign, malignant, or normal. Results: The CNN obtained an accuracy of 96.10%, the RF an accuracy of 61.46%, and the KNN an accuracy of 64.39% with the BUSI dataset. Standard evaluation measures were employed to assess the performance for benignancy, malignancy, and normality classification. Furthermore, the models’ area under the curve-receiver operating characteristics (AUC-ROC) are 0.99 by the CNN, 0.85 by the RF, and 0.65 by the KNN. Conclusions: The study’s findings revealed that DL surpasses conventional ML when it comes to training image datasets; hence, DL is suggested for breast cancer detection and classification. Furthermore, the resilience of the models used in this study overcomes data imbalance by allowing them to train both binary and multiclass datasets.https://www.imrpress.com/journal/CEOG/50/12/10.31083/j.ceog5012271artificial intelligencebreast cancerconvolutional neural networkdeep learningk-nearest neighbormachine learningrandom forestultrasound |
| spellingShingle | Stephen Afrifa Vijayakumar Varadarajan Peter Appiahene Tao Zhang A Novel Artificial Intelligence Techniques for Women Breast Cancer Classification Using Ultrasound Images Clinical and Experimental Obstetrics & Gynecology artificial intelligence breast cancer convolutional neural network deep learning k-nearest neighbor machine learning random forest ultrasound |
| title | A Novel Artificial Intelligence Techniques for Women Breast Cancer Classification Using Ultrasound Images |
| title_full | A Novel Artificial Intelligence Techniques for Women Breast Cancer Classification Using Ultrasound Images |
| title_fullStr | A Novel Artificial Intelligence Techniques for Women Breast Cancer Classification Using Ultrasound Images |
| title_full_unstemmed | A Novel Artificial Intelligence Techniques for Women Breast Cancer Classification Using Ultrasound Images |
| title_short | A Novel Artificial Intelligence Techniques for Women Breast Cancer Classification Using Ultrasound Images |
| title_sort | novel artificial intelligence techniques for women breast cancer classification using ultrasound images |
| topic | artificial intelligence breast cancer convolutional neural network deep learning k-nearest neighbor machine learning random forest ultrasound |
| url | https://www.imrpress.com/journal/CEOG/50/12/10.31083/j.ceog5012271 |
| work_keys_str_mv | AT stephenafrifa anovelartificialintelligencetechniquesforwomenbreastcancerclassificationusingultrasoundimages AT vijayakumarvaradarajan anovelartificialintelligencetechniquesforwomenbreastcancerclassificationusingultrasoundimages AT peterappiahene anovelartificialintelligencetechniquesforwomenbreastcancerclassificationusingultrasoundimages AT taozhang anovelartificialintelligencetechniquesforwomenbreastcancerclassificationusingultrasoundimages AT stephenafrifa novelartificialintelligencetechniquesforwomenbreastcancerclassificationusingultrasoundimages AT vijayakumarvaradarajan novelartificialintelligencetechniquesforwomenbreastcancerclassificationusingultrasoundimages AT peterappiahene novelartificialintelligencetechniquesforwomenbreastcancerclassificationusingultrasoundimages AT taozhang novelartificialintelligencetechniquesforwomenbreastcancerclassificationusingultrasoundimages |