Breast Cancer Classification Using Fine-Tuned SWIN Transformer Model on Mammographic Images
Breast cancer is the most prevalent type of disease among women. It has become one of the foremost causes of death among women globally. Early detection plays a significant role in administering personalized treatment and improving patient outcomes. Mammography procedures are often used to detect ea...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-11-01
|
| Series: | Analytics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2813-2203/3/4/26 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846106302493753344 |
|---|---|
| author | Oluwatosin Tanimola Olamilekan Shobayo Olusogo Popoola Obinna Okoyeigbo |
| author_facet | Oluwatosin Tanimola Olamilekan Shobayo Olusogo Popoola Obinna Okoyeigbo |
| author_sort | Oluwatosin Tanimola |
| collection | DOAJ |
| description | Breast cancer is the most prevalent type of disease among women. It has become one of the foremost causes of death among women globally. Early detection plays a significant role in administering personalized treatment and improving patient outcomes. Mammography procedures are often used to detect early-stage cancer cells. This traditional method of mammography while valuable has limitations in its potential for false positives and negatives, patient discomfort, and radiation exposure. Therefore, there is a probe for more accurate techniques required in detecting breast cancer, leading to exploring the potential of machine learning in the classification of diagnostic images due to its efficiency and accuracy. This study conducted a comparative analysis of pre-trained CNNs (ResNet50 and VGG16) and vision transformers (ViT-base and SWIN transformer) with the inclusion of ViT-base trained from scratch model architectures to effectively classify mammographic breast cancer images into benign and malignant cases. The SWIN transformer exhibits superior performance with 99.9% accuracy and a precision of 99.8%. These findings demonstrate the efficiency of deep learning to accurately classify mammographic breast cancer images for the diagnosis of breast cancer, leading to improvements in patient outcomes. |
| format | Article |
| id | doaj-art-cf84d1c314b74ddcab1a00502e21a904 |
| institution | Kabale University |
| issn | 2813-2203 |
| language | English |
| publishDate | 2024-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Analytics |
| spelling | doaj-art-cf84d1c314b74ddcab1a00502e21a9042024-12-27T14:05:26ZengMDPI AGAnalytics2813-22032024-11-013446147510.3390/analytics3040026Breast Cancer Classification Using Fine-Tuned SWIN Transformer Model on Mammographic ImagesOluwatosin Tanimola0Olamilekan Shobayo1Olusogo Popoola2Obinna Okoyeigbo3School of Computing and Digital Technologies, Sheffield Hallam University, Sheffield S1 2NU, UKSchool of Computing and Digital Technologies, Sheffield Hallam University, Sheffield S1 2NU, UKSchool of Computing and Digital Technologies, Sheffield Hallam University, Sheffield S1 2NU, UKDepartment of Engineering, Edge Hill University, Ormskirk L39 4QP, UKBreast cancer is the most prevalent type of disease among women. It has become one of the foremost causes of death among women globally. Early detection plays a significant role in administering personalized treatment and improving patient outcomes. Mammography procedures are often used to detect early-stage cancer cells. This traditional method of mammography while valuable has limitations in its potential for false positives and negatives, patient discomfort, and radiation exposure. Therefore, there is a probe for more accurate techniques required in detecting breast cancer, leading to exploring the potential of machine learning in the classification of diagnostic images due to its efficiency and accuracy. This study conducted a comparative analysis of pre-trained CNNs (ResNet50 and VGG16) and vision transformers (ViT-base and SWIN transformer) with the inclusion of ViT-base trained from scratch model architectures to effectively classify mammographic breast cancer images into benign and malignant cases. The SWIN transformer exhibits superior performance with 99.9% accuracy and a precision of 99.8%. These findings demonstrate the efficiency of deep learning to accurately classify mammographic breast cancer images for the diagnosis of breast cancer, leading to improvements in patient outcomes.https://www.mdpi.com/2813-2203/3/4/26breast cancerdeep learningtransformer models |
| spellingShingle | Oluwatosin Tanimola Olamilekan Shobayo Olusogo Popoola Obinna Okoyeigbo Breast Cancer Classification Using Fine-Tuned SWIN Transformer Model on Mammographic Images Analytics breast cancer deep learning transformer models |
| title | Breast Cancer Classification Using Fine-Tuned SWIN Transformer Model on Mammographic Images |
| title_full | Breast Cancer Classification Using Fine-Tuned SWIN Transformer Model on Mammographic Images |
| title_fullStr | Breast Cancer Classification Using Fine-Tuned SWIN Transformer Model on Mammographic Images |
| title_full_unstemmed | Breast Cancer Classification Using Fine-Tuned SWIN Transformer Model on Mammographic Images |
| title_short | Breast Cancer Classification Using Fine-Tuned SWIN Transformer Model on Mammographic Images |
| title_sort | breast cancer classification using fine tuned swin transformer model on mammographic images |
| topic | breast cancer deep learning transformer models |
| url | https://www.mdpi.com/2813-2203/3/4/26 |
| work_keys_str_mv | AT oluwatosintanimola breastcancerclassificationusingfinetunedswintransformermodelonmammographicimages AT olamilekanshobayo breastcancerclassificationusingfinetunedswintransformermodelonmammographicimages AT olusogopopoola breastcancerclassificationusingfinetunedswintransformermodelonmammographicimages AT obinnaokoyeigbo breastcancerclassificationusingfinetunedswintransformermodelonmammographicimages |