A deep fusion‐based vision transformer for breast cancer classification
Abstract Breast cancer is one of the most common causes of death in women in the modern world. Cancerous tissue detection in histopathological images relies on complex features related to tissue structure and staining properties. Convolutional neural network (CNN) models like ResNet50, Inception‐V1,...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2024-12-01
|
| Series: | Healthcare Technology Letters |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/htl2.12093 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850099289172213760 |
|---|---|
| author | Ahsan Fiaz Basit Raza Muhammad Faheem Aadil Raza |
| author_facet | Ahsan Fiaz Basit Raza Muhammad Faheem Aadil Raza |
| author_sort | Ahsan Fiaz |
| collection | DOAJ |
| description | Abstract Breast cancer is one of the most common causes of death in women in the modern world. Cancerous tissue detection in histopathological images relies on complex features related to tissue structure and staining properties. Convolutional neural network (CNN) models like ResNet50, Inception‐V1, and VGG‐16, while useful in many applications, cannot capture the patterns of cell layers and staining properties. Most previous approaches, such as stain normalization and instance‐based vision transformers, either miss important features or do not process the whole image effectively. Therefore, a deep fusion‐based vision Transformer model (DFViT) that combines CNNs and transformers for better feature extraction is proposed. DFViT captures local and global patterns more effectively by fusing RGB and stain‐normalized images. Trained and tested on several datasets, such as BreakHis, breast cancer histology (BACH), and UCSC cancer genomics (UC), the results demonstrate outstanding accuracy, F1 score, precision, and recall, setting a new milestone in histopathological image analysis for diagnosing breast cancer. |
| format | Article |
| id | doaj-art-afa4095df7ce44588cbf706b1052b4d7 |
| institution | DOAJ |
| issn | 2053-3713 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Wiley |
| record_format | Article |
| series | Healthcare Technology Letters |
| spelling | doaj-art-afa4095df7ce44588cbf706b1052b4d72025-08-20T02:40:30ZengWileyHealthcare Technology Letters2053-37132024-12-0111647148410.1049/htl2.12093A deep fusion‐based vision transformer for breast cancer classificationAhsan Fiaz0Basit Raza1Muhammad Faheem2Aadil Raza3Department of Computer ScienceCOMSATS University Islamabad (CUI)IslamabadPakistanDepartment of Computer ScienceCOMSATS University Islamabad (CUI)IslamabadPakistanSchool of Technology and InnovationsUniversity of VaasaVaasaFinlandDepartment of PhysicsCOMSATS University Islamabad (CUI)IslamabadPakistanAbstract Breast cancer is one of the most common causes of death in women in the modern world. Cancerous tissue detection in histopathological images relies on complex features related to tissue structure and staining properties. Convolutional neural network (CNN) models like ResNet50, Inception‐V1, and VGG‐16, while useful in many applications, cannot capture the patterns of cell layers and staining properties. Most previous approaches, such as stain normalization and instance‐based vision transformers, either miss important features or do not process the whole image effectively. Therefore, a deep fusion‐based vision Transformer model (DFViT) that combines CNNs and transformers for better feature extraction is proposed. DFViT captures local and global patterns more effectively by fusing RGB and stain‐normalized images. Trained and tested on several datasets, such as BreakHis, breast cancer histology (BACH), and UCSC cancer genomics (UC), the results demonstrate outstanding accuracy, F1 score, precision, and recall, setting a new milestone in histopathological image analysis for diagnosing breast cancer.https://doi.org/10.1049/htl2.12093artificial intelligencebreast cancerclassificationdeep learninghistopathology imagesmachine learning |
| spellingShingle | Ahsan Fiaz Basit Raza Muhammad Faheem Aadil Raza A deep fusion‐based vision transformer for breast cancer classification Healthcare Technology Letters artificial intelligence breast cancer classification deep learning histopathology images machine learning |
| title | A deep fusion‐based vision transformer for breast cancer classification |
| title_full | A deep fusion‐based vision transformer for breast cancer classification |
| title_fullStr | A deep fusion‐based vision transformer for breast cancer classification |
| title_full_unstemmed | A deep fusion‐based vision transformer for breast cancer classification |
| title_short | A deep fusion‐based vision transformer for breast cancer classification |
| title_sort | deep fusion based vision transformer for breast cancer classification |
| topic | artificial intelligence breast cancer classification deep learning histopathology images machine learning |
| url | https://doi.org/10.1049/htl2.12093 |
| work_keys_str_mv | AT ahsanfiaz adeepfusionbasedvisiontransformerforbreastcancerclassification AT basitraza adeepfusionbasedvisiontransformerforbreastcancerclassification AT muhammadfaheem adeepfusionbasedvisiontransformerforbreastcancerclassification AT aadilraza adeepfusionbasedvisiontransformerforbreastcancerclassification AT ahsanfiaz deepfusionbasedvisiontransformerforbreastcancerclassification AT basitraza deepfusionbasedvisiontransformerforbreastcancerclassification AT muhammadfaheem deepfusionbasedvisiontransformerforbreastcancerclassification AT aadilraza deepfusionbasedvisiontransformerforbreastcancerclassification |