BreastMultiNet: A multi-scale feature fusion method using deep neural network to detect breast cancer
Breast cancer is predominantly seen in women and is the leading cause of death in females worldwide. Diagnosis of breast cancer using biopsy tissue images is expensive, time-intensive, and fraught with conflicts among doctors. Pathologists can now diagnose breast cancer more consistently and promptl...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2022-12-01
|
| Series: | Array |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2590005622000893 |
| _version_ | 1811185819980922880 |
|---|---|
| author | Md. Mahbubur Rahman Md. Saikat Islam Khan Hafiz Md. Hasan Babu |
| author_facet | Md. Mahbubur Rahman Md. Saikat Islam Khan Hafiz Md. Hasan Babu |
| author_sort | Md. Mahbubur Rahman |
| collection | DOAJ |
| description | Breast cancer is predominantly seen in women and is the leading cause of death in females worldwide. Diagnosis of breast cancer using biopsy tissue images is expensive, time-intensive, and fraught with conflicts among doctors. Pathologists can now diagnose breast cancer more consistently and promptly because of advances in the Computer-Aided Diagnosis (CAD) system. As a result, there has been a surge in demand for CAD-based machine learning techniques. This study describes a “BreastMultiNet” framework that focuses on the transfer learning concept for identifying distinct types of breast cancer by utilizing two publicly available datasets. The suggested “BreastMultiNet” architecture allows rapid and comprehensive breast cancer diagnosis. The suggested scheme extracts features from microscope images with the help of well-known conventional and deep learning models such as HOG, LBP, SURP, DenseNet201, and VGG19. Comparatively, transfer learning models provide good accuracy than conventional models. The collected properties of transfer learning models are subsequently dispatched into the summing layer, resulting in a fused vector. The proposed framework achieves 99% and 95% classification accuracy on both BreakHis and ICIAR dataset respectively, outperforming all the other state of the art techniques. In terms of accuracy, the “BreastMultiNet” framework may be employed as a modeling approach in hospitals and medical care contexts. |
| first_indexed | 2024-04-11T13:35:48Z |
| format | Article |
| id | doaj.art-b5a0e5f338cd476bb4b43f54e77d9471 |
| institution | Directory Open Access Journal |
| issn | 2590-0056 |
| language | English |
| last_indexed | 2024-04-11T13:35:48Z |
| publishDate | 2022-12-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Array |
| spelling | doaj.art-b5a0e5f338cd476bb4b43f54e77d94712022-12-22T04:21:30ZengElsevierArray2590-00562022-12-0116100256BreastMultiNet: A multi-scale feature fusion method using deep neural network to detect breast cancerMd. Mahbubur Rahman0Md. Saikat Islam Khan1Hafiz Md. Hasan Babu2Department of Computer Science and Engineering, Mawlana Bhashani Science and Technology University, Bangladesh; Department of Computer Science and Engineering, Dhaka International University, Bangladesh; Corresponding author. Department of Computer Science and Engineering, Mawlana Bhashani Science and Technology University, Bangladesh.Department of Computer Science and Engineering, Mawlana Bhashani Science and Technology University, Bangladesh; Department of Computer Science and Engineering, Dhaka International University, Bangladesh; Corresponding author. Department of Computer Science and Engineering, Mawlana Bhashani Science and Technology University, Bangladesh.Department of Computer Science and Engineering, Dhaka University, BangladeshBreast cancer is predominantly seen in women and is the leading cause of death in females worldwide. Diagnosis of breast cancer using biopsy tissue images is expensive, time-intensive, and fraught with conflicts among doctors. Pathologists can now diagnose breast cancer more consistently and promptly because of advances in the Computer-Aided Diagnosis (CAD) system. As a result, there has been a surge in demand for CAD-based machine learning techniques. This study describes a “BreastMultiNet” framework that focuses on the transfer learning concept for identifying distinct types of breast cancer by utilizing two publicly available datasets. The suggested “BreastMultiNet” architecture allows rapid and comprehensive breast cancer diagnosis. The suggested scheme extracts features from microscope images with the help of well-known conventional and deep learning models such as HOG, LBP, SURP, DenseNet201, and VGG19. Comparatively, transfer learning models provide good accuracy than conventional models. The collected properties of transfer learning models are subsequently dispatched into the summing layer, resulting in a fused vector. The proposed framework achieves 99% and 95% classification accuracy on both BreakHis and ICIAR dataset respectively, outperforming all the other state of the art techniques. In terms of accuracy, the “BreastMultiNet” framework may be employed as a modeling approach in hospitals and medical care contexts.http://www.sciencedirect.com/science/article/pii/S2590005622000893DenseNet-201VGG19Histogram oriented gradientLocal binary patternSpeed-up robust feature |
| spellingShingle | Md. Mahbubur Rahman Md. Saikat Islam Khan Hafiz Md. Hasan Babu BreastMultiNet: A multi-scale feature fusion method using deep neural network to detect breast cancer Array DenseNet-201 VGG19 Histogram oriented gradient Local binary pattern Speed-up robust feature |
| title | BreastMultiNet: A multi-scale feature fusion method using deep neural network to detect breast cancer |
| title_full | BreastMultiNet: A multi-scale feature fusion method using deep neural network to detect breast cancer |
| title_fullStr | BreastMultiNet: A multi-scale feature fusion method using deep neural network to detect breast cancer |
| title_full_unstemmed | BreastMultiNet: A multi-scale feature fusion method using deep neural network to detect breast cancer |
| title_short | BreastMultiNet: A multi-scale feature fusion method using deep neural network to detect breast cancer |
| title_sort | breastmultinet a multi scale feature fusion method using deep neural network to detect breast cancer |
| topic | DenseNet-201 VGG19 Histogram oriented gradient Local binary pattern Speed-up robust feature |
| url | http://www.sciencedirect.com/science/article/pii/S2590005622000893 |
| work_keys_str_mv | AT mdmahbuburrahman breastmultinetamultiscalefeaturefusionmethodusingdeepneuralnetworktodetectbreastcancer AT mdsaikatislamkhan breastmultinetamultiscalefeaturefusionmethodusingdeepneuralnetworktodetectbreastcancer AT hafizmdhasanbabu breastmultinetamultiscalefeaturefusionmethodusingdeepneuralnetworktodetectbreastcancer |