Enhanced Pre-Trained Xception Model Transfer Learned for Breast Cancer Detection
Early detection and timely breast cancer treatment improve survival rates and patients’ quality of life. Hence, many computer-assisted techniques based on artificial intelligence are being introduced into the traditional diagnostic workflow. This inclusion of automatic diagnostic systems speeds up d...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-03-01
|
| Series: | Computation |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-3197/11/3/59 |
| _version_ | 1797612597780938752 |
|---|---|
| author | Shubhangi A. Joshi Anupkumar M. Bongale P. Olof Olsson Siddhaling Urolagin Deepak Dharrao Arunkumar Bongale |
| author_facet | Shubhangi A. Joshi Anupkumar M. Bongale P. Olof Olsson Siddhaling Urolagin Deepak Dharrao Arunkumar Bongale |
| author_sort | Shubhangi A. Joshi |
| collection | DOAJ |
| description | Early detection and timely breast cancer treatment improve survival rates and patients’ quality of life. Hence, many computer-assisted techniques based on artificial intelligence are being introduced into the traditional diagnostic workflow. This inclusion of automatic diagnostic systems speeds up diagnosis and helps medical professionals by relieving their work pressure. This study proposes a breast cancer detection framework based on a deep convolutional neural network. To mine useful information about breast cancer through breast histopathology images of the 40× magnification factor that are publicly available, the BreakHis dataset and IDC(Invasive ductal carcinoma) dataset are used. Pre-trained convolutional neural network (CNN) models EfficientNetB0, ResNet50, and Xception are tested for this study. The top layers of these architectures are replaced by custom layers to make the whole architecture specific to the breast cancer detection task. It is seen that the customized Xception model outperformed other frameworks. It gave an accuracy of 93.33% for the 40× zoom images of the BreakHis dataset. The networks are trained using 70% data consisting of BreakHis 40× histopathological images as training data and validated on 30% of the total 40× images as unseen testing and validation data. The histopathology image set is augmented by performing various image transforms. Dropout and batch normalization are used as regularization techniques. Further, the proposed model with enhanced pre-trained Xception CNN is fine-tuned and tested on a part of the IDC dataset. For the IDC dataset training, validation, and testing percentages are kept as 60%, 20%, and 20%, respectively. It obtained an accuracy of 88.08% for the IDC dataset for recognizing invasive ductal carcinoma from H&E-stained histopathological tissue samples of breast tissues. Weights learned during training on the BreakHis dataset are kept the same while training the model on IDC dataset. Thus, this study enhances and customizes functionality of pre-trained model as per the task of classification on the BreakHis and IDC datasets. This study also tries to apply the transfer learning approach for the designed model to another similar classification task. |
| first_indexed | 2024-03-11T06:44:17Z |
| format | Article |
| id | doaj.art-f53068be01174f9a9fc62da1d333d354 |
| institution | Directory Open Access Journal |
| issn | 2079-3197 |
| language | English |
| last_indexed | 2024-03-11T06:44:17Z |
| publishDate | 2023-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Computation |
| spelling | doaj.art-f53068be01174f9a9fc62da1d333d3542023-11-17T10:26:13ZengMDPI AGComputation2079-31972023-03-011135910.3390/computation11030059Enhanced Pre-Trained Xception Model Transfer Learned for Breast Cancer DetectionShubhangi A. Joshi0Anupkumar M. Bongale1P. Olof Olsson2Siddhaling Urolagin3Deepak Dharrao4Arunkumar Bongale5Symbiosis Institute of Technology (SIT), Symbiosis International (Deemed University), Lavale, Pune 412 115, Maharashtra, IndiaDepartment of Artificial Intelligence and Machine Learning, Symbiosis Institute of Technology (SIT), Symbiosis International (Deemed University), Lavale, Pune 412 115, Maharashtra, IndiaFujairah Genetics Center, Fujairah, United Arab EmiratesDepartment of Computer Science, Birla Institute of Technology & Science, Pilani, Dubai International Academic City, Dubai P.O. Box 345055, United Arab EmiratesDepartment of Computer Science and Engineering, Symbiosis Institute of Technology (SIT), Symbiosis International (Deemed University), Lavale, Pune 412 115, Maharashtra, IndiaSymbiosis Institute of Technology (SIT), Symbiosis International (Deemed University), Lavale, Pune 412 115, Maharashtra, IndiaEarly detection and timely breast cancer treatment improve survival rates and patients’ quality of life. Hence, many computer-assisted techniques based on artificial intelligence are being introduced into the traditional diagnostic workflow. This inclusion of automatic diagnostic systems speeds up diagnosis and helps medical professionals by relieving their work pressure. This study proposes a breast cancer detection framework based on a deep convolutional neural network. To mine useful information about breast cancer through breast histopathology images of the 40× magnification factor that are publicly available, the BreakHis dataset and IDC(Invasive ductal carcinoma) dataset are used. Pre-trained convolutional neural network (CNN) models EfficientNetB0, ResNet50, and Xception are tested for this study. The top layers of these architectures are replaced by custom layers to make the whole architecture specific to the breast cancer detection task. It is seen that the customized Xception model outperformed other frameworks. It gave an accuracy of 93.33% for the 40× zoom images of the BreakHis dataset. The networks are trained using 70% data consisting of BreakHis 40× histopathological images as training data and validated on 30% of the total 40× images as unseen testing and validation data. The histopathology image set is augmented by performing various image transforms. Dropout and batch normalization are used as regularization techniques. Further, the proposed model with enhanced pre-trained Xception CNN is fine-tuned and tested on a part of the IDC dataset. For the IDC dataset training, validation, and testing percentages are kept as 60%, 20%, and 20%, respectively. It obtained an accuracy of 88.08% for the IDC dataset for recognizing invasive ductal carcinoma from H&E-stained histopathological tissue samples of breast tissues. Weights learned during training on the BreakHis dataset are kept the same while training the model on IDC dataset. Thus, this study enhances and customizes functionality of pre-trained model as per the task of classification on the BreakHis and IDC datasets. This study also tries to apply the transfer learning approach for the designed model to another similar classification task.https://www.mdpi.com/2079-3197/11/3/59breast cancer detectionmagnification dependenthistopathologyBreakHisIDCXception model |
| spellingShingle | Shubhangi A. Joshi Anupkumar M. Bongale P. Olof Olsson Siddhaling Urolagin Deepak Dharrao Arunkumar Bongale Enhanced Pre-Trained Xception Model Transfer Learned for Breast Cancer Detection Computation breast cancer detection magnification dependent histopathology BreakHis IDC Xception model |
| title | Enhanced Pre-Trained Xception Model Transfer Learned for Breast Cancer Detection |
| title_full | Enhanced Pre-Trained Xception Model Transfer Learned for Breast Cancer Detection |
| title_fullStr | Enhanced Pre-Trained Xception Model Transfer Learned for Breast Cancer Detection |
| title_full_unstemmed | Enhanced Pre-Trained Xception Model Transfer Learned for Breast Cancer Detection |
| title_short | Enhanced Pre-Trained Xception Model Transfer Learned for Breast Cancer Detection |
| title_sort | enhanced pre trained xception model transfer learned for breast cancer detection |
| topic | breast cancer detection magnification dependent histopathology BreakHis IDC Xception model |
| url | https://www.mdpi.com/2079-3197/11/3/59 |
| work_keys_str_mv | AT shubhangiajoshi enhancedpretrainedxceptionmodeltransferlearnedforbreastcancerdetection AT anupkumarmbongale enhancedpretrainedxceptionmodeltransferlearnedforbreastcancerdetection AT polofolsson enhancedpretrainedxceptionmodeltransferlearnedforbreastcancerdetection AT siddhalingurolagin enhancedpretrainedxceptionmodeltransferlearnedforbreastcancerdetection AT deepakdharrao enhancedpretrainedxceptionmodeltransferlearnedforbreastcancerdetection AT arunkumarbongale enhancedpretrainedxceptionmodeltransferlearnedforbreastcancerdetection |