Improving Computer-Aided Cervical Cells Classification Using Transfer Learning Based Snapshot Ensemble
Cervical cells classification is a crucial component of computer-aided cervical cancer detection. Fine-grained classification is of great clinical importance when guiding clinical decisions on the diagnoses and treatment, which remains very challenging. Recently, convolutional neural networks (CNN)...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-10-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/10/20/7292 |
| _version_ | 1797550585456623616 |
|---|---|
| author | Wen Chen Xinyu Li Liang Gao Weiming Shen |
| author_facet | Wen Chen Xinyu Li Liang Gao Weiming Shen |
| author_sort | Wen Chen |
| collection | DOAJ |
| description | Cervical cells classification is a crucial component of computer-aided cervical cancer detection. Fine-grained classification is of great clinical importance when guiding clinical decisions on the diagnoses and treatment, which remains very challenging. Recently, convolutional neural networks (CNN) provide a novel way to classify cervical cells by using automatically learned features. Although the ensemble of CNN models can increase model diversity and potentially boost the classification accuracy, it is a multi-step process, as several CNN models need to be trained respectively and then be selected for ensemble. On the other hand, due to the small training samples, the advantages of powerful CNN models may not be effectively leveraged. In order to address such a challenging issue, this paper proposes a transfer learning based snapshot ensemble (TLSE) method by integrating snapshot ensemble learning with transfer learning in a unified and coordinated way. Snapshot ensemble provides ensemble benefits within a single model training procedure, while transfer learning focuses on the small sample problem in cervical cells classification. Furthermore, a new training strategy is proposed for guaranteeing the combination. The TLSE method is evaluated on a pap-smear dataset called Herlev dataset and is proved to have some superiorities over the exiting methods. It demonstrates that TLSE can improve the accuracy in an ensemble manner with only one single training process for the small sample in fine-grained cervical cells classification. |
| first_indexed | 2024-03-10T15:31:27Z |
| format | Article |
| id | doaj.art-5254d253a5c94f0e974c52436936b00d |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T15:31:27Z |
| publishDate | 2020-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-5254d253a5c94f0e974c52436936b00d2023-11-20T17:36:02ZengMDPI AGApplied Sciences2076-34172020-10-011020729210.3390/app10207292Improving Computer-Aided Cervical Cells Classification Using Transfer Learning Based Snapshot EnsembleWen Chen0Xinyu Li1Liang Gao2Weiming Shen3State Key Lab. of Digital Manufacturing Equipment & Technology, Huazhong University of Science & Technology, Wuhan 430074, ChinaState Key Lab. of Digital Manufacturing Equipment & Technology, Huazhong University of Science & Technology, Wuhan 430074, ChinaState Key Lab. of Digital Manufacturing Equipment & Technology, Huazhong University of Science & Technology, Wuhan 430074, ChinaState Key Lab. of Digital Manufacturing Equipment & Technology, Huazhong University of Science & Technology, Wuhan 430074, ChinaCervical cells classification is a crucial component of computer-aided cervical cancer detection. Fine-grained classification is of great clinical importance when guiding clinical decisions on the diagnoses and treatment, which remains very challenging. Recently, convolutional neural networks (CNN) provide a novel way to classify cervical cells by using automatically learned features. Although the ensemble of CNN models can increase model diversity and potentially boost the classification accuracy, it is a multi-step process, as several CNN models need to be trained respectively and then be selected for ensemble. On the other hand, due to the small training samples, the advantages of powerful CNN models may not be effectively leveraged. In order to address such a challenging issue, this paper proposes a transfer learning based snapshot ensemble (TLSE) method by integrating snapshot ensemble learning with transfer learning in a unified and coordinated way. Snapshot ensemble provides ensemble benefits within a single model training procedure, while transfer learning focuses on the small sample problem in cervical cells classification. Furthermore, a new training strategy is proposed for guaranteeing the combination. The TLSE method is evaluated on a pap-smear dataset called Herlev dataset and is proved to have some superiorities over the exiting methods. It demonstrates that TLSE can improve the accuracy in an ensemble manner with only one single training process for the small sample in fine-grained cervical cells classification.https://www.mdpi.com/2076-3417/10/20/7292cervical cells classificationsnapshot ensembletransfer learningdeep convolutional neural networkdeep learningmedical image |
| spellingShingle | Wen Chen Xinyu Li Liang Gao Weiming Shen Improving Computer-Aided Cervical Cells Classification Using Transfer Learning Based Snapshot Ensemble Applied Sciences cervical cells classification snapshot ensemble transfer learning deep convolutional neural network deep learning medical image |
| title | Improving Computer-Aided Cervical Cells Classification Using Transfer Learning Based Snapshot Ensemble |
| title_full | Improving Computer-Aided Cervical Cells Classification Using Transfer Learning Based Snapshot Ensemble |
| title_fullStr | Improving Computer-Aided Cervical Cells Classification Using Transfer Learning Based Snapshot Ensemble |
| title_full_unstemmed | Improving Computer-Aided Cervical Cells Classification Using Transfer Learning Based Snapshot Ensemble |
| title_short | Improving Computer-Aided Cervical Cells Classification Using Transfer Learning Based Snapshot Ensemble |
| title_sort | improving computer aided cervical cells classification using transfer learning based snapshot ensemble |
| topic | cervical cells classification snapshot ensemble transfer learning deep convolutional neural network deep learning medical image |
| url | https://www.mdpi.com/2076-3417/10/20/7292 |
| work_keys_str_mv | AT wenchen improvingcomputeraidedcervicalcellsclassificationusingtransferlearningbasedsnapshotensemble AT xinyuli improvingcomputeraidedcervicalcellsclassificationusingtransferlearningbasedsnapshotensemble AT lianggao improvingcomputeraidedcervicalcellsclassificationusingtransferlearningbasedsnapshotensemble AT weimingshen improvingcomputeraidedcervicalcellsclassificationusingtransferlearningbasedsnapshotensemble |