High Precision Cervical Precancerous Lesion Classification Method Based on ConvNeXt
Traditional cervical cancer diagnosis mainly relies on human papillomavirus (HPV) concentration testing. Considering that HPV concentrations vary from individual to individual and fluctuate over time, this method requires multiple tests, leading to high costs. Recently, some scholars have focused on...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-12-01
|
| Series: | Bioengineering |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2306-5354/10/12/1424 |
| _version_ | 1827575645375299584 |
|---|---|
| author | Jing Tang Ting Zhang Zeyu Gong Xianjun Huang |
| author_facet | Jing Tang Ting Zhang Zeyu Gong Xianjun Huang |
| author_sort | Jing Tang |
| collection | DOAJ |
| description | Traditional cervical cancer diagnosis mainly relies on human papillomavirus (HPV) concentration testing. Considering that HPV concentrations vary from individual to individual and fluctuate over time, this method requires multiple tests, leading to high costs. Recently, some scholars have focused on the method of cervical cytology for diagnosis. However, cervical cancer cells have complex textural characteristics and small differences between different cell subtypes, which brings great challenges for high-precision screening of cervical cancer. In this paper, we propose a high-precision cervical cancer precancerous lesion screening classification method based on ConvNeXt, utilizing self-supervised data augmentation and ensemble learning strategies to achieve cervical cancer cell feature extraction and inter-class discrimination, respectively. We used the Deep Cervical Cytological Levels (DCCL) dataset, which includes 1167 cervical cytology specimens from participants aged 32 to 67, for algorithm training and validation. We tested our method on the DCCL dataset, and the final classification accuracy was 8.85% higher than that of previous advanced models, which means that our method has significant advantages compared to other advanced methods. |
| first_indexed | 2024-03-08T20:59:59Z |
| format | Article |
| id | doaj.art-b7ee465d7c7240acbb51418c7e98bde3 |
| institution | Directory Open Access Journal |
| issn | 2306-5354 |
| language | English |
| last_indexed | 2024-03-08T20:59:59Z |
| publishDate | 2023-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Bioengineering |
| spelling | doaj.art-b7ee465d7c7240acbb51418c7e98bde32023-12-22T13:54:14ZengMDPI AGBioengineering2306-53542023-12-011012142410.3390/bioengineering10121424High Precision Cervical Precancerous Lesion Classification Method Based on ConvNeXtJing Tang0Ting Zhang1Zeyu Gong2Xianjun Huang3State Key Laboratory of Intelligent Manufacturing Equipment and Technology, School of Mechanical Science and Engineering, Huazhong University of Science and Technology, Wuhan 430074, ChinaMOE Key Laboratory of Molecular Biophysics, College of Life Science and Technology, Huazhong University of Science and Technology, Wuhan 430074, ChinaState Key Laboratory of Intelligent Manufacturing Equipment and Technology, School of Mechanical Science and Engineering, Huazhong University of Science and Technology, Wuhan 430074, ChinaSchool of Computer Science and Engineering, Guangzhou Institute of Science and Technology, Guangzhou 510006, ChinaTraditional cervical cancer diagnosis mainly relies on human papillomavirus (HPV) concentration testing. Considering that HPV concentrations vary from individual to individual and fluctuate over time, this method requires multiple tests, leading to high costs. Recently, some scholars have focused on the method of cervical cytology for diagnosis. However, cervical cancer cells have complex textural characteristics and small differences between different cell subtypes, which brings great challenges for high-precision screening of cervical cancer. In this paper, we propose a high-precision cervical cancer precancerous lesion screening classification method based on ConvNeXt, utilizing self-supervised data augmentation and ensemble learning strategies to achieve cervical cancer cell feature extraction and inter-class discrimination, respectively. We used the Deep Cervical Cytological Levels (DCCL) dataset, which includes 1167 cervical cytology specimens from participants aged 32 to 67, for algorithm training and validation. We tested our method on the DCCL dataset, and the final classification accuracy was 8.85% higher than that of previous advanced models, which means that our method has significant advantages compared to other advanced methods.https://www.mdpi.com/2306-5354/10/12/1424deep learningcervical cancer screeningliquid-based cytology |
| spellingShingle | Jing Tang Ting Zhang Zeyu Gong Xianjun Huang High Precision Cervical Precancerous Lesion Classification Method Based on ConvNeXt Bioengineering deep learning cervical cancer screening liquid-based cytology |
| title | High Precision Cervical Precancerous Lesion Classification Method Based on ConvNeXt |
| title_full | High Precision Cervical Precancerous Lesion Classification Method Based on ConvNeXt |
| title_fullStr | High Precision Cervical Precancerous Lesion Classification Method Based on ConvNeXt |
| title_full_unstemmed | High Precision Cervical Precancerous Lesion Classification Method Based on ConvNeXt |
| title_short | High Precision Cervical Precancerous Lesion Classification Method Based on ConvNeXt |
| title_sort | high precision cervical precancerous lesion classification method based on convnext |
| topic | deep learning cervical cancer screening liquid-based cytology |
| url | https://www.mdpi.com/2306-5354/10/12/1424 |
| work_keys_str_mv | AT jingtang highprecisioncervicalprecancerouslesionclassificationmethodbasedonconvnext AT tingzhang highprecisioncervicalprecancerouslesionclassificationmethodbasedonconvnext AT zeyugong highprecisioncervicalprecancerouslesionclassificationmethodbasedonconvnext AT xianjunhuang highprecisioncervicalprecancerouslesionclassificationmethodbasedonconvnext |