Label credibility correction based on cell morphological differences for cervical cells classification
Abstract Cervical cancer is one of the deadliest cancers that pose a significant threat to women’s health. Early detection and treatment are commonly used methods to prevent cervical cancer. The use of pathological image analysis techniques for the automatic interpretation of cervical cells in patho...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-01-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-024-84899-8 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841559587603349504 |
|---|---|
| author | Wenbo Pang Yue Qiu Shu Jin Huiyan Jiang Yi Ma |
| author_facet | Wenbo Pang Yue Qiu Shu Jin Huiyan Jiang Yi Ma |
| author_sort | Wenbo Pang |
| collection | DOAJ |
| description | Abstract Cervical cancer is one of the deadliest cancers that pose a significant threat to women’s health. Early detection and treatment are commonly used methods to prevent cervical cancer. The use of pathological image analysis techniques for the automatic interpretation of cervical cells in pathological slides is a prominent area of research in the field of digital medicine. According to The Bethesda System, cervical cytology necessitates further classification of precancerous lesions based on positive interpretations. However, clinical definitions among different categories of lesion are complex and often characterized by fuzzy boundaries. In addition, pathologists can deduce different criteria for judgment based on The Bethesda System, leading to potential confusion during data labeling. Noisy labels due to this reason are a great challenge for supervised learning. To address the problem caused by noisy labels, we propose a method based on label credibility correction for cervical cell images classification network. Firstly, a contrastive learning network is used to extract discriminative features from cell images to obtain more similar intra-class sample features. Subsequently, these features are fed into an unsupervised method for clustering, resulting in unsupervised class labels. Then unsupervised labels are corresponded to the true labels to separate confusable and typical samples. Through a similarity comparison between the cluster samples and the statistical feature centers of each class, the label credibility analysis is carried out to group labels. Finally, a cervical cell images multi-class network is trained using synergistic grouping method. In order to enhance the stability of the classification model, momentum is incorporated into the synergistic grouping loss. Experimental validation is conducted on a dataset comprising approximately 60,000 cells from multiple hospitals, showcasing the effectiveness of our proposed approach. The method achieves 2-class task accuracy of 0.9241 and 5-class task accuracy of 0.8598. Our proposed method achieves better performance than existing classification networks on cervical cancer. |
| format | Article |
| id | doaj-art-292414e846a648b1b04714d45af83f76 |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-292414e846a648b1b04714d45af83f762025-01-05T12:20:57ZengNature PortfolioScientific Reports2045-23222025-01-0115111510.1038/s41598-024-84899-8Label credibility correction based on cell morphological differences for cervical cells classificationWenbo Pang0Yue Qiu1Shu Jin2Huiyan Jiang3Yi Ma4Software College, Northeastern UniversityUniversity of WarwickPathology Department, Haining Traditional Chinese Medicine HospitalSoftware College, Northeastern UniversityDepartment of Pathology, The First Affiliated Hospital of Wenzhou Medical UniversityAbstract Cervical cancer is one of the deadliest cancers that pose a significant threat to women’s health. Early detection and treatment are commonly used methods to prevent cervical cancer. The use of pathological image analysis techniques for the automatic interpretation of cervical cells in pathological slides is a prominent area of research in the field of digital medicine. According to The Bethesda System, cervical cytology necessitates further classification of precancerous lesions based on positive interpretations. However, clinical definitions among different categories of lesion are complex and often characterized by fuzzy boundaries. In addition, pathologists can deduce different criteria for judgment based on The Bethesda System, leading to potential confusion during data labeling. Noisy labels due to this reason are a great challenge for supervised learning. To address the problem caused by noisy labels, we propose a method based on label credibility correction for cervical cell images classification network. Firstly, a contrastive learning network is used to extract discriminative features from cell images to obtain more similar intra-class sample features. Subsequently, these features are fed into an unsupervised method for clustering, resulting in unsupervised class labels. Then unsupervised labels are corresponded to the true labels to separate confusable and typical samples. Through a similarity comparison between the cluster samples and the statistical feature centers of each class, the label credibility analysis is carried out to group labels. Finally, a cervical cell images multi-class network is trained using synergistic grouping method. In order to enhance the stability of the classification model, momentum is incorporated into the synergistic grouping loss. Experimental validation is conducted on a dataset comprising approximately 60,000 cells from multiple hospitals, showcasing the effectiveness of our proposed approach. The method achieves 2-class task accuracy of 0.9241 and 5-class task accuracy of 0.8598. Our proposed method achieves better performance than existing classification networks on cervical cancer.https://doi.org/10.1038/s41598-024-84899-8Noisy labelPathological image analysisCervical cellsClassification network |
| spellingShingle | Wenbo Pang Yue Qiu Shu Jin Huiyan Jiang Yi Ma Label credibility correction based on cell morphological differences for cervical cells classification Scientific Reports Noisy label Pathological image analysis Cervical cells Classification network |
| title | Label credibility correction based on cell morphological differences for cervical cells classification |
| title_full | Label credibility correction based on cell morphological differences for cervical cells classification |
| title_fullStr | Label credibility correction based on cell morphological differences for cervical cells classification |
| title_full_unstemmed | Label credibility correction based on cell morphological differences for cervical cells classification |
| title_short | Label credibility correction based on cell morphological differences for cervical cells classification |
| title_sort | label credibility correction based on cell morphological differences for cervical cells classification |
| topic | Noisy label Pathological image analysis Cervical cells Classification network |
| url | https://doi.org/10.1038/s41598-024-84899-8 |
| work_keys_str_mv | AT wenbopang labelcredibilitycorrectionbasedoncellmorphologicaldifferencesforcervicalcellsclassification AT yueqiu labelcredibilitycorrectionbasedoncellmorphologicaldifferencesforcervicalcellsclassification AT shujin labelcredibilitycorrectionbasedoncellmorphologicaldifferencesforcervicalcellsclassification AT huiyanjiang labelcredibilitycorrectionbasedoncellmorphologicaldifferencesforcervicalcellsclassification AT yima labelcredibilitycorrectionbasedoncellmorphologicaldifferencesforcervicalcellsclassification |