Classification and diagnosis of cervical lesions based on colposcopy images using deep fully convolutional networks: A man-machine comparison cohort study
Colposcopy is an important technique in the diagnosis of cervical cancer. The development of computer-aided diagnosis methods can mitigate the shortage of colposcopists and improve the accuracy and efficiency of colposcopy examinations in China. This study proposes the Dense-U-Net model for colposco...
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
KeAi Communications Co. Ltd.
2025-01-01
|
| Series: | Fundamental Research |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2667325822004319 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832583016360181760 |
|---|---|
| author | Binhua Dong Huifeng Xue Ye Li Ping Li Jiancui Chen Tao Zhang Lihua Chen Diling Pan Peizhong Liu Pengming Sun |
| author_facet | Binhua Dong Huifeng Xue Ye Li Ping Li Jiancui Chen Tao Zhang Lihua Chen Diling Pan Peizhong Liu Pengming Sun |
| author_sort | Binhua Dong |
| collection | DOAJ |
| description | Colposcopy is an important technique in the diagnosis of cervical cancer. The development of computer-aided diagnosis methods can mitigate the shortage of colposcopists and improve the accuracy and efficiency of colposcopy examinations in China. This study proposes the Dense-U-Net model for colposcopy image recognition. This was a man–machine comparison cohort study. It presents a novel artificial intelligence (AI) model for the diagnosis of cervical lesions through colposcopy images using a Dense-U-Net image semantic segmentation algorithm. The Dense-U-Net model was created by applying the methods of “deepening the network structure,” “applying dropout” and “max pooling.” Moreover, image-based and population-based diagnostic performances of the AI algorithm and physicians with different levels of specialist experience were compared. In total, 2,475 participants were recruited, and 13,084 colposcopy images were included in this study. The diagnostic accuracy of the Dense-U-Net model increased significantly with increasing colposcopy images per patient. As the number of images in the training set increased, the diagnostic accuracy of the Dense-U-Net model for cervical intraepithelial neoplasm 3 or worse (CIN3+) diagnosis increased (P = 0.035). The rate of diagnostic accuracy (0.89 vs 0.85, P < 0.001) of CIN3+ lesions using the Dense-U-Net model was higher than that of expert colposcopists, and the missed diagnosis (0.06 vs 0.07, P = 0.002) and false positive (0.05 vs 0.08, P < 0.001) were lower. Moreover, Dense-U-Net is more accurate in diagnosing the type III cervical transformation zone, which is difficult to diagnose by experts (P < 0.001). The Dense-U-Net model also showed higher diagnostic accuracy for CIN3+ in an independent test set (P < 0.001). To diagnose the same 870 test images, the Dense-U-Net system took 1.76 ± 0.09 min, while the expert, senior, and junior colposcopists took 716.3 ± 49.76, 892.1 ± 92.30, and 3034.7 ± 259.51 min, respectively. The study successfully built a reliable, quick, and effective Dense-U-Net model to assist with colposcopy examinations. |
| format | Article |
| id | doaj-art-4a0e039b4779442986cf02c2e0035d9d |
| institution | Kabale University |
| issn | 2667-3258 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | KeAi Communications Co. Ltd. |
| record_format | Article |
| series | Fundamental Research |
| spelling | doaj-art-4a0e039b4779442986cf02c2e0035d9d2025-01-29T05:02:29ZengKeAi Communications Co. Ltd.Fundamental Research2667-32582025-01-0151419428Classification and diagnosis of cervical lesions based on colposcopy images using deep fully convolutional networks: A man-machine comparison cohort studyBinhua Dong0Huifeng Xue1Ye Li2Ping Li3Jiancui Chen4Tao Zhang5Lihua Chen6Diling Pan7Peizhong Liu8Pengming Sun9Laboratory of Gynecologic Oncology, Department of Gynecology, Fujian Maternity and Child Health Hospital, College of Clinical Medicine for Obstetrics & Gynecology and Pediatrics, Fujian Medical University, Fuzhou 350001, China; Fujian Key Laboratory of Women and Children's Critical Diseases Research, Fuzhou 350001, ChinaMedical Center of Cervical Disease and Colposcopy, Fujian Maternity and Child Health Hospital, Fuzhou 350001, ChinaLaboratory of Gynecologic Oncology, Department of Gynecology, Fujian Maternity and Child Health Hospital, College of Clinical Medicine for Obstetrics & Gynecology and Pediatrics, Fujian Medical University, Fuzhou 350001, ChinaDepartment of Gynecology and Obstetrics, Quanzhou First Hospital, Fujian Medical University, Quanzhou 362000, ChinaMedical Center of Cervical Disease and Colposcopy, Fujian Maternity and Child Health Hospital, Fuzhou 350001, ChinaCollege of Computer Science and Technology, Huaqiao University, Xiamen 361021, ChinaLaboratory of Gynecologic Oncology, Department of Gynecology, Fujian Maternity and Child Health Hospital, College of Clinical Medicine for Obstetrics & Gynecology and Pediatrics, Fujian Medical University, Fuzhou 350001, ChinaDepartment of Pathology, Fujian Maternity and Child Health Hospital, Fuzhou 350001, ChinaCollege of Engineering, Huaqiao University, Quanzhou 362021, China; School of Medicine, Huaqiao University, Quanzhou 362021, China; Corresponding authors.Laboratory of Gynecologic Oncology, Department of Gynecology, Fujian Maternity and Child Health Hospital, College of Clinical Medicine for Obstetrics & Gynecology and Pediatrics, Fujian Medical University, Fuzhou 350001, China; Fujian Key Laboratory of Women and Children's Critical Diseases Research, Fuzhou 350001, China; Corresponding authors.Colposcopy is an important technique in the diagnosis of cervical cancer. The development of computer-aided diagnosis methods can mitigate the shortage of colposcopists and improve the accuracy and efficiency of colposcopy examinations in China. This study proposes the Dense-U-Net model for colposcopy image recognition. This was a man–machine comparison cohort study. It presents a novel artificial intelligence (AI) model for the diagnosis of cervical lesions through colposcopy images using a Dense-U-Net image semantic segmentation algorithm. The Dense-U-Net model was created by applying the methods of “deepening the network structure,” “applying dropout” and “max pooling.” Moreover, image-based and population-based diagnostic performances of the AI algorithm and physicians with different levels of specialist experience were compared. In total, 2,475 participants were recruited, and 13,084 colposcopy images were included in this study. The diagnostic accuracy of the Dense-U-Net model increased significantly with increasing colposcopy images per patient. As the number of images in the training set increased, the diagnostic accuracy of the Dense-U-Net model for cervical intraepithelial neoplasm 3 or worse (CIN3+) diagnosis increased (P = 0.035). The rate of diagnostic accuracy (0.89 vs 0.85, P < 0.001) of CIN3+ lesions using the Dense-U-Net model was higher than that of expert colposcopists, and the missed diagnosis (0.06 vs 0.07, P = 0.002) and false positive (0.05 vs 0.08, P < 0.001) were lower. Moreover, Dense-U-Net is more accurate in diagnosing the type III cervical transformation zone, which is difficult to diagnose by experts (P < 0.001). The Dense-U-Net model also showed higher diagnostic accuracy for CIN3+ in an independent test set (P < 0.001). To diagnose the same 870 test images, the Dense-U-Net system took 1.76 ± 0.09 min, while the expert, senior, and junior colposcopists took 716.3 ± 49.76, 892.1 ± 92.30, and 3034.7 ± 259.51 min, respectively. The study successfully built a reliable, quick, and effective Dense-U-Net model to assist with colposcopy examinations.http://www.sciencedirect.com/science/article/pii/S2667325822004319Cervical lesionsDense-U-NetColposcopic imageLesion segmentationAuxiliary diagnosis |
| spellingShingle | Binhua Dong Huifeng Xue Ye Li Ping Li Jiancui Chen Tao Zhang Lihua Chen Diling Pan Peizhong Liu Pengming Sun Classification and diagnosis of cervical lesions based on colposcopy images using deep fully convolutional networks: A man-machine comparison cohort study Fundamental Research Cervical lesions Dense-U-Net Colposcopic image Lesion segmentation Auxiliary diagnosis |
| title | Classification and diagnosis of cervical lesions based on colposcopy images using deep fully convolutional networks: A man-machine comparison cohort study |
| title_full | Classification and diagnosis of cervical lesions based on colposcopy images using deep fully convolutional networks: A man-machine comparison cohort study |
| title_fullStr | Classification and diagnosis of cervical lesions based on colposcopy images using deep fully convolutional networks: A man-machine comparison cohort study |
| title_full_unstemmed | Classification and diagnosis of cervical lesions based on colposcopy images using deep fully convolutional networks: A man-machine comparison cohort study |
| title_short | Classification and diagnosis of cervical lesions based on colposcopy images using deep fully convolutional networks: A man-machine comparison cohort study |
| title_sort | classification and diagnosis of cervical lesions based on colposcopy images using deep fully convolutional networks a man machine comparison cohort study |
| topic | Cervical lesions Dense-U-Net Colposcopic image Lesion segmentation Auxiliary diagnosis |
| url | http://www.sciencedirect.com/science/article/pii/S2667325822004319 |
| work_keys_str_mv | AT binhuadong classificationanddiagnosisofcervicallesionsbasedoncolposcopyimagesusingdeepfullyconvolutionalnetworksamanmachinecomparisoncohortstudy AT huifengxue classificationanddiagnosisofcervicallesionsbasedoncolposcopyimagesusingdeepfullyconvolutionalnetworksamanmachinecomparisoncohortstudy AT yeli classificationanddiagnosisofcervicallesionsbasedoncolposcopyimagesusingdeepfullyconvolutionalnetworksamanmachinecomparisoncohortstudy AT pingli classificationanddiagnosisofcervicallesionsbasedoncolposcopyimagesusingdeepfullyconvolutionalnetworksamanmachinecomparisoncohortstudy AT jiancuichen classificationanddiagnosisofcervicallesionsbasedoncolposcopyimagesusingdeepfullyconvolutionalnetworksamanmachinecomparisoncohortstudy AT taozhang classificationanddiagnosisofcervicallesionsbasedoncolposcopyimagesusingdeepfullyconvolutionalnetworksamanmachinecomparisoncohortstudy AT lihuachen classificationanddiagnosisofcervicallesionsbasedoncolposcopyimagesusingdeepfullyconvolutionalnetworksamanmachinecomparisoncohortstudy AT dilingpan classificationanddiagnosisofcervicallesionsbasedoncolposcopyimagesusingdeepfullyconvolutionalnetworksamanmachinecomparisoncohortstudy AT peizhongliu classificationanddiagnosisofcervicallesionsbasedoncolposcopyimagesusingdeepfullyconvolutionalnetworksamanmachinecomparisoncohortstudy AT pengmingsun classificationanddiagnosisofcervicallesionsbasedoncolposcopyimagesusingdeepfullyconvolutionalnetworksamanmachinecomparisoncohortstudy |