BackgroundColposcopy is an important method in the diagnosis of cervical lesions. However, experienced colposcopists are lacking at present, and the training cycle is long. Therefore, the artificial intelligence-based colposcopy-assisted examination has great prospects. In this paper, a cervical lesion segmentation model (CLS-Model) was proposed for cervical lesion region segmentation from colposcopic post-acetic-acid images and accurate segmentation results could provide a good foundation for further research on the classification of the lesion and the selection of biopsy site.MethodsFirst, the improved Faster Region-convolutional neural network (R-CNN) was used to obtain the cervical region without interference from other tissues or instruments. Afterward, a deep convolutional neural network (CLS-Net) was proposed, which used EfficientNet-B3 to extract the features of the cervical region and used the redesigned atrous spatial pyramid pooling (ASPP) module according to the size of the lesion region and the feature map after subsampling to capture multiscale features. We also used cross-layer feature fusion to achieve fine segmentation of the lesion region. Finally, the segmentation result was mapped to the original image.ResultsExperiments showed that on 5455 LSIL+ (including cervical intraepithelial neoplasia and cervical cancer) colposcopic post-acetic-acid images, the accuracy, specificity, sensitivity, and dice coefficient of the proposed model were 93.04%, 96.00%, 74.78%, and 73.71%, respectively, which were all higher than those of the mainstream segmentation model.ConclusionThe CLS-Model proposed in this paper has good performance in the segmentation of cervical lesions in colposcopic post-acetic-acid images and can better assist colposcopists in improving the diagnostic level.
High-risk human papillomavirus (HPV) persistent infection is the major tumorigenesis factor for cervical cancer (CC). However, the incidence of HPV-negative CC is 5% to 30% with different HPV detection methods. High-risk HPV E6/E7 mRNA in situ hybridization (RISH) can detect HPV-driven tumors. Our study aimed to explore whether HPV typing-negative CC was caused by HPV infection. The tissues of CC patients with HPV typing results, collected from cervical biopsies, conization, or hysterectomies, were submitted to RISH using RNAscope chromogenicin. Immunohistochemistry was performed to evaluate the expression of p16INK4a and Ki-67. A total of 308 women with HPV typing results were enrolled, and 30 (9.74%) cases of HPV typing were negative. In HPV typingnegative CCs, 28/30 (93.3%) were positive for RISH, which contained 22/22 (100%) squamous cell carcinomas and 6/8 (75%) adenocarcinomas. RISH was positive in 278/278 (100%) HPV typing-positive CCs, which included 232/232 (100%) squamous cell carcinomas and 46/46 (100%) adenocarcinomas. Positive RISH in HPV typing-negative CC was significantly lower than in the HPV typing-positive group (P = 0.002, 95% confidence interval: 0.848-1.027). However, this significant difference only existed in adenocarcinoma. No significant differences were seen in the expression of p16INK4a and Ki-67 (all P > 0.05). HPV typing may cause misdiagnosis in 9.74% of CC patients, and HPV E6/E7 mRNA can detect HPV in CC with HPV typing-negative patients. This approach could provide a novel option to accurately detect high-risk HPVs in cervical tumors and help to eliminate the percentage of misdiagnosed HPV-related cases.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.